A content recommendation method and device, computer equipment and a storage medium

Abstract

The embodiment of the application belongs to the field of artificial intelligence and big data, and relates to a content recommendation method, which comprises the following steps: acquiring user browsing records in a target time period and the browsing times of each content category corresponding to a user preference pool; determining a content preference attribute according to the user browsing records, and determining a first recommendation priority according to the browsing times of each content category, the first recommendation priority being the recommendation priority of the content category in personalized content; acquiring a second recommendation priority, determining a category preference attribute according to the first recommendation priority and the second recommendation priority, and the second recommendation priority being a preset recommendation priority of personalized content and default content; and determining target recommendation content according to the content preference attribute and the category preference attribute. The application also provides a content recommendation device, a computer device and a storage medium. In addition, the application also relates to blockchain technology, and the user browsing records, the content category and the browsing times can be stored in the blockchain. The application improves the accuracy of content recommendation.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of artificial intelligence and big data technology, and particularly relates to a content recommendation method and device, computer equipment and a storage medium. BACKGROUND

[0002] In the prior art, content recommendation is performed according to user behavior habits or interests, but the focus of the pushed content or the considered dimensions are not comprehensive enough in the process of pushing the content to the user client, so that the pushed content browsed by the user lacks regularity and focus, and the content recommendation accuracy is insufficient. SUMMARY

[0003] The embodiments of the present application aim to provide a content recommendation method, device, computer equipment and storage medium to solve the problem of insufficient content recommendation accuracy in the prior art.

[0004] To solve the above technical problems, the embodiments of the present application provide a content recommendation method, which adopts the following technical solutions:

[0005] Obtain the user browsing records in a target time period and the browsing times of each content category in a user preference pool;

[0006] Determine a content preference attribute according to the user browsing records, and determine a first recommendation priority according to the browsing times of each content category, wherein the first recommendation priority is the recommendation priority of the content category in the personalized content;

[0007] Obtain a second recommendation priority, and determine a category preference attribute according to the first recommendation priority and the second recommendation priority, wherein the second recommendation priority is a preset recommendation priority of the personalized content and the default content;

[0008] Determine a target recommendation content according to the content preference attribute and the category preference attribute.

[0009] Further, before the step of obtaining the user browsing records in a target time period and the browsing times of each content category in a user preference pool, the method further comprises:

[0010] Determine whether the user preference pool contains a content category;

[0011] If the user preference pool does not contain the content category, obtain a comprehensive recommendation rule, and recommend content according to the comprehensive recommendation rule;

[0012] The step of obtaining the user preference pool comprises:

[0013] extracting all the content categories and the corresponding number of times of browsing from the user preference pool if the user preference pool contains the content categories.

[0014] Further, before the step of obtaining the user browsing record in the target time period and the number of times of browsing corresponding to each content category in the user preference pool, the method further comprises:

[0015] obtaining the number of times of browsing corresponding to each content category in the first preset time period in the user browsing record.

[0016] if the number of times of browsing corresponding to each content category in the first preset time period meets a preset number threshold, adding all the content categories meeting the preset number threshold and the number of times of browsing to the user preference pool.

[0017] Further, the step of determining the content preference attribute according to the user browsing record comprises:

[0018] extracting the content attribute of all the browsed content and the number of times of exposure of the content attribute from the user browsing record, wherein the content attribute represents the presentation form of the browsed content.

[0019] calculating a first weight value of each content attribute according to the content attribute of all the browsed content and the number of times of exposure of the content attribute.

[0020] determining the content preference attribute of the target recommended content according to the first weight value of each content data.

[0021] Further, the step of determining the first recommended priority according to the number of times of browsing corresponding to each content category comprises:

[0022] calculating a second weight value corresponding to each content category according to the number of times of browsing corresponding to each content category.

[0023] determining the first recommended priority of each content category in the individual content according to the second weight value corresponding to each content category.

[0024] Further, the step of calculating a second weight value corresponding to each content category according to the number of times of browsing corresponding to each content category comprises:

[0025] calculating the total number of times of browsing according to the number of times of browsing corresponding to each content category.

[0026] respectively calculating the ratio of the number of times of browsing corresponding to each content category to the total number of times of browsing, and taking the ratio as the second weight value.

[0027] Further, after the step of determining the target recommendation content according to the content preference attribute and the category preference attribute, the method further comprises:

[0028] If the number of times of browsing corresponding to the content category in the user preference pool is not increased in a second preset time period, deleting the content category whose number of times of browsing is not increased in the second preset time period.

[0029] Further, after the step of determining the target recommendation content according to the content preference attribute and the category preference attribute, the method further comprises:

[0030] If the number of times of browsing corresponding to all content categories in the user preference pool is not increased in a third preset time period, deleting all content categories in the user preference pool.

[0031] To solve the above technical problems, the embodiment of the present application further provides a content recommendation device, which adopts the technical scheme as follows:

[0032] The first acquisition module is configured to acquire user browsing records in a target time period and the number of times of browsing corresponding to each content category in a user preference pool.

[0033] The first determination module is configured to determine a content preference attribute according to the user browsing records, and determine a first recommendation priority according to the number of times of browsing corresponding to each content category, wherein the first recommendation priority is a recommendation priority of a content category in a personalized content.

[0034] The second determination module is configured to acquire a second recommendation priority, and determine a category preference attribute according to the first recommendation priority and the second recommendation priority, wherein the second recommendation priority is a preset recommendation priority of the personalized content and a default content.

[0035] The first recommendation module is configured to determine a target recommendation content according to the content preference attribute and the category preference attribute.

[0036] To solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the technical scheme as follows:

[0037] The computer device comprises a memory and a processor, the memory stores computer readable instructions, and the processor executes the computer readable instructions to realize the steps of the content recommendation method.

[0038] To solve the above technical problems, the embodiment of the present application further provides a computer readable storage medium, which adopts the technical scheme as follows:

[0039] The computer readable storage medium stores computer readable instructions, which are executed by the processor to implement the steps of the content recommendation method.

[0040] Compared with the prior art, the embodiment of the application has the following beneficial effects: by obtaining the user browsing record in the target time period and the browsing times of each content category in the user preference pool, determining the content preference attribute according to the user browsing record, and determining the first recommendation priority according to the browsing times of each content category, wherein the first recommendation priority is the recommendation priority of the content category in the personalized content, obtaining the second recommendation priority, determining the category preference attribute according to the first recommendation priority and the second recommendation priority, wherein the second recommendation priority is the preset recommendation priority of the personalized content and the default content, and determining the target recommendation content according to the content preference attribute and the category preference attribute. The application determines the content preference attribute according to the user browsing record in the target time period, and determines the category preference attribute according to the second recommendation priority and the first recommendation priority determined by the browsing times of each content category, constructs the target recommendation content according to the two dimensions of the content preference attribute and the category preference attribute, so as to make the target recommendation content meet the behavior modification and preference of the user, and improve the accuracy of content recommendation. BRIEF DESCRIPTION OF DRAWINGS

[0041] In order to more clearly illustrate the schemes in the application, the drawings needed in the description of the embodiments of the application will be briefly introduced. Obviously, the drawings in the following description are some embodiments of the application, and other drawings can be obtained by those skilled in the art without creative labor on the basis of these drawings.

[0042] Figure 1 is an exemplary system architecture diagram in which the application can be applied;

[0043] Figure 2 is a flowchart of one embodiment of the content recommendation method according to the application

[0044] Figure 3 is a structural schematic diagram of one embodiment of the content recommendation device according to the application;

[0045] Figure 4 is a structural schematic diagram of one embodiment of the computer device according to the application. DETAILED DESCRIPTION

[0046] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used in the description herein is for describing particular embodiments only and is not intended to be limiting of the application; the use herein of terms such as "comprise" and "comprising", or "have" and "having", or "include" and "including" and any variations thereof, is intended to cover a non-exclusive inclusion; the use herein of terms such as "first", "second" and the like is intended to distinguish between similar objects going in different directions, and is not intended to denote a particular order.

[0047] Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase that an embodiment in various places in the specification are not necessarily all referring to the same embodiment, nor are they necessarily mutually exclusive or alternative embodiments.

[0048] In order to make the technical personnel in the art better understand the scheme of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings.

[0049] As shown in Figure 1 The system architecture 100 can include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is a medium for providing a communication link between the terminal devices 101, 102, 103 and the server 105. The network 104 can include various connection types, such as wired, wireless communication links, or optical fiber cables, etc.

[0050] A user can use the terminal devices 101, 102, 103 to interact with the server 105 through the network 104 to receive or send messages, etc. Various communication client applications can be installed on the terminal devices 101, 102, 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0051] The terminal devices 101, 102, 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smartphones, tablet computers, e-book readers, MP3 (Moving Picture Experts Group Audio Layer III) players, MP4 (Moving Picture Experts Group Audio Layer IV) players, laptop portable computers, and desktop computers, etc.

[0052] Server 105 can be a server that provides various services, such as a backend server that supports the pages displayed on terminal devices 101, 102, and 103.

[0053] It should be noted that the content recommendation method provided in this application embodiment is generally executed by a server / terminal device, and correspondingly, the content recommendation device is generally set in the server / terminal device.

[0054] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0055] Continue to refer to Figure 2 A flowchart of an embodiment of the content recommendation method according to this application is shown. The content recommendation method includes the following steps:

[0056] Step S201: Obtain user browsing records within the target time period and the number of views corresponding to each content category in the user preference pool.

[0057] In this embodiment, the content recommendation method runs on an electronic device (e.g., Figure 1 The server / terminal device shown can receive user browsing records for a target time period and the number of views for each content category in the user preference pool from the system (such as the server) via wired or wireless connection. It should be noted that the aforementioned wireless connection methods may include, but are not limited to, 3G / 4G / 5G connections, WiFi connections, Bluetooth connections, WiMAX connections, Zigbee connections, UWB (ultra-wideband) connections, and other currently known or future known wireless connection methods.

[0058] Specifically, the unit of the target time period mentioned above can be seconds, minutes, days, months, etc., and the target time period can be adjusted to meet different usage needs.

[0059] User browsing history is a record generated when browsing content. This browsing history includes the browsed content, the content attributes corresponding to the browsed content, the number of exposures for each content attribute, the content category corresponding to the browsed content, and the number of views for each content category. It should be noted that the above-mentioned content attributes represent the presentation format of the browsed content, such as video, article, or topic, the above-mentioned exposures represent the number of times the content attributes appear, the above-mentioned content categories represent the category to which the browsed content belongs, such as car insurance, car brand, daily life, etc., and the above-mentioned number of views represents the number of times the content category appears.

[0060] The user preference pool is used to store the content categories preferred by the user and the number of times each content category is browsed, and the specific steps of adding content categories to the user preference pool will be described below.

[0061] In step S202, the content preference attribute is determined according to the user browsing record, and the first recommendation priority is determined according to the number of times each content category is browsed. The first recommendation priority is the recommendation priority of the content category in the personalized content.

[0062] In this embodiment, the content preference attribute represents the content attribute preferred by the user.

[0063] The personalized content represents the content preferred by the user. In actual application, the preference degree of the user for each content category is determined according to the number of times each content category is browsed in the user preference pool, and then each content category is counted according to the preference degree of the user for each content category (see below for details) to determine the first recommendation priority.

[0064] In step S203, the second recommendation priority is obtained, and the category preference attribute is determined according to the first recommendation priority and the second recommendation priority. The second recommendation priority is the preset recommendation priority of the personalized content and the default content.

[0065] In this embodiment, the second recommendation priority has been preset, and the ratio of the personalized content to the default content is greater than 1 to make the finally determined category preference attribute conform to the individual characteristics of the user. In actual application, the proportion of the personalized content and the default content in the initial recommendation content is determined according to the second recommendation priority, and the initial recommendation content includes the personalized content and the default content.

[0066] The category preference attribute represents the content category preferred by the user. In actual application, the proportion of the personalized content corresponding to the individual characteristics of the user (such as content preference) in the initial recommendation content is high according to the second recommendation priority, and the content categories in the personalized content are prioritized according to the first recommendation priority (see below for details), so that the finally determined category preference attribute conforms to the individual characteristics of the user, and the accuracy of content recommendation is improved.

[0067] In step S204, the target recommendation content is determined according to the content preference attribute and the category preference attribute.

[0068] In the embodiment, the proportion of the personalized content and the default content in the initial recommended content is determined according to the category preference attribute, and the content attribute of the personalized content and the default content is respectively determined according to the content preference attribute, so that the target recommended content is constructed from the two dimensions of the content preference attribute (such as the preference attribute of video, article, etc.) and the category preference attribute (such as the preference attribute of car insurance, life, etc.), so that the target recommended content conforms to the behavior habit and preference of the user, and the accuracy of content recommendation is improved.

[0069] The application determines the content preference attribute through the user browsing record in the target time period, and determines the category preference attribute through the second recommendation priority and the first recommendation priority determined by the browsing times corresponding to each content category, and constructs the target recommended content according to the two dimensions of the content preference attribute and the category preference attribute, so that the target recommended content conforms to the behavior habit and preference of the user, and the accuracy of content recommendation is improved.

[0070] In some optional implementations, before the step S201 of acquiring the user preference pool, the method further includes:

[0071] determining whether the user preference pool contains the content category;

[0072] if the user preference pool does not contain the content category, acquiring a comprehensive recommendation rule, and recommending content according to the comprehensive recommendation rule;

[0073] The step of acquiring the user preference pool includes:

[0074] if the user preference pool contains the content category, extracting all the content categories and the browsing times corresponding to each content category from the user preference pool.

[0075] In the embodiment, the state of the user preference pool exists in two cases.

[0076] One is that the user preference pool does not contain the content category, which represents that the content category previously browsed by the user does not meet the condition of joining the user preference pool (for details, see below), the user is a new user or the content category of the user preference pool has been deleted; in this case, there is no content preference attribute and category preference attribute, and the video, article, topic and other content in the recommended content are determined with the same proportion, so that the recommended content with wide content coverage is performed in the case where the user preference is not determined.

[0077] The other is that the user preference pool contains the content category, which represents that the content category previously browsed by the user meets the condition of joining the user preference pool (for details, see below), and the steps S201 to S204 are executed.

[0078] In some optional implementation, before the step S201 of acquiring the browsing records of the user in the target time period and the browsing times of each content category in the user preference pool, the method further comprises the following steps of:

[0079] acquiring the browsing times of each content category in a first preset time period in the user browsing records;

[0080] if the browsing times of each content category in the first preset time period meet a preset number threshold, adding all the content categories meeting the preset number threshold and the browsing times of the content categories to the user preference pool.

[0081] In the embodiment, the unit of the first preset time period can be second, minute, day, month, etc., and the target time period can be adjusted to meet different use requirements.

[0082] For example, the first preset time period is one day, if the browsing times of each content category in the user browsing records in the day are less than the preset number threshold of 3, the content categories are not added to the user preference pool, otherwise, if the browsing times of each content category in the user browsing records in the day are greater than the preset number threshold of 3, the content categories are added to the user preference pool.

[0083] In this way, the user preference pool is continuously updated to effectively ensure that the finally determined recommended content meets the behavior habit and preference of the user, and the accuracy of content recommendation is improved.

[0084] In some optional implementation, the step S202 of determining the content preference attribute according to the user browsing records comprises the following steps of:

[0085] extracting all content attributes and the exposure times of the content attributes from the user browsing records, wherein the content attribute represents the presentation form of the browsed content;

[0086] calculating a first weight value of each content attribute according to all content attributes and the exposure times of the content attributes;

[0087] determining the content preference attribute of the target recommended content according to the first weight value of each content data.

[0088] In the embodiment, the user browsing records comprise a plurality of browsed contents, wherein one browsed content corresponds to one content attribute (for example, the browsed content of a car video corresponds to the content attribute of a video), each browsed content in the user browsing records is classified according to the content attribute, and the click times of the browsed contents with the same content attribute are accumulated to obtain the exposure times.

[0089] In actual application, the total exposure times is obtained by accumulating all the exposure times corresponding to the content attributes, and the ratio of the exposure times corresponding to each content attribute to the total exposure times is calculated as the first weight value. For example, the user browsing record includes A content attribute, B content attribute and C content attribute, wherein the exposure times corresponding to the A content attribute is 5, the exposure times corresponding to the B content attribute is 3, and the exposure times corresponding to the C content attribute is 1, then the total exposure times is 9, the first weight value corresponding to the A content attribute is 5 / 9, the first weight value corresponding to the B content attribute is 1 / 3, and the first weight value corresponding to the C content attribute is 1 / 9.

[0090] In some optional implementations, the step of determining the first recommendation priority according to the browsing times corresponding to each of the content categories comprises:

[0091] calculating a second weight value corresponding to each of the content categories according to the browsing times corresponding to each of the content categories;

[0092] determining the first recommendation priority of each of the content categories in the personalized content according to the second weight value corresponding to each of the content categories.

[0093] In this embodiment, for example, the personalized content includes A content category, B content category and C content category, wherein if the second weight value of the A content category, the second weight value of the B content category and the second weight value of the C content category decrease in turn, then the first recommendation priority in the personalized content is determined to be the A content category, the B content category and the C content category in turn.

[0094] In actual application, the content related to the content category with the largest second weight value (for example, the A content category described above) can be selected as the personalized content according to the first recommendation priority, or the content related to the target number of content categories (for example, the A content category and the B content category described above) can be selected as the personalized content according to the first recommendation priority in which the second weight values decrease from large to small, which is not limited here.

[0095] In some optional implementations, the step of calculating a second weight value corresponding to each of the content categories according to the browsing times corresponding to each of the content categories comprises:

[0096] calculating a total browsing times according to the browsing times corresponding to each of the content categories;

[0097] calculating the ratio of the browsing times corresponding to each of the content categories to the total browsing times respectively, and taking the ratio as the second weight value.

[0098] In the embodiment, the number of browsings corresponding to each content category is accumulated first to obtain the total number of browsings, and then the ratio of each content category to the total number of browsings is calculated, and the ratio is taken as the second weight value, so as to obtain the second weight value corresponding to each content category, so as to reflect the preference degree of the user to each content category.

[0099] For example, the A content category, the B content category and the C content category are included, the second weight value of the A content category, the second weight value of the B content category and the second weight value of the C content category decrease in turn, which indicates that the user prefers the A content category more, the B content category second, and so on. In this way, the recommended content conforms to the behavior habit and preference of the user, and the accuracy of the content recommendation is effectively ensured.

[0100] In some optional implementation manners, the step S204 further includes, after the step of determining the target recommended content according to the content preference attribute and the category preference attribute:

[0101] If the number of browsings corresponding to the content category in the user preference pool is not increased in the second preset time period, the content category whose number of browsings is not increased in the second preset time period is deleted.

[0102] And / or, after the step of determining the target recommended content according to the content preference attribute and the category preference attribute, the step further includes:

[0103] If the number of browsings corresponding to all content categories in the user preference pool is not increased in the third preset time period, all content categories in the user preference pool are deleted.

[0104] In the embodiment, the historical increase record represents the increase record of the number of browsings corresponding to the content category in the user preference pool.

[0105] In actual application, when a new content category is added to the user preference pool, the new content category needs to be matched with all content categories in the user preference pool first, to determine whether there is a content category corresponding to the new content category in the user preference pool. If yes, the number of browsings of the content category corresponding to the new content category in the user preference pool is increased by one, and the increase is recorded in the historical increase record. If not, a new content category corresponding to the new content category is created in the user preference pool, and the number of browsings of the content category corresponding to the new content category created in the user preference pool is increased by one, and the increase is recorded in the historical increase record.

[0106] In order to effectively ensure that the user preference pool conforms to the behavior habit and preference of the user, the content categories in the user preference pool are deleted after the second preset time period / third preset time period, so as to avoid the mutual interference of too many content categories in the user preference pool, and ensure the accuracy of the recommended content.

[0107] For example, if the number of times of browsing corresponding to the A content category of the user preference pool is not increased in a second preset time period (for example, 3 days), it is determined that the preference degree of the user for the content category is weakened, and the A content category of the user preference pool can be deleted.

[0108] For another example, when the number of times of browsing corresponding to each content category in the user preference pool is not increased in a third preset time period (for example, 7 days), it is represented that the preference degree of the user for all content categories in the user preference pool is weakened, and all content categories of the user preference pool can be deleted to reacquire the preferred content category of the user, so as to ensure the accuracy of the recommended content.

[0109] It should be emphasized that, in order to further ensure the privacy and security of the number of times of browsing corresponding to each content category in the user browsing record and the user preference pool, the privacy and security of the number of times of browsing corresponding to each content category in the user browsing record and the user preference pool can also be stored in a node of a block chain.

[0110] The block chain referred to in the present application is a new application mode of distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm and other computer technologies. The block chain (block chain) is essentially a decentralized database, which is a series of data blocks associated using cryptographic methods, each data block contains a batch of network transaction information, used to verify the validity (anti-fake) of the information and generate the next block. The block chain can include a block chain underlying platform, a platform product service layer and an application service layer.

[0111] The embodiments of the present application can acquire and process related data based on artificial intelligence technology. Among them, artificial intelligence (Artificial Intelligence, AI) is to use digital computers or digital computer controlled machines to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. Theory, method, technology and application system.

[0112] The basic technology of artificial intelligence generally includes technologies such as sensors, special artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction system, mechatronics, etc. The software technology of artificial intelligence mainly includes computer vision technology, robot technology, biometric technology, speech processing technology, natural language processing technology, and machine learning / deep learning, etc. several major directions.

[0113] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing relevant hardware through computer readable instructions, and the computer readable instructions can be stored in a computer readable storage medium. When the program is executed, the processes of the above-mentioned embodiment methods can be included. The storage medium can be a magnetic disc, an optical disc, a read-only memory (ROM), a non-volatile storage medium, or a random access memory (RAM).

[0114] It should be understood that, although each step in the flowchart of the accompanying drawings is shown in sequence according to the direction of the arrow, these steps are not necessarily executed in sequence according to the direction of the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and they can be executed in other orders. Moreover, at least part of the steps in the flowchart of the accompanying drawings can include multiple sub-steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence is not necessarily sequential, but can be alternately executed with other steps or sub-steps or stages of other steps.

[0115] Further referring to Figure 3 , as an implementation of the method shown in the above Figure 2 , the present application provides an embodiment of a content recommendation device, which corresponds to the method embodiment shown in Figure 2 , and the device can be specifically applied to various electronic devices.

[0116] As shown in Figure 3 , the content recommendation device 300 described in the embodiment includes a first obtaining module 301, a first determining module 302, a second determining module 303, and a first recommendation module 304. Wherein:

[0117] The first obtaining module 301 is configured to obtain user browsing records in a target time period and a browsing frequency corresponding to each content category in a user preference pool;

[0118] The first determining module 302 is configured to determine a content preference attribute according to the user browsing records, and determine a first recommendation priority according to the browsing frequency corresponding to each content category, wherein the first recommendation priority is the recommendation priority of the content category in the personalized content;

[0119] The second determining module 303 is configured to obtain a second recommendation priority, and determine a category preference attribute according to the first recommendation priority and the second recommendation priority, wherein the second recommendation priority is a preset recommendation priority of the personalized content and the default content.

[0120] The first recommendation module 304 is configured to determine target recommendation content according to the content preference attribute and the category preference attribute.

[0121] The application determines the content preference attribute according to the user browsing record in the target time period, and determines the category preference attribute according to the second recommendation priority and the first recommendation priority determined according to the browsing frequency of each content category, and constructs the target recommendation content according to the content preference attribute and the category preference attribute in two dimensions, so as to make the target recommendation content meet the behavior modification and preference of the user, and improve the accuracy of content recommendation.

[0122] In some optional implementation manners, the method further includes a judging module and a second recommendation module. Wherein:

[0123] The judging module is configured to judge whether the user preference pool contains the content category.

[0124] The second recommendation module is configured to obtain a comprehensive recommendation rule if the user preference pool does not contain the content category, and recommend content according to the comprehensive recommendation rule.

[0125] The first obtaining module 301 includes a first extraction submodule. Wherein:

[0126] The first extraction submodule is configured to extract all the content categories and the browsing frequency corresponding to each content category from the user preference pool if the user preference pool contains the content category.

[0127] In some optional implementation manners, the method further includes a second obtaining module and a data adding module. Wherein:

[0128] The second obtaining module obtains the browsing frequency corresponding to each content category in a first preset time period in the user browsing record.

[0129] The data adding module is configured to add all the content categories and the browsing frequency corresponding to the content categories to the user preference pool if the browsing frequency corresponding to each content category in the first preset time period meets a preset frequency threshold.

[0130] In some optional implementation manners, the first determining module 302 includes a second extraction submodule, a first calculation submodule and a first determining submodule. Wherein:

[0131] a second extraction submodule configured to extract content attributes of all the browsing contents and exposure times of the content attributes from the user browsing record, wherein the content attributes represent presentation forms of the browsing contents;

[0132] a first calculation submodule configured to calculate first weight values of each of the content attributes according to the content attributes of all the browsing contents and the exposure times of the content attributes;

[0133] a first determination submodule configured to determine content preference attributes of the target recommended content according to the first weight values of each of the content data.

[0134] In some optional implementation manners, the first determination module 302 includes a second calculation submodule and a second determination submodule. Wherein:

[0135] the second calculation submodule is configured to calculate second weight values corresponding to each of the content categories according to the browsing times corresponding to each of the content categories;

[0136] the second determination submodule is configured to determine first recommended priorities of each of the content categories in the personalized content according to the second weight values corresponding to each of the content categories.

[0137] In some optional implementation manners, the second calculation submodule includes a first calculation unit and a second calculation unit. Wherein:

[0138] the first calculation unit is configured to calculate a total browsing time according to the browsing times corresponding to each of the content categories;

[0139] the second calculation unit is configured to calculate a ratio of the browsing time corresponding to each of the content categories to the total browsing time respectively, and take the ratio as the second weight value.

[0140] In some optional implementation manners, the application further includes a first deletion module and / or a second deletion module. Wherein:

[0141] the first deletion module is configured to delete the content categories for which the browsing times are not increased in a second preset time period, if the browsing times corresponding to the content categories in the user preference pool are not increased in the second preset time period;

[0142] the second deletion module is configured to delete all the content categories in the user preference pool, if the browsing times corresponding to all the content categories in the user preference pool are not increased in a third preset time period.

[0143] To solve the above technical problems, the application further provides a computer device. For details, please refer to Figure 4 , Figure 4 is a basic structure block diagram of the computer device of the application.

[0144] The computer device 4 comprises a memory 41, a processor 42, and a network interface 43, which are communicatively connected by a system bus. It should be noted that only the computer device 4 with components 41-43 is shown in the figure, but it should be understood that all the shown components are not required to be implemented, and more or fewer components can be alternatively implemented. Among them, those skilled in the art can understand that the computer device herein is a device capable of automatically performing numerical calculation and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0145] The computer device can be a desktop computer, a notebook computer, a palm computer, a cloud server, and the like. The computer device can interact with a user through a keyboard, a mouse, a remote controller, a touchpad, a voice control device, and the like.

[0146] The memory 41 comprises at least one type of readable storage medium, including a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., an SD or DX memory, etc.), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, and the like. In some embodiments, the memory 41 can be an internal storage unit of the computer device 4, such as a hard disk or a memory of the computer device 4. In other embodiments, the memory 41 can also be an external storage device of the computer device 4, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, and the like. Of course, the memory 41 can also include both the internal storage unit and the external storage device of the computer device 4. In the present embodiment, the memory 41 is generally used to store an operating system and various application software installed in the computer device 4, such as computer readable instructions of the content recommendation method, and the like. In addition, the memory 41 can also be used to temporarily store various data that have been output or will be output.

[0147] The processor 42 may, in some embodiments, be a Central Processing Unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip. The processor 42 is generally used to control the overall operation of the computer device 4. In the present embodiment, the processor 42 is configured to execute computer-readable instructions stored in the memory 41 or to process data, such as computer-readable instructions for implementing the content recommendation method.

[0148] The network interface 43 may include a wireless network interface or a wired network interface, and is generally used to establish a communication connection between the computer device 4 and other electronic devices.

[0149] The present application determines the content preference attribute based on the user browsing record in the target time period, and determines the category preference attribute based on the second recommendation priority and the first recommendation priority determined by the browsing times corresponding to each content category, and constructs the target recommendation content in two dimensions of the content preference attribute and the category preference attribute, so that the target recommendation content conforms to the behavior modification and preference of the user, and improves the accuracy of content recommendation.

[0150] The present application also provides another embodiment, i.e., a computer-readable storage medium storing computer-readable instructions, which can be executed by at least one processor to make the at least one processor execute the steps of the content recommendation method as described above.

[0151] The present application determines the content preference attribute based on the user browsing record in the target time period, and determines the category preference attribute based on the second recommendation priority and the first recommendation priority determined by the browsing times corresponding to each content category, and constructs the target recommendation content in two dimensions of the content preference attribute and the category preference attribute, so that the target recommendation content conforms to the behavior modification and preference of the user, and improves the accuracy of content recommendation.

[0152] From the above description of the embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment method can be realized by means of software and a general hardware platform as required, and of course can also be realized by hardware, but in many cases the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product, which is stored in a storage medium (such as a ROM / RAM, a magnetic disk, or an optical disk), and includes a plurality of instructions for causing a terminal device (which can be a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the methods described in the various embodiments of the present application.

[0153] Obviously, the above-described embodiments are only some embodiments but not all the embodiments of the present application, the preferred embodiments of the present application are shown in the drawings, but do not limit the patent scope of the present application. The present application can be implemented in many different forms, and conversely, the purpose of providing these embodiments is to make the disclosure of the present application more thorough and comprehensive. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing specific embodiments, or make equivalent replacements to some technical features therein. Any equivalent structure made by using the content of the specification and drawings, directly or indirectly applied to other related technical fields, is also within the patent protection scope of the present application.

Claims

1. A content recommendation method characterized by, The method comprises the following steps: obtaining user browsing records in a target time period and the number of times of browsing each content category in a user preference pool; determining a content preference attribute according to the user browsing records and determining a first recommendation priority according to the number of times of browsing each content category, wherein the first recommendation priority is the recommendation priority of the content category in personalized content; obtaining a second recommendation priority, determining a category preference attribute according to the first recommendation priority and the second recommendation priority, wherein the second recommendation priority is a preset recommendation priority of the personalized content and default content; determining target recommendation content according to the content preference attribute and the category preference attribute, wherein the initial recommendation content comprises personalized content and default content, the proportion of the personalized content and the default content in the initial recommendation content is determined according to the category preference attribute, and the content attribute of the personalized content and the default content is respectively determined according to the content preference attribute to determine the target recommendation content.

2. The content recommendation method according to claim 1, characterized by, Before the step of obtaining the user browsing records in the target time period and the number of times of browsing each content category in the user preference pool, the method further comprises the following steps: determining whether the user preference pool contains a content category; if the user preference pool does not contain the content category, obtaining a comprehensive recommendation rule and recommending content according to the comprehensive recommendation rule; the step of obtaining the user preference pool comprises the following steps: if the user preference pool contains the content category, extracting all the content categories and the number of times of browsing each content category from the user preference pool.

3. The content recommendation method according to claim 1 or 2, characterized by, Before the step of obtaining the user browsing records in the target time period and the number of times of browsing each content category in the user preference pool, the method further comprises the following steps: obtaining the number of times of browsing each content category in a first preset time period in the user browsing records; if the number of times of browsing each content category in the first preset time period meets a preset number threshold, adding all the content categories meeting the preset number threshold and the number of times of browsing to the user preference pool.

4. The content recommendation method according to claim 1 or 2, characterized by, The step of determining a content preference attribute according to the user browsing records comprises the following steps: extracting the content attribute of all browsing content and the number of times of exposure of the content attribute from the user browsing records, wherein the content attribute represents the presentation form of the browsing content; calculating a first weight value of each content attribute according to the content attribute of all browsing content and the number of times of exposure of the content attribute; determining the content preference attribute of the target recommendation content according to the first weight value of each content data.

5. The content recommendation method according to claim 1 or 2, characterized by, The step of determining a first recommendation priority according to the number of times of browsing each content category comprises the following steps: calculating a second weight value corresponding to each content category according to the number of times of browsing each content category; determining the first recommendation priority of each content category in personalized content through the second weight value corresponding to each content category.

6. The content recommendation method according to claim 4, characterized by, The step of calculating a second weight value corresponding to each content category according to the number of times of browsing each content category comprises the following steps: calculating a total number of times of browsing according to the number of times of browsing each content category; Calculate the ratio of the number of times each content category is browsed to the total number of times browsed, and use the ratio as a second weight value.

7. The content recommendation method according to claim 1 or 2, characterized by, After the step of determining the target recommended content according to the content preference attribute and the category preference attribute, the method further comprises: If the number of times each content category is browsed in the user preference pool does not increase in a second preset time period, delete the content category whose number of times browsed does not increase in the second preset time period. And / or, after the step of determining the target recommended content according to the content preference attribute and the category preference attribute, the method further comprises: If the number of times each content category is browsed in the user preference pool does not increase in a third preset time period, delete all content categories in the user preference pool.

8. A content recommendation apparatus characterized by comprising: Comprise: A first acquisition module for acquiring user browsing records in a target time period and the number of times each content category is browsed in a user preference pool; A first determination module for determining a content preference attribute according to the user browsing records and determining a first recommendation priority according to the number of times each content category is browsed, wherein the first recommendation priority is the recommendation priority of a content category in personalized content; A second determination module for acquiring a second recommendation priority and determining a category preference attribute according to the first recommendation priority and the second recommendation priority, wherein the second recommendation priority is a preset recommendation priority of the personalized content and default content; And A first recommendation module for determining a target recommended content according to the content preference attribute and the category preference attribute, wherein the initial recommended content comprises personalized content and default content, determining the proportion of personalized content and default content in the initial recommended content according to the category preference attribute, and determining the content attribute of each of the personalized content and the default content according to the content preference attribute to determine the target recommended content.

9. A computer device comprising a memory and a processor, wherein the memory stores computer readable instructions, and the processor executes the computer readable instructions to implement the steps of the content recommendation method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer readable instructions, and the computer readable instructions are executed by the processor to implement the steps of the content recommendation method according to any one of claims 1 to 7.

Images