A method for screening recommended content, related device and related medium

Abstract

The present application provides a method for screening recommended content, a related device and a related medium, which can be applied to a server. The method for screening recommended content provided in the embodiment of the present application can reasonably recall the recommended content related to the user's historical negative feedback behavior and re-recommend it to the user, which helps to increase the exposure of various recommended content and also helps to determine the user's latest browsing habits and browsing preferences, thereby further improving the user's corresponding user portrait, and can achieve the purpose of improving the user's usage experience.

Description

Technical Field

[0001] The present application relates to the field of communication technology, and in particular to a method for screening recommended content, a related device and a related medium. Background Art

[0002] With the rapid development of the Internet, users can shop, socialize and learn about social hot spots through the Internet. In order to improve their own user retention rate and user stickiness, major software and / or network platforms have begun to vigorously develop and improve recommendation systems. Recommendation systems are widely used in the video and audio industry and the e-commerce industry. While helping merchants to obtain higher profits, they also help users quickly discover potential content of interest (audio and video, products, news and other information flows), thereby improving user experience.

[0003] At present, the existing technology can remove the recommended content corresponding to the negative feedback operation from the recommendation list according to the user's negative feedback operation (such as blacklisting and deletion), and no longer recommend the recommended content related to the negative feedback operation to the user, so as to achieve the purpose of retaining the user. However, the user's preferences are not static. When the user becomes interested in the recommended content that has previously had negative feedback operations, the existing technology cannot follow up the user's latest browsing preferences, and thus cannot recommend appropriate recommended content to the user more accurately. Therefore, how to adjust the recommendation mechanism of the recommended content after the user's negative feedback operation is a problem that technicians in this field urgently need to solve. Summary of the invention

[0004] In a first aspect, the present application provides a method for screening recommended content, a related device, and a related medium. The method can be applied to a server, and the method may include:

[0005] Receiving first negative feedback information sent by a user terminal, where the first negative feedback information may include user identification information, a first recommendation tag, and a negative feedback type, where the first recommendation tag is used to indicate a recommendation tag associated with the recommended content corresponding to the first negative feedback information;

[0006] Updating a user portrait corresponding to the user identification information based on the first negative feedback information;

[0007] Filtering target recommended content that meets preset conditions based on the updated user profile, where the target recommended content is the recommended content associated with the recommended tag indicated by the historical negative feedback information corresponding to the user identification information;

[0008] A first recommendation list is generated based on the target recommended content and the updated user profile.

[0009] By implementing the method provided in the first aspect, the server can update the user's user portrait based on the user's negative feedback operation, and can also recall the recommended content related to the user's historical negative feedback behavior and re-recommend it to the user, which helps the server determine the user's latest browsing habits and browsing preferences, thereby further improving the user's corresponding user portrait and achieving the purpose of improving the user's usage experience.

[0010] In one implementation of the method provided in the first aspect, the user portrait can be used to indicate the user's personal attributes, industry preferences, and shopping preferences. The personal attributes may include at least one of gender, age, education level, and IP address.

[0011] By implementing the method provided in the above embodiment, the server can analyze the user through multiple dimensions, which helps to better understand the user's usage needs and usage preferences, thereby providing the user with more accurate recommended content and improving the user's usage experience.

[0012] In implementing the method provided in the first aspect, in one implementation, the user portrait may include a negative feedback adjacency matrix;

[0013] Updating the user portrait corresponding to the user identification information based on the first negative feedback information may include:

[0014] Based on the first recommended label, the value of the target matrix point in the negative feedback adjacency matrix is ​​set to 1.

[0015] By implementing the method provided in the above embodiment, the server marks the user's negative feedback operation on a certain recommendation tag (or recommended content) by changing the value of the matrix point in the negative feedback adjacency matrix, which helps the server to use a suitable formula to infer the target recommended content that the user may be interested in, thereby improving the accuracy of the server's screening of recommended content and ensuring the user's usage experience.

[0016] Implementing the method provided in the first aspect, in one embodiment, the target matrix point is determined based on user identification information and a first recommended label, the user identification information is used to determine the row corresponding to the target matrix point in the negative feedback adjacency matrix, and the first recommended label is used to determine the column corresponding to the target matrix point in the negative feedback adjacency matrix.

[0017] By implementing the method provided in the above embodiment, the server uses user identification information and recommendation tags to generate a negative feedback adjacency matrix, which helps to more clearly record the user's preferences for each recommendation tag, thereby ensuring the accuracy of the server's screening of target recommended content and improving user satisfaction with the recommended content.

[0018] In one implementation of the method provided in the first aspect, screening target recommended content that meets preset conditions based on the updated user portrait may include:

[0019] Activation parameters corresponding to each recommended tag based on the updated user profile;

[0020] Determine the recommended label corresponding to the activation parameter greater than the preset threshold as the target recommended label;

[0021] The recommended content associated with the target recommendation tag is determined as the target recommended content.

[0022] By implementing the method provided in the above embodiment, the server can quantify the recommendation index of each recommendation tag by calculating the activation parameters, which helps to more scientifically represent the attractiveness of each recommendation tag to the user, thereby helping to select recommendation tags that are more in line with the user's browsing habits or browsing preferences (i.e., determining the recommendation tag corresponding to the activation parameter greater than the preset threshold as the target recommendation tag), helping to improve the user's satisfaction with the recommended content, thereby improving the user stickiness and user retention rate of the software and / or website.

[0023] In one implementation of the method provided in the first aspect, the user portrait may further include a user feature matrix, a time matrix, a first activation function, a time scale adjustment function, and a recommended content feature matrix;

[0024] The method may include:

[0025] Based on the user feature matrix, the time matrix, the first activation function, the time scale adjustment function and the recommended content feature matrix, calculate the first negative feedback activation matrix corresponding to the user portrait;

[0026] Performing mapping processing on the first negative feedback activation matrix to generate a second negative feedback activation matrix;

[0027] Screen out target matrix points whose values ​​in the second negative feedback activation matrix are less than a preset threshold;

[0028] Determine the target recommendation content based on the target matrix point.

[0029] By implementing the method provided in the above embodiment, the server can map the numerical value of each matrix point in the negative feedback activation matrix to a preset interval, which helps to quantify the recommendation index of each recommended tag, thereby helping to select recommended tags that are more in line with the user's browsing habits or browsing preferences, thereby achieving the purpose of improving the user's satisfaction with the recommended content.

[0030] In one embodiment, the method provided in the first aspect may include:

[0031] The first negative feedback activation matrix is ​​calculated based on the following formula,

[0032]

[0033] Among them, S is the first negative feedback activation matrix, X is the user feature matrix, is the negative feedback adjacency matrix, s is the first activation function, α is the time scale adjustment function, T is the time matrix, and X′ is the recommended content feature matrix;

[0034] The first negative feedback activation matrix is ​​mapped by using a mapping function, and the values ​​of each matrix point in the first negative feedback activation matrix are mapped to the interval (0,1), so as to generate a second negative feedback activation matrix;

[0035] Filtering out the target matrix point in the second negative feedback activation matrix, and determining the recommended label and user identification information corresponding to the target matrix point based on the row and column information of the target matrix point;

[0036] The recommended content associated with the recommended tag corresponding to the target matrix point is determined as the target recommended content.

[0037] By implementing the method provided in the above embodiment, the server can determine the target recommended content based on the time when the user performs negative feedback operations on different recommended tags (or recommended content), and the server can determine the user's latest browsing habits and browsing preferences based on the user's operations on the target recommended content, which helps to more accurately grasp the user's latest user portrait, thereby improving the accuracy of recommended content recommendations. In addition, the server will also map the negative feedback activation matrix to a reasonable interval, which helps to ensure the accuracy of the target recommended content screening.

[0038] In one implementation of the method provided in the first aspect, generating a first recommendation list based on the target recommended content and the updated user portrait may include:

[0039] Determining at least one positive feedback recommendation content based on the user portrait, where the positive feedback recommendation content is the recommendation content that is not associated with the recommendation tag indicated by the historical negative feedback information corresponding to the user identification information;

[0040] Generate a first recommendation list based on the target recommendation content and the positive feedback recommendation content;

[0041] The first recommendation list is sent to the user terminal.

[0042] By implementing the method provided in the above embodiment, the recommendation list generated by the server includes not only the recommendation content related to the user's historical negative feedback operations, but also the recommendation content related to the user's historical positive feedback operations, which helps to ensure that the user's satisfaction with the recommendation content included in the recommendation list is higher than a certain value and avoid causing user disgust.

[0043] In one implementation of the method provided in the first aspect, the negative feedback type may include at least one of blacklisting, deleting, giving a bad review, reporting, not interested, and no longer recommending.

[0044] By implementing the method provided in the above embodiment, the server defines multiple user operations as negative feedback operations, which helps to understand the user's browsing habits or browsing preferences from a more detailed perspective, thereby helping to portray a more accurate user portrait.

[0045] In a second aspect, the present application provides a method for screening recommended content, which is applied to a user terminal. The method may include:

[0046] In response to a negative feedback operation by a user, determining a first recommendation tag and a negative feedback type corresponding to the negative feedback operation, wherein the first recommendation tag is a recommendation tag associated with the recommended content corresponding to the negative feedback behavior;

[0047] Generate first negative feedback information based on the first recommendation tag, the negative feedback type, and the user identification information of the user;

[0048] The first negative feedback information is sent to the server.

[0049] By implementing the method provided in the second aspect, the user terminal can collect and analyze the user's negative feedback operations on a certain recommended content, generate negative feedback information, and send the negative feedback information to the server, which helps to ensure that the server accurately understands the user's browsing habits or browsing preferences, thereby helping the server to screen out recommended content that the user is more satisfied with.

[0050] In one implementation of the method provided in the second aspect, the negative feedback type may include at least one of blacklisting, deleting, giving a bad review, reporting, not interested, and no longer recommending.

[0051] By implementing the method provided in the above embodiment, the present application defines a variety of user operations as negative feedback operations, which helps to understand the user's browsing habits or browsing preferences from a more detailed perspective, thereby helping to portray a more accurate user portrait.

[0052] Implementing the method provided in the second aspect, in one embodiment, the method may further include:

[0053] receiving a first recommendation list sent by the server;

[0054] Recommended content corresponding to the first recommendation list is presented to the user based on the arrangement order of the first recommendation list.

[0055] By implementing the method provided in the above embodiment, the user terminal can present the recommended content corresponding to the first recommendation list to the user according to the arrangement order of the first recommendation list, which helps to ensure the user's usage experience, avoid continuous negative feedback of operation-related content that reduces the user's browsing interest, and help to ensure the user retention rate of the software and / or website.

[0056] Implementing the method provided in the second aspect, in one embodiment, the first recommendation list may include target recommended content and positive feedback recommended content, the target recommended content is the recommended content associated with the recommended tag indicated by the historical negative feedback information corresponding to the user identification information, and the positive feedback recommended content is the recommended content not associated with the recommended tag indicated by the historical negative feedback information corresponding to the user identification information.

[0057] By implementing the method provided in the above embodiment, the recommendation list can include not only the recommended content related to the user's historical negative feedback operations, but also the recommended content related to the user's historical positive feedback operations, which helps to ensure that the user's satisfaction with the recommended content included in the recommendation list is higher than a certain value and avoid causing user disgust.

[0058] In a third aspect, the present application provides a server that may include one or more processors and one or more memories; wherein the one or more memories are coupled to one or more processors, and the one or more memories are used to store computer program code, and the computer program code may include computer instructions, and when one or more processors execute the computer instructions, the method described in the first aspect is executed.

[0059] In a fourth aspect, the present application provides a user terminal that may include one or more processors and one or more memories; wherein the one or more memories are coupled to the one or more processors, and the one or more memories are used to store computer program codes, and the computer program codes may include computer instructions, and when the one or more processors execute the computer instructions, the method described in the second aspect is executed.

[0060] In a fifth aspect, the present application provides a system for screening recommended content, which may include the server as described in the third aspect and the user terminal as described in the fourth aspect.

[0061] In a sixth aspect, the present application provides a computer-readable storage medium, which may include instructions, which, when executed on a server, enable execution of the method described in any one of the first aspects.

[0062] In a seventh aspect, the present application provides a computer-readable storage medium, which may include instructions, which, when executed on a user terminal, execute the method described in the second aspect.

[0063] In an eighth aspect, the present application provides a computer program product comprising instructions, which, when executed on a server, enables the server to execute the method described in the first aspect and any possible implementation of the first aspect.

[0064] In a ninth aspect, the present application provides a computer program product comprising instructions, which, when executed on a server, enables the server to execute the method described in the second aspect and any possible implementation of the second aspect.

[0065] It can be understood that the server provided in the third aspect, the user terminal provided in the fourth aspect, the system for screening recommended content provided in the fifth aspect, the computer-readable storage medium provided in the sixth and seventh aspects, and the computer program products provided in the eighth and ninth aspects are all used to execute the method provided in the present application. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method, which will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 It is a flowchart of a content recommendation method provided in an embodiment of the present application;

[0067] Figure 2 It is a schematic diagram of the architecture of a system for screening recommended content provided by an embodiment of the present application;

[0068] Figure 3 It is a flowchart of a method for screening recommended content provided by an embodiment of the present application;

[0069] Figure 4 This is a schematic diagram of a scenario in which a user performs a negative feedback operation on recommended content, provided in an embodiment of the present application;

[0070] Figure 5a It is a schematic diagram of a scenario of updating a negative feedback adjacency matrix provided in an embodiment of the present application;

[0071] Figure 5b is a schematic diagram of a scenario for generating a first recommendation list provided in an embodiment of the present application;

[0072] Figure 6 It is a flowchart of a method for determining target recommended content provided by an embodiment of the present application;

[0073] Figure 7 It is a scene schematic diagram of a time matrix provided in an embodiment of the present application;

[0074] Figure 8 is a flowchart of another method for screening recommended content provided by an embodiment of the present application;

[0075] Fig. 9 It is a schematic diagram of the composition of a server provided in an embodiment of the present application;

[0076] Fig.10 This is a schematic diagram of the composition of a user terminal provided in an embodiment of the present application;

[0077] Fig.11 It is a schematic diagram of the composition of another destination server provided in an embodiment of the present application;

[0078] Fig.12 is a schematic diagram of the hardware structure of a user terminal provided in an embodiment of the present application;

[0079] Fig.13 It is a software structure block diagram of a user terminal in an embodiment of the present application. DETAILED DESCRIPTION

[0080] The technical solutions in the embodiments of the present application will be described clearly and in detail below in conjunction with the accompanying drawings. In the description of the embodiments of the present application, unless otherwise specified, " / " means or, for example, A / B can mean A or B; "and / or" in the text is only a description of the association relationship of associated objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, "multiple" means two or more than two.

[0081] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.

[0082] The term "user interface (UI)" in the following embodiments of the present application refers to a medium interface for interaction and information exchange between an application or operating system and a user, which realizes the conversion between the internal form of information and the form acceptable to the user. The user interface is a source code written in a specific computer language such as Java and extensible markup language (XML). The interface source code is parsed and rendered on the user terminal, and finally presented as content that the user can recognize. The commonly used form of user interface is the graphical user interface (GUI), which refers to a user interface related to computer operation displayed in a graphical manner. It can be a visual interface element such as text, icons, buttons, menus, tabs, text boxes, dialog boxes, status bars, navigation bars, widgets, etc. displayed on the display screen of the user terminal.

[0083] In order to make the description of the following embodiments clear and concise, a brief introduction to the related technology is first given:

[0084] In order to improve their own user retention rate and user stickiness, software and / or websites will use different recommendation mechanisms to recommend recommendations that meet users' browsing habits or preferences. The entire recommendation mechanism can be divided into four processes: recall, rough sorting, fine sorting, and re-ranking. Among them, recall solves the problem of recalling thousands of items from a large number of candidate items; rough sorting is essentially similar to fine sorting, except that rough sorting is simpler than fine sorting in terms of features and model complexity; fine sorting solves the problem of going from thousands of items to dozens of items; re-ranking solves the problem of the most appropriate display order or method for displaying the list.

[0085] At present, the existing technology can achieve the purpose of improving user retention rate and user stickiness by removing the recommended content related to the negative feedback operation from the recommendation list based on the user's negative feedback operation, and no longer retrieving the recommended content from the database.

[0086] See also Figure 1 , Figure 1 The figure is a flowchart of a content recommendation method in the prior art.

[0087] like Figure 1 As shown, the prior art can be based on the user's browsing behavior (such as clicking Figure 1 to label different recommendations ( Figure 1 The recall system will then remove Ad A from the recommendation list, and the recall system will select new recommended content from the database to fill in the recommendation list. As the number of user visits increases, more recommended content will be removed from the recommendation list (such as Figure 1 The removed "Advertisement C" is not included in the recall system, and the removed recommended content (such as Figure 1 "Ad A" and "Ad C" in the video).

[0088] It can be seen that the prior art provides a specific implementation method for generating a recommendation list, which is conducive to eliminating content that users are not interested in and recommending content that is more in line with their browsing preferences. However, the recommendation mechanism of the prior art will lead to related content (such as Figure 1 The exposure rate of "Ad A" and "Ad C" in the advertisement will decrease, which will affect the revenue of the software and / or web platform. In addition, the prior art does not take into account that the user's interest in various things will change dynamically over time. Therefore, those skilled in the art need to find out how to reasonably recall the recommended content corresponding to the user's historical negative feedback operations.

[0089] The present application can provide a method for screening recommended content, which can enable the server to reasonably screen out recommended content related to the user's historical negative feedback behavior based on preset conditions and re-recommend it to the user, which helps to determine the user's latest browsing habits and browsing preferences, so as to accurately push the content of interest to the user. In addition to achieving the purpose of improving the user's usage experience, it can also increase the user stickiness of various software or websites and improve user retention rate.

[0090] See also Figure 2 , Figure 2 A schematic diagram of the architecture of a system for screening recommended content provided in an embodiment of the present application.

[0091] like Figure 2 As shown, the system 20 for screening recommended contents may include a server 21 and a user terminal 22 .

[0092] Specifically, in the embodiment of the present application, the server 21 can establish a communication connection with multiple user terminals 22, and the server 21 can be used to receive the first negative feedback information sent by the user terminal 22, the first negative feedback information can include user identification information, a first recommendation tag and a negative feedback type, and the first recommendation tag can be used to indicate the recommendation tag associated with the recommended content corresponding to the first negative feedback information; the server 21 can also update the user portrait corresponding to the user identification information based on the first negative feedback information; the server 21 can also be used to filter the target recommended content that meets the preset conditions based on the updated user portrait, and the target recommended content is the recommended content associated with the recommendation tag indicated by the historical feedback information corresponding to the user identification information; the server 21 can also generate a first recommendation list based on the target recommended content and the updated user portrait, and send the first recommendation list to the user terminal 22. Among them, the first recommendation list can include the target recommended content and positive feedback recommended content, the target recommended content is the recommended content associated with the recommendation tag indicated by the historical negative feedback information corresponding to the user identification information, and the positive feedback recommended content is the recommended content not associated with the recommendation tag indicated by the historical negative feedback information corresponding to the user identification information.

[0093] It can be seen that the embodiment of the present application can filter out recommended content related to the user's historical negative feedback behavior based on preset conditions and re-recommend it to the user, which helps to increase the exposure of the recommended content and also helps to determine the user's latest browsing habits and browsing preferences, thereby further improving the user's corresponding user portrait and achieving the purpose of improving the user's usage experience.

[0094] It should be noted that the server 21 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms. For example, cloud-side devices may include cloud servers, central servers, etc. Taking cloud servers as an example, cloud servers refer to a central computing device cluster used to provide computing, storage, and communication resources. Cloud servers are a type of server with the characteristics of being highly distributed and highly virtualized. Its computing resources are obtained by scheduling from a large number of integrated virtualized physical servers. From the perspective of node scale, such a virtualization scale may be several, dozens, or hundreds of physical servers, or it may be a large cloud virtual resource pool built from thousands of physical hardware across data centers.

[0095] Furthermore, in an embodiment of the present application, the user terminal 22 can receive a negative feedback operation of the user, and determine a first recommendation tag and a negative feedback type corresponding to the negative feedback operation; the user terminal 22 can also generate first negative feedback information based on the first recommendation tag, the negative feedback type and the user identification information of the user, and send the first negative feedback recommendation information to the server 21. Optionally, the user terminal 22 can also receive a first recommendation list sent by the server 21, and present the recommended content corresponding to the first recommendation list to the user based on the arrangement order of the first recommendation list. It can be seen that the user terminal 22 can analyze and generate negative feedback information corresponding to the user's negative feedback operation, and send the negative feedback information to the server 21, which helps the server calculate a recommendation list that is more suitable for the user's browsing habits and browsing preferences, and improves the user's experience.

[0096] It should be noted that the user terminal 22 is a smart terminal device, which can be of various types, and the embodiments of the present application do not limit its specific type. For example, the user terminal can be a mobile phone, and can also include a tablet computer, a desktop computer, a desktop computer with a touch-sensitive surface or a touch panel, a laptop computer (laptop), a handheld computer, a notebook computer, a smart screen, a wearable device (such as a smart watch, a smart bracelet, etc.), an augmented reality (AR) device, a virtual reality (VR) device, an artificial intelligence (AI) device, a car machine, a smart headset, a game console, and can also be an Internet of Things (IOT) device or a smart home device such as a smart water heater, a smart lamp, a smart air conditioner, etc.

[0097] See also Figure 3 , Figure 3 A flowchart of a method for screening recommended content provided in an embodiment of the present application is applied to the server 21.

[0098] like Figure 3 Said method may include the following steps:

[0099] S301: The server receives first negative feedback information sent by a user terminal.

[0100] Specifically, the first negative feedback information may include user identification information, a first recommendation tag, and a negative feedback type. The first recommendation tag may be used to indicate a recommendation tag associated with the recommended content corresponding to the first negative feedback information.

[0101] Among them, the user identification information can be information that reflects the user's identity, such as the user's mobile phone number, ID number (such as ID number, etc.), account number and nickname, etc., when logging into the software and / or website. Different users have different user identification information, that is, there is a one-to-one correspondence between the user and the user identification information. It should be noted that the software and / or website involved in the embodiments of the present application have the function of collecting and analyzing the user's browsing behavior in the software and / or website, and generating and presenting corresponding recommended content to the user based on the user's browsing behavior.

[0102] Furthermore, the first recommendation tag may be, but is not limited to, tags describing the theme of the recommended content, such as “pet”, “furniture”, “food”, and “scenery”.

[0103] Furthermore, negative feedback types may include but are not limited to blacklisting, deleting, giving a bad review, reporting, not interested, and no longer recommending, etc., which indicate that the user has a negative attitude towards the recommended content.

[0104] For example, see Figure 4 , Figure 4 A schematic diagram of a scenario in which a user performs a negative feedback operation on recommended content provided in an embodiment of the present application.

[0105] like Figure 4As shown, the software 410 presents the recommended content 411 (assuming that the user identification information of the user in the software 410 is 123456) on the display interface of the user terminal 22 (assuming that the user identification information of the user in the software 410 is 123456) (assuming that the associated recommended tag is "scenery"), and assuming that the user does not like the recommended content 411, the user can call up the operation pop-up window 412 by long pressing the screen, and click the button 413 (that is, click the "dislike" button) in the operation pop-up window 412, which can be regarded as the user performing a negative feedback operation on the recommended content 411. Then, the user terminal 22 can generate the first negative feedback information based on the user identification information "123456", the first recommended tag "scenery" and the negative feedback operation type "dislike", and send the first negative feedback information to the server 21.

[0106] S302: The server updates the user portrait corresponding to the user identification information based on the first negative feedback information.

[0107] Specifically, user portraits can be used to indicate the user's personal attributes, industry preferences, and shopping preferences. Personal attributes may include, but are not limited to, gender, age, education, and IP address; industry preferences may include, but are not limited to, finance, real estate, travel, and automobiles; shopping preferences may include, but are not limited to, clothing, food, furniture, and IP-related products.

[0108] In some possible implementations, the user profile may include a negative feedback adjacency matrix;

[0109] Updating the user portrait corresponding to the user identification information based on the first negative feedback information may include:

[0110] Based on the first recommended label, the value of the target matrix point in the negative feedback adjacency matrix is ​​set to 1.

[0111] There is a one-to-one correspondence between the rows of the negative feedback adjacency matrix and the users (or user identification information), and there is a one-to-one correspondence between the columns of the negative feedback adjacency matrix and the recommended content.

[0112] Specifically, the target matrix point is determined based on user identification information and a first recommended label, the user identification information is used to determine the row corresponding to the target matrix point in the negative feedback adjacency matrix, and the first recommended label is used to determine the column corresponding to the target matrix point in the negative feedback adjacency matrix.

[0113] For example, see Figure 5a , Figure 5a A schematic diagram of a scenario for updating a negative feedback adjacency matrix provided in an embodiment of the present application.

[0114] like Figure 5aAs shown, it is assumed that the first row to the third row of the first negative feedback adjacency matrix 510 correspond to the user identification information 511 of the first user, the user identification information 512 of the second user and the identification information 513 of the third user respectively, and the first column to the third column of the first negative feedback adjacency matrix 510 correspond to the recommendation tag 514 associated with the first recommended content, the recommendation tag 515 associated with the second recommended content and the recommendation tag 516 associated with the third recommended content respectively. If the second user has a negative feedback operation with a negative feedback type of "dislike" on the third recommended content, the server 21 can determine the matrix point located in the second row and third column of the first negative feedback adjacency matrix 510 as the target matrix point, and set the value of the target matrix point to 1, so as to obtain the second negative feedback adjacency matrix 520.

[0115] Optionally, the server may also set the value of the matrix point to a different number according to different negative feedback operations.

[0116] S303: The server filters target recommended content that meets preset conditions based on the updated user portrait.

[0117] The target recommended content is the recommended content associated with the recommendation tag indicated by the historical negative feedback information corresponding to the user identification information.

[0118] In some possible implementations, filtering target recommended content that meets preset conditions based on the updated user profile may include:

[0119] Activation parameters corresponding to each recommended tag based on the updated user profile;

[0120] Determine the recommended label corresponding to the activation parameter greater than the preset threshold as the target recommended label;

[0121] The recommended content associated with the target recommendation tag is determined as the target recommended content.

[0122] Specifically, the activation parameters corresponding to each recommended label are equivalent to Figure 6 The values ​​of each matrix point in the second negative feedback activation matrix mentioned in the embodiment, so the relevant examples and explanations of the embodiments of the present application can refer to Figure 6 And its embodiments are not described in detail here.

[0123] It can be seen that the server can calculate the activation parameters to help more scientifically represent the attractiveness of each recommended tag to the user, thereby helping to select recommended tags that are more in line with the user's browsing habits or browsing preferences, thereby improving the user's satisfaction with the recommended content.

[0124] S304: The server generates a first recommendation list based on the target recommended content and the updated user portrait.

[0125] In some possible implementations, generating the first recommendation list based on the target recommended content and the updated user portrait may include:

[0126] Determining at least one positive feedback recommendation content based on the user portrait, where the positive feedback recommendation content is the recommendation content that is not associated with the recommendation tag indicated by the historical negative feedback information corresponding to the user identification information;

[0127] Generate a first recommendation list based on the target recommendation content and the positive feedback recommendation content;

[0128] The first recommendation list is sent to the user terminal.

[0129] Exemplarily, suppose there are fourth recommended content, fifth recommended content, sixth recommended content and seventh recommended content, if the fifth recommended content and the sixth recommended content are associated with the recommendation label indicated by the historical negative feedback information corresponding to the user identification information, and the fifth recommended content meets the preset conditions, then the fifth recommended content can be considered as the target recommended content, and the fourth recommended content and the seventh recommended content are positive feedback recommended content, so the server 21 can generate a first recommendation list based on the fourth recommended content, the fifth recommended content and the seventh recommended content, and send the first recommendation list to the user terminal 22. Optionally, if both the fifth recommended content and the sixth recommended content do not meet the preset conditions, the first recommendation list will not include the target recommended content, but will only include the positive feedback recommended content (that is, the first recommendation list only includes the fourth recommended content and the seventh recommended content).

[0130] In a possible implementation, the server 21 may also determine the order of the recommended contents in the first recommendation list according to the user portrait. Optionally, the server 21 may arrange the order of the recommended contents in the first recommendation list according to the user's preference for different recommended tags (or different recommended contents) indicated by the user portrait, wherein the preference may be determined based on the number of views, browsing time, number of likes, and number of shares of the recommended tag (or recommended content) by the user. It should be noted that this application does not limit the arrangement of the recommended contents, and the specific arrangement is set by the technical staff according to the actual situation.

[0131] It can be seen that by implementing the embodiments of the present application, the server can update the user's user portrait based on the user's negative feedback operations, and can also recall the recommended content related to the user's historical negative feedback behavior and re-recommend it to the user, which helps the server determine the user's latest browsing habits and browsing preferences, thereby further improving the user's corresponding user portrait and achieving the purpose of improving the user's usage experience.

[0132] See also Figure 5b , Figure 5bA schematic diagram of a scenario for generating a first recommendation list provided in an embodiment of the present application.

[0133] like Figure 5b As shown, the user terminal 22 can generate the first negative feedback information 10 based on the negative feedback operation of the user 1 on the recommended content 1. The first negative feedback information 10 may include the user identification information corresponding to the negative feedback operation of the user 1 (such as Figure 5b 001 shown in ), the first recommended tag (such as Figure 5b The “landscape” shown in ) and negative feedback types (such as Figure 5b The server 21 may determine the user profile 1 of the user 1 based on the user identification information in the first negative feedback information 10, and update the user profile 1 based on the first negative feedback information 10. Further, the server 21 may filter the target recommended content (such as the negative feedback recommended content database 2102) that meets the preset conditions from the negative feedback recommended content database 2101 based on the updated user profile 1. Figure 5b ), and select a certain number of recommended contents (such as the “first video” shown in ) from the positive feedback recommended content database 2103 of the recommended content database 2101. Figure 5b ). Furthermore, the server 21 may generate a first recommendation list 2104 based on the recommended content screened from the recommended content database 2101. The negative feedback recommended content database 2102 may be used to store historical negative feedback information corresponding to user 1, and the positive feedback recommended content database 2103 may be used to store historical positive feedback information corresponding to user 1.

[0134] See also Figure 6 , Figure 6 A flowchart of a method for determining target recommended content provided in an embodiment of the present application.

[0135] like Figure 6 As shown, the method may include:

[0136] S601: The server calculates a first negative feedback activation matrix corresponding to the user portrait based on the user feature matrix, the time matrix, the first activation function, the time scale adjustment function, and the recommended content feature matrix.

[0137] Among them, the user portrait can also include a user feature matrix, a time matrix, a first activation function, a time scale adjustment function, and a recommended content feature matrix. Specifically, different rows of the user feature matrix can be used to indicate different user identification information, and different columns of the user feature matrix can be used to indicate the user's character attributes (such as gender, age, education, and IP address, etc.); different rows of the time matrix can be used to indicate different user identification information, different columns of the time matrix can be used to indicate different recommended tags, and the values ​​of each matrix point of the time matrix can be used to indicate the length of time after a certain user performs a negative feedback operation on a certain recommended tag (i.e., a certain recommended content); the first activation function and the time scale adjustment function are both used to perform numerical conversion processing on the time matrix, and the values ​​of each matrix point in the time matrix can be adjusted to a reasonable interval. The specific calculation formulas of the first activation function and the time scale adjustment function are not limited in this application. The specific calculation formulas of the first activation function and the time scale adjustment function are set by the staff according to the actual situation; different rows of the recommended content feature matrix can be used to indicate different recommended content, and different columns of the recommended content feature matrix can be used to indicate different recommended tags. It can be considered that the recommended content feature matrix can be used to indicate the association between recommended content and recommended tags.

[0138] For example, see Figure 7 , Figure 7 A schematic diagram of a time matrix scenario provided in an embodiment of the present application.

[0139] like Figure 7 As shown, the first row to the third row of the first time matrix 710 correspond to the user identification information 511 of the first user, the user identification information 512 of the second user, and the user identification information 513 of the third user, respectively. The first column to the third column of the first time matrix 710 correspond to the recommendation tag 514 associated with the first recommended content, the recommendation tag 515 associated with the second recommended content, and the recommendation tag 516 associated with the third recommended content, respectively. If the second user has a negative feedback operation with a negative feedback type of "dislike" on the third recommended content, the server 21 can set the value of the matrix point located in the second row and the third column in the first time matrix 710 to 1, and obtain the second time matrix 720. Optionally, as time increases, the value of the matrix point in the second row and the third column will also increase (such as every day, the value of the matrix point in the second row and the third column will increase by 1). Optionally, the unit of the corresponding value of the matrix point in the first time matrix 710 and the second time matrix 720 can be seconds, minutes, hours, days, months or years, which is not limited in this application, and the specific time measurement unit is set by the staff according to the actual situation.

[0140] In some possible implementations, the server 21 may calculate the first negative feedback activation matrix based on the following formula:

[0141]

[0142] Among them, S is the first negative feedback activation matrix, X is the user feature matrix, is the negative feedback adjacency matrix, s is the first activation function, α is the time scale adjustment function, T is the time matrix, and X′ is the recommended content feature matrix.

[0143] It should be noted that

[0144] S602: The server performs mapping processing on the first negative feedback activation matrix to generate a second negative feedback activation matrix.

[0145] In some possible implementations, the server 21 may use a mapping function to perform mapping processing on the first negative feedback activation matrix, map the values ​​of each matrix point in the first negative feedback activation matrix to the interval (0, 1), and generate a second negative feedback activation matrix.

[0146] S603: The server selects target matrix points whose values ​​in the second negative feedback activation matrix are less than a preset threshold.

[0147] In some possible implementations, the server 21 may also limit the number of target recommended contents in a single recommendation list. Exemplarily, the server 21 may limit the number of target recommended contents in a single recommendation list to no more than 20% of the positive feedback recommended contents, which helps to ensure that the user's satisfaction with the recommended contents in the recommendation list is higher than a certain value while testing the user's latest browsing habits or browsing preferences, so as to avoid causing user disgust.

[0148] S604: The server determines target recommended content based on the target matrix point.

[0149] In some possible implementations, the server 21 may determine the recommended tag and user identification information corresponding to the target matrix point based on the row and column information of the target matrix point, and determine the recommended content associated with the recommended tag corresponding to the target matrix point as the target recommended content. Further, the server 21 may send the target recommended content to the user terminal 22 of the corresponding user based on the user identification information.

[0150] It can be seen that by implementing the method of the embodiment of the present application, the server can determine the target recommended content based on the time when the user performs negative feedback operations on different recommended tags (or recommended content), and the server can determine the user's latest browsing habits and browsing preferences based on the user's operation on the target recommended content, which helps to more accurately grasp the user's latest user portrait, thereby improving the accuracy of recommended content recommendations, improving the user's usage experience, and further improving the user stickiness with the software and / or website. In addition, the server will also map the negative feedback activation matrix to a reasonable interval, which helps to ensure the accuracy of the target recommended content screening.

[0151] See also Figure 8 , Figure 8 A flowchart of another method for screening recommended content provided in an embodiment of the present application is applied to a user terminal.

[0152] like Figure 8 As shown, the method may include the following steps:

[0153] S801: In response to a negative feedback operation of a user, a user terminal determines a first recommended tag and a negative feedback type corresponding to the negative feedback operation.

[0154] S802: The user terminal generates first negative feedback information based on the first recommendation tag, the negative feedback type, and the user identification information of the user.

[0155] S803: The user terminal sends the first negative feedback information to the server.

[0156] The specific implementation process of steps S801 to S803 can be referred to Figure 4 The scenes shown and their implementation contents are not described in detail here.

[0157] In some possible implementations, the method may further include the following steps:

[0158] receiving a first recommendation list sent by the server;

[0159] Recommended content corresponding to the first recommendation list is presented to the user based on the arrangement order of the first recommendation list.

[0160] It can be seen that the user terminal can collect and analyze the user's negative feedback operations on a certain recommended content, generate negative feedback information, and send the negative feedback information to the server, which helps to ensure that the server accurately understands the user's browsing habits or browsing preferences, thereby helping the server to screen out recommended content that the user is more satisfied with.

[0161] See also Fig. 9 , Fig. 9 A schematic diagram of the composition of a server provided in an embodiment of the present application.

[0162] like Fig. 9 The server 21 may include: a communication module 211 and a computing module 212;

[0163] The communication module 211 may be used to receive first negative feedback information sent by the user terminal 22, where the first negative feedback information may include user identification information, a first recommendation tag, and a negative feedback type, where the first recommendation tag is used to indicate a recommendation tag associated with the recommended content corresponding to the first negative feedback information;

[0164] A calculation module 212 may be used to update a user portrait corresponding to the user identification information based on the first negative feedback information;

[0165] The calculation module 212 may also be used to filter target recommended content that meets preset conditions based on the updated user portrait, where the target recommended content is the recommended content associated with the recommendation tag indicated by the historical negative feedback information corresponding to the user identification information;

[0166] The calculation module 212 may also be used to generate a first recommendation list based on the target recommended content and the updated user portrait.

[0167] In some possible implementations, the user portrait may be used to indicate the user's personal attributes, industry preferences, and shopping preferences. The personal attributes may include at least one of gender, age, education level, and IP address.

[0168] In some other possible implementations, the user profile may include a negative feedback adjacency matrix;

[0169] The server 21 may also include:

[0170] The calculation module 212 may also be used to set the value of the target matrix point in the negative feedback adjacency matrix to 1 based on the first recommended label.

[0171] In some other possible implementations, the target matrix point is determined based on user identification information and a first recommended tag, the user identification information is used to determine the row corresponding to the target matrix point in the negative feedback adjacency matrix, and the first recommended tag is used to determine the column corresponding to the target matrix point in the negative feedback adjacency matrix.

[0172] In some other possible implementations, the server 21 may further include:

[0173] The calculation module 212 may also be used to calculate activation parameters corresponding to each recommendation tag based on the updated user profile;

[0174] The calculation module 212 may also be used to determine a recommended tag corresponding to an activation parameter greater than a preset threshold as a target recommended tag;

[0175] The calculation module 212 may also be configured to determine the recommended content associated with the target recommendation tag as the target recommended content.

[0176] In some other possible implementations, the user portrait may further include a user feature matrix, a time matrix, a first activation function, a time scale adjustment function, and a recommended content feature matrix;

[0177] The server 21 may also include:

[0178] The calculation module 212 may also be used to calculate a first negative feedback activation matrix corresponding to the user portrait based on the user feature matrix, the time matrix, the first activation function, the time scale adjustment function, and the recommended content feature matrix;

[0179] The calculation module 212 may also be used to perform mapping processing on the first negative feedback activation matrix to generate a second negative feedback activation matrix;

[0180] The calculation module 212 may also be used to screen out target matrix points whose values ​​in the second negative feedback activation matrix are less than a preset threshold;

[0181] The calculation module 212 may also be used to determine target recommended content based on the target matrix point.

[0182] In some other possible implementations, the server 21 may further include:

[0183] The calculation module 212 may also be used to calculate the first negative feedback activation matrix based on the following formula:

[0184]

[0185] Among them, S is the first negative feedback activation matrix, X is the user feature matrix, is the negative feedback adjacency matrix, s is the first activation function, α is the time scale adjustment function, T is the time matrix, and X′ is the recommended content feature matrix;

[0186] The calculation module 212 may also be used to map the first negative feedback activation matrix using a mapping function, map the values ​​of each matrix point in the first negative feedback activation matrix to the interval (0, 1), and generate a second negative feedback activation matrix;

[0187] The calculation module 212 may also be used to screen out the target matrix point in the second negative feedback activation matrix, and determine the recommended label and user identification information corresponding to the target matrix point based on the row and column information of the target matrix point;

[0188] The calculation module 212 may also be used to determine the recommended content associated with the recommendation tag corresponding to the target matrix point as the target recommended content.

[0189] In some other possible implementations, the server 21 may further include:

[0190] The calculation module 212 may also be used to determine at least one positive feedback recommendation content based on the user portrait, where the positive feedback recommendation content is the recommendation content that is not associated with the recommendation tag indicated by the historical negative feedback information corresponding to the user identification information;

[0191] The calculation module 212 may also be used to generate a first recommendation list based on the target recommendation content and the positive feedback recommendation content;

[0192] The communication module 211 may also be configured to send the first recommendation list to a user terminal.

[0193] In some other possible implementations, the negative feedback type may include at least one of blacklisting, deleting, giving a bad review, reporting, not interested, and no longer recommending.

[0194] See also Fig.10 , Fig.10 A schematic diagram of the composition of a user terminal provided in an embodiment of the present application.

[0195] like Fig.10 As shown, the user terminal 22 may include: a communication module 221 and a calculation module 222;

[0196] The calculation module 222 may be used to determine a first recommendation tag and a negative feedback type corresponding to the negative feedback operation in response to a negative feedback operation by a user, wherein the first recommendation tag is a recommendation tag associated with the recommended content corresponding to the negative feedback behavior;

[0197] The calculation module 222 may also be used to generate first negative feedback information based on the first recommendation tag, the negative feedback type and the user identification information of the user;

[0198] The communication module 221 may be configured to send the first negative feedback information to the server.

[0199] In some possible implementations, the negative feedback type may include at least one of blacklisting, deleting, giving a bad review, reporting, not interested, and no longer recommending.

[0200] In some other possible implementations, the user terminal 22 may further include: a display module 223;

[0201] The communication module 221 may also be used to receive the first recommendation list sent by the server;

[0202] The display module 223 may be configured to present the recommended contents corresponding to the first recommendation list to the user based on the arrangement order of the first recommendation list.

[0203] In some other possible implementations, the first recommendation list may include target recommended content and positive feedback recommended content, wherein the target recommended content is the recommended content associated with the recommended tag indicated by the historical negative feedback information corresponding to the user identification information, and the positive feedback recommended content is the recommended content not associated with the recommended tag indicated by the historical negative feedback information corresponding to the user identification information.

[0204] See also Fig.11 , Fig.11 A schematic diagram of another server provided in an embodiment of the present application, the server may include:

[0205] Processor 1010, memory 1020 and I / O interface 1030. The processor 1010, memory 1020 and I / O interface 1030 can be connected to each other in a communicative manner. The memory 1020 is used to store instructions, and the processor 1010 is used to execute the instructions stored in the memory 1020 to implement the following. Figure 3 and / or Figure 6 The corresponding method steps.

[0206] The processor 1010 is used to execute the instructions stored in the memory 1020 to control the I / O interface 1030 to receive and send signals and complete the steps in the above method. The memory 1020 can be integrated in the processor 1010 or set separately from the processor 1010.

[0207] The memory 1020 may also include a storage system 1021, a cache 1022, and a RAM 1023. The cache 1022 is a primary memory between the RAM 1023 and the CPU, which is composed of a static memory chip (SRAM). It has a relatively small capacity but a much higher speed than the main memory, close to the speed of the CPU; the RAM 1023 is an internal memory that directly exchanges data with the CPU, which can be read and written at any time (except when refreshed), and has a very high speed. It is usually used as a temporary data storage medium for the operating system or other running programs. The three are combined to realize the functions of the memory 1020.

[0208] As an implementation, the function of the I / O interface 1030 may be implemented by a transceiver circuit or a dedicated transceiver chip. The processor 1010 may be implemented by a dedicated processing chip, a processing circuit, a processor or a general-purpose chip.

[0209] As another implementation method, it is possible to use a general-purpose computer to implement the device provided in the embodiment of the present application. That is, the program code that implements the functions of the processor 1010 and the I / O interface 1030 is stored in the memory 1020, and the general-purpose processor implements the functions of the processor 1010 and the I / O interface 1030 by executing the code in the memory 1020.

[0210] For the concepts, explanations, detailed descriptions and other steps involved in the device and related to the technical solutions provided in the embodiments of the present application, please refer to the description of the method steps performed by the device in the aforementioned method or other embodiments, which will not be repeated here.

[0211] As another implementation of this embodiment, a computer-readable storage medium is provided, on which instructions are stored. When the instructions are executed, the method in the above method embodiment is executed.

[0212] As another implementation of this embodiment, a computer program product including instructions is provided, and when the instructions are executed, the method in the above method embodiment is performed.

[0213] Those skilled in the art will appreciate that for ease of description, Fig.11 Only one memory and processor are shown. In an actual terminal or server, there may be multiple processors and memories. The memory may also be referred to as a storage medium or a storage device, etc., which is not limited in the embodiments of the present application.

[0214] It should be understood that in the embodiments of the present application, the processor may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc.

[0215] It should also be understood that the memory mentioned in the embodiments of the present application 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), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), 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), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM) and direct memory bus random access memory (Direct Rambus RAM, DR RAM).

[0216] It should be noted that when the processor is a general-purpose processor, DSP, ASIC, FPGA or other programmable logic device, discrete gate or transistor logic device, discrete hardware component, the memory (storage module) is integrated in the processor.

[0217] It should be noted that the memory described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0218] In addition to the data bus, the bus may also include a power bus, a control bus, and a status signal bus. However, for the sake of clarity, Fig.11 In the text file, various buses are marked as buses.

[0219] It should also be understood that the first, second, third, fourth and various numerical numbers involved in this document are only distinctions made for the convenience of description and are not intended to limit the scope of the present application.

[0220] It should be understood that the term "and / or" in this article is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0221] In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in a processor or an instruction in the form of software. The steps of the method disclosed in conjunction with the embodiment of the present application can be directly embodied as a hardware processor for execution, or a combination of hardware and software modules in a processor for execution. The software module can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in a memory, and the processor reads the information in the memory and completes the steps of the above method in conjunction with its hardware. To avoid repetition, it is not described in detail here.

[0222] In various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0223] Those skilled in the art will appreciate that the various illustrative logical blocks (ILBs) and steps described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel 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.

[0224] In the several embodiments provided in the present 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 only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, 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.

[0225] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0226] 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.

[0227] In the above embodiments, it 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. When the computer program instructions are loaded and executed on a computer, the process or function described in 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 devices. 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 a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integration. The available medium can be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state hard disk), etc.

[0228] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. The computer program is executed by a processor to implement part or all of the steps of any method for screening recommended content as recorded in the above method embodiments.

[0229] An embodiment of the present application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute part or all of the steps of any method for screening recommended content recorded in the above method embodiments.

[0230] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0231] See also Fig.12 , Fig.12 The hardware structure diagram of a user terminal provided in an embodiment of the present application is shown in FIG.

[0232] The user terminal 22 may include a processor 101, a memory 102, a wireless communication module 103, a mobile communication module 104, an antenna 103A, an antenna 104A, a power switch 105, a sensor module 106, a focus motor 107, a camera 108, a display screen 109, etc. Among them, the sensor module 106 may include a gyroscope sensor 106A, an acceleration sensor 106B, an ambient light sensor 106C, an image sensor 106D, a distance sensor 106E, etc. Among them, the wireless communication module 103 may include a WLAN communication module, a Bluetooth communication module, etc. The above multiple parts can transmit data through a bus.

[0233] The processor 101 may include one or more processing units, for example, the processor 101 may include an application processor (AP), a modem processor, a graphics processor (GPU), an image signal processor (ISP), a controller, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural-network processing unit (NPU), etc. Different processing units may be independent devices or integrated into one or more processors.

[0234] The memory 102 may be used to store computer executable program codes, and the executable program codes may include instructions. The processor 101 executes various functional applications and data processing of the user terminal 22 by running the instructions stored in the memory 102. The memory 102 may include a program storage area and a data storage area. In a specific implementation, the memory 102 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more disk storage devices, flash memory devices, or other non-volatile solid-state storage devices.

[0235] The wireless communication function of the user terminal 22 can be realized through the antenna 103A, the antenna 104A, the mobile communication module 104, the wireless communication module 103, the modem processor and the baseband processor.

[0236] Antenna 103A and antenna 104A can be used to transmit and receive electromagnetic wave signals. Each antenna in user terminal 22 can be used to cover a single or multiple communication frequency bands. Different antennas can also be reused to improve antenna utilization.

[0237] The mobile communication module 104 can provide solutions for wireless communications including 2G / 3G / 4G / 5G, etc., applied to the user terminal 22. The mobile communication module 104 may include at least one filter, a switch, a power amplifier, a low noise amplifier (LNA), etc. The mobile communication module 104 can receive electromagnetic waves through the antenna 104A, and filter, amplify, etc. the received electromagnetic waves, and transmit them to the modulation and demodulation processor for demodulation. The mobile communication module 104 can also amplify the signal modulated by the modulation and demodulation processor, and convert it into electromagnetic waves for radiation through the antenna 104A.

[0238] The modulation and demodulation processor may include a modulator and a demodulator. The modulator is used to modulate the low-frequency baseband signal to be transmitted into a medium-high frequency signal. The demodulator is used to demodulate the received electromagnetic wave signal into a low-frequency baseband signal. The demodulator then transmits the demodulated low-frequency baseband signal to the baseband processor for processing. After the low-frequency baseband signal is processed by the baseband processor, it is transmitted to the application processor. The application processor outputs a sound signal through an audio device, or displays an image or video through the display screen 109.

[0239] The wireless communication module 103 can provide wireless communication solutions including wireless local area networks (WLAN), Bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), infrared (IR), etc., which are applied to the user terminal 22. The wireless communication module 103 can be one or more devices integrating at least one communication processing module. The wireless communication module 103 receives electromagnetic waves via the antenna 103A, modulates the frequency of the electromagnetic wave signal and performs filtering, and sends the processed signal to the processor 101. The wireless communication module 103 can also receive the signal to be sent from the processor 101, modulate the frequency of the signal, amplify it, and convert it into electromagnetic waves for radiation through the antenna 103A.

[0240] The power switch 105 may be used to control the supply of power to the user terminal 22 .

[0241] The gyroscope sensor 106A can be used to determine the motion posture of the user terminal 22. In some embodiments, the angular velocity of the user terminal 22 around three axes (i.e., x, y, and z axes) can be determined by the gyroscope sensor 106A. The gyroscope sensor 106A can be used for anti-shake shooting. For example, when the shutter is pressed, the gyroscope sensor 106A detects the angle of the user terminal 22 shaking, calculates the distance that the lens module needs to compensate based on the angle, and allows the lens to offset the shaking of the user terminal 22 through reverse movement to achieve anti-shake. The gyroscope sensor 106A can also be used for navigation and somatosensory game scenes.

[0242] The acceleration sensor 106B can detect the magnitude of acceleration of the user terminal 22 in various directions (generally three axes). When the user terminal 22 is stationary, the magnitude and direction of gravity can be detected. It can also be used to identify the posture of the user terminal. For example, the acceleration sensor 106B can be applied to applications such as horizontal and vertical screen switching and pedometers.

[0243] The ambient light sensor 106C is used to sense the brightness of the ambient light. The user terminal 22 can adaptively adjust the brightness of the display screen 109 according to the sensed brightness of the ambient light. The ambient light sensor 106C can also be used to automatically adjust the white balance when taking pictures.

[0244] The image sensor 106D, also known as a photosensitive element, can utilize the photoelectric conversion function of the photoelectric device to convert the light image on the photosensitive surface into an electrical signal that is proportional to the light image. The image sensor can be a charge coupled device (CCD) sensor or a complementary metal-oxide-semiconductor (CMOS) sensor.

[0245] The distance sensor 106E can be used to measure the distance. The user terminal 22 can measure the distance by infrared or laser. In some shooting scenes, the user terminal 22 can use the distance sensor 106E to measure the distance to achieve fast focusing.

[0246] The focus motor 107 can be used for fast focusing. The user terminal 22 can control the movement of the lens through the focus motor 107 to achieve automatic focusing.

[0247] The user terminal 22 can realize the shooting function through the ISP, the camera 108, the video codec, the GPU, the display screen 109 and the application processor.

[0248] The ISP is used to process the data fed back by the camera 108. For example, when taking a photo, the shutter is opened, and the light is transmitted to the camera photosensitive element through the lens. The light signal is converted into an electrical signal, and the camera photosensitive element transmits the electrical signal to the ISP for processing and converts it into an image visible to the naked eye. The ISP can also perform algorithm optimization on the noise and brightness of the image. The ISP can also optimize the exposure, color temperature and other parameters of the shooting scene. In some embodiments, the ISP can be set in the camera 108.

[0249] The camera 108 can be used to capture still images or videos. The object generates an optical image through the lens and projects it onto the image sensor. The image sensor can convert the optical signal into an electrical signal, and then transmit the electrical signal to the ISP to convert it into a digital image signal. The ISP can output the digital image signal to the DSP for processing. The DSP converts the digital image signal into an image signal in a standard RGB, YUV or other format. In some embodiments, the user terminal 22 may include 1 or N cameras 108, where N is a positive integer greater than 1.

[0250] The video codec is used to compress or decompress digital images. The user terminal 22 may support one or more image codecs. In this way, the user terminal 22 can open or save pictures or videos in multiple encoding formats.

[0251] The user terminal 22 can realize the display function through a GPU, a display screen 109, and an application processor. The GPU is a microprocessor for image processing, which connects the display screen 109 and the application processor. The GPU is used to perform mathematical and geometric calculations for graphics rendering. The processor 101 may include one or more GPUs, which execute program instructions to generate or change display information.

[0252] The display screen 109 is used to display images, videos, etc. The display screen 109 includes a display panel. The display panel can be a liquid crystal display (LCD), an organic light-emitting diode (OLED), an active-matrix organic light-emitting diode or an active-matrix organic light-emitting diode (AMOLED), a flexible light-emitting diode (FLED), Miniled, MicroLed, Micro-oLed, a quantum dot light-emitting diode (QLED), etc. In some embodiments, the user terminal 22 may include 1 or N display screens 109, where N is a positive integer greater than 1.

[0253] It is to be understood that the structure illustrated in the embodiment of the present invention does not constitute a specific limitation on the user terminal 22. In other embodiments of the present application, the user terminal 22 may include more or fewer components than shown in the figure, or combine some components, or split some components, or arrange the components differently. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0254] The operations performed by the various components in the user terminal 22 may be specifically referred to the relevant description of the above method embodiment, which will not be elaborated here.

[0255] The software system of the user terminal 22 can adopt a layered architecture, an event-driven architecture, a micro-kernel architecture, a micro-service architecture, or a cloud architecture. The embodiment of the present application takes a mobile operating system with a layered architecture as an example to illustrate the software structure of the user terminal 22.

[0256] See also Fig.13 , Fig.13 It is a software structure block diagram of a user terminal in an embodiment of the present application.

[0257] The layered architecture divides the software into several layers, each with clear roles and division of labor. The layers communicate with each other through software interfaces. In some embodiments, the mobile operating system is divided into four layers, from top to bottom: application layer, application framework layer / core service layer, system library and runtime, and kernel layer.

[0258] The application layer can include a series of application packages.

[0259] like Fig.13 As shown, the application package may include camera, gallery, calendar, call, map, navigation, WLAN, Bluetooth, music, video, short message and other applications.

[0260] The application framework layer provides an application programming interface (API) and a programming framework for the applications in the application layer. The application framework layer includes some predefined functions.

[0261] like Fig.13 As shown, the application framework layer may include a window manager, a content provider, a view system, a phone manager, a resource manager, a notification manager, and the like.

[0262] The window manager is used to manage window programs. The window manager can obtain the display screen size, determine whether there is a status bar, lock the screen, capture the screen, etc.

[0263] Content providers are used to store and retrieve data and make it accessible to applications. The data may include videos, images, audio, calls made and received, browsing history and bookmarks, phone books, etc.

[0264] The view system includes visual controls, such as controls for displaying text, controls for displaying images, etc. The view system can be used to build applications. A display interface can be composed of one or more views. For example, a display interface including a text notification icon can include a view for displaying text and a view for displaying images.

[0265] The phone manager is used to provide communication functions for the user terminal, such as the management of call status (including answering, hanging up, etc.).

[0266] The resource manager provides various resources for applications, such as localized strings, icons, images, layout files, video files, and so on.

[0267] The notification manager enables applications to display notification information in the status bar. It can be used to convey notification-type messages and can disappear automatically after a short stay without user interaction. For example, the notification manager is used to notify download completion, message reminders, etc. The notification manager can also be a notification that appears in the system top status bar in the form of a chart or scroll bar text, such as notifications of applications running in the background, or a notification that appears on the screen in the form of a dialog window. For example, a text message is displayed in the status bar, a prompt sound is emitted, the user terminal vibrates, the indicator light flashes, etc.

[0268] The runtime can refer to all code libraries, frameworks, etc. required for the program to run. For example, for the C language, the runtime includes a series of function libraries required for the C program to run. For the Java language, in addition to the core library, the runtime also includes the virtual machine required for the Java program to run. The above core library may include the function functions that the Java language needs to call.

[0269] The system library may include multiple functional modules, such as surface manager, media library, 3D graphics processing library (such as OpenGL ES), 2D graphics engine (such as SGL), etc.

[0270] The surface manager is used to manage the display subsystem and provide the fusion of 2D and 3D layers for multiple applications.

[0271] The media library supports playback and recording of a variety of commonly used audio and video formats, as well as static image files, etc. The media library can support a variety of audio and video encoding formats, such as: MPEG4, H.264, MP3, AAC, AMR, JPG, PNG, etc.

[0272] The 3D graphics processing library is used to implement 3D graphics drawing, image rendering, compositing, and layer processing.

[0273] A 2D graphics engine is a drawing engine for 2D drawings.

[0274] The kernel layer is the layer between hardware and software. The kernel layer contains at least display driver, camera driver, audio driver, and sensor driver.

[0275] It should be understood that each step in the above method embodiment can be completed by an integrated logic circuit of hardware in a processor or by instructions in the form of software. The method steps disclosed in the embodiments of the present application can be directly embodied as being executed by a hardware processor, or by a combination of hardware and software modules in a processor.

[0276] The present application also provides a user terminal, which may include: a memory and a processor. The memory may be used to store a computer program; the processor may be used to call the computer program in the memory, so that the user terminal executes the method executed by the user terminal side in any of the above embodiments.

[0277] The present application also provides a user terminal, which may include: a memory and a processor. The memory may be used to store a computer program; the processor may be used to call the computer program in the memory, so that the user terminal executes the method executed by the user terminal side in any of the above embodiments.

[0278] The present application also provides a chip system, which includes at least one processor for implementing the functions involved in the user terminal side in any of the above embodiments.

[0279] In one possible design, the chip system also includes a memory, which is used to store program instructions and data, and the memory is located inside or outside the processor.

[0280] The chip system may be composed of the chip, or may include the chip and other discrete devices.

[0281] Optionally, the processor in the chip system may be one or more. The processor may be implemented by hardware or by software. When implemented by hardware, the processor may be a logic circuit, an integrated circuit, etc. When implemented by software, the processor may be a general-purpose processor implemented by reading software code stored in a memory.

[0282] Optionally, the memory in the chip system may also be one or more. The memory may be integrated with the processor or may be separately arranged with the processor, which is not limited in the embodiments of the present application. Exemplarily, the memory may be a non-transient processor, such as a read-only memory ROM, which may be integrated with the processor on the same chip or may be arranged on different chips respectively. The embodiments of the present application do not specifically limit the type of memory and the arrangement of the memory and the processor.

[0283] Exemplarily, the chip system can be a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on chip (SoC), a central processor unit (CPU), a network processor (NP), a digital signal processor (DSP), a microcontroller unit (MCU), a programmable logic device (PLD) or other integrated chips.

[0284] The present application also provides a computer program product, which includes: a computer program (also referred to as code, or instruction), which, when executed, enables a computer to execute the method executed by the user terminal side in any of the above embodiments.

[0285] The present application also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program (also referred to as code or instruction). When the computer program is executed, the computer executes the method executed by the user terminal side in any of the above embodiments.

[0286] The various implementation modes of the present application can be combined arbitrarily to achieve different technical effects.

[0287] In the above embodiments, it 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. When the computer program instructions are loaded and executed on a computer, the process or function described in this 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 a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state disk (SSD)), etc.

[0288] Those skilled in the art can understand that to implement all or part of the processes in the above-mentioned embodiments, the processes can be completed by computer programs to instruct related hardware, and the programs can be stored in computer-readable storage media. When the programs are executed, they can include the processes of the above-mentioned method embodiments. The aforementioned storage media include: ROM or random access memory RAM, magnetic disk or optical disk and other media that can store program codes.

[0289] In short, the above description is only an embodiment of the technical solution of this application, and is not intended to limit the protection scope of this application. Any modification, equivalent replacement, improvement, etc. made according to the disclosure of this application shall be included in the protection scope of this application.

Claims

1. A method for screening recommended content, characterized in that: Applied to a server, the method comprises: Receiving first negative feedback information sent by a user terminal, the first negative feedback information including user identification information, a first recommendation tag and a negative feedback type, the first recommendation tag being used to indicate a recommendation tag associated with recommended content corresponding to the first negative feedback information; updating a user portrait corresponding to the user identification information based on the first negative feedback information, wherein the user portrait includes a negative feedback adjacency matrix; Filtering target recommended content that meets preset conditions based on the updated user portrait, the target recommended content being the recommended content associated with the recommended tag indicated by the historical negative feedback information corresponding to the user identification information; Generate a first recommendation list based on the target recommended content and the updated user portrait; The updating of the user portrait corresponding to the user identification information based on the first negative feedback information includes: Based on the first recommended label, the value of the target matrix point in the negative feedback adjacency matrix is ​​set to 1, the target matrix point is determined based on the user identification information and the first recommended label, the user identification information is used to determine the row corresponding to the target matrix point in the negative feedback adjacency matrix, and the first recommended label is used to determine the column corresponding to the target matrix point in the negative feedback adjacency matrix.

2. The method according to claim 1, characterized in that: The user portrait is used to indicate the user's personal attributes, industry preferences and shopping preferences, and the personal attributes include at least one of gender, age, education level and IP address.

3. The method according to claim 2, characterized in that The filtering of target recommended content that meets preset conditions based on the updated user portrait includes: Based on the activation parameters corresponding to each recommended tag of the updated user portrait; Determine the recommended label corresponding to the activation parameter greater than the preset threshold as the target recommended label; The recommended content associated with the target recommendation tag is determined as the target recommended content.

4. The method according to claim 3, characterized in that The user portrait also includes a user feature matrix, a time matrix, a first activation function, a time scale adjustment function, and a recommended content feature matrix; The method comprises: Calculate a first negative feedback activation matrix corresponding to the user portrait based on the user feature matrix, the time matrix, the first activation function, the time scale adjustment function, and the recommended content feature matrix; Performing mapping processing on the first negative feedback activation matrix to generate a second negative feedback activation matrix; Screen out target matrix points whose values ​​in the second negative feedback activation matrix are less than the preset threshold; The target recommended content is determined based on the target matrix point.

5. The method according to claim 4, characterized in that The method comprises: Based on the formula Calculate the first negative feedback activation matrix, where S is the first negative feedback activation matrix, X is the user feature matrix, is the negative feedback adjacency matrix, s is the first activation function, α is the time scale adjustment function, T is the time matrix, and X′ is the recommended content feature matrix; Using a mapping function to map the first negative feedback activation matrix, mapping the values ​​of each matrix point in the first negative feedback activation matrix to the interval (0,1), and generating the second negative feedback activation matrix; Screening out the target matrix point in the second negative feedback activation matrix, and determining the recommended label and user identification information corresponding to the target matrix point based on the row and column information of the target matrix point; The recommended content associated with the recommended tag corresponding to the target matrix point is determined as the target recommended content.

6. The method according to any one of claims 1 to 5, characterized in that: The generating a first recommendation list based on the target recommended content and the updated user portrait includes: Determining at least one positive feedback recommended content based on the user portrait, the positive feedback recommended content being recommended content that is not associated with a recommendation tag indicated by historical negative feedback information corresponding to the user identification information; Generate the first recommendation list based on the target recommended content and the positive feedback recommended content; The first recommendation list is sent to the user terminal.

7. The method according to claim 6, characterized in that The negative feedback type includes at least one of blacklisting, deleting, giving a bad review, reporting, not interested, and no longer recommending.

8. A method for screening recommended content, characterized in that: Applied to a user terminal, the method comprises: In response to a negative feedback operation by a user, determining a first recommendation tag and a negative feedback type corresponding to the negative feedback operation, wherein the first recommendation tag is a recommendation tag associated with the recommended content corresponding to the negative feedback behavior; Generate first negative feedback information based on the first recommendation tag, the negative feedback type and the user identification information of the user; Sending the first negative feedback information to a server, wherein the first negative feedback information is used to update a user portrait corresponding to the user identification information in the server, wherein the user portrait includes a negative feedback adjacency matrix, wherein the negative feedback adjacency matrix includes a target matrix point, wherein the target matrix point is determined based on the user identification information and the first recommended label, wherein the user identification information is used to determine a row corresponding to the target matrix point in the negative feedback adjacency matrix, and the first recommended label is used to determine a column corresponding to the target matrix point in the negative feedback adjacency matrix; The method further comprises: receiving a first recommendation list sent by the server, where the first recommendation list is generated by the server based on target recommended content and the updated user portrait, and the target recommended content is obtained by screening by the server based on the updated user portrait; Based on the arrangement order of the first recommendation list, the recommended content corresponding to the first recommendation list is presented to the user.

9. The method according to claim 8, characterized in that The negative feedback type includes at least one of blacklisting, deleting, giving a bad review, reporting, not interested, and no longer recommending.

10. The method according to claim 9, characterized in that The first recommendation list includes target recommended content and positive feedback recommended content. The target recommended content is the recommended content associated with the recommendation tag indicated by the historical negative feedback information corresponding to the user identification information, and the positive feedback recommended content is the recommended content not associated with the recommendation tag indicated by the historical negative feedback information corresponding to the user identification information.

11. A server, characterized in that: The method comprises one or more processors and one or more memories; wherein the one or more memories are coupled to the one or more processors, and the one or more memories are used to store computer program codes, wherein the computer program codes include computer instructions, and when the one or more processors execute the computer instructions, the method according to any one of claims 1 to 7 is executed.

12. A user terminal, characterized in that: It comprises one or more processors and one or more memories; wherein, the one or more memories are coupled to the one or more processors, and the one or more memories are used to store computer program codes, and the computer program codes include computer instructions, and when the one or more processors execute the computer instructions, the method as described in any one of claims 8 to 10 is executed.

13. A system for screening recommended content, characterized in that: The system comprises the server according to claim 11 and the user terminal according to claim 12.

14. A computer-readable storage medium comprising instructions, characterized in that: When the instructions are executed on the server, the method according to any one of claims 1 to 7 is executed.

15. A computer-readable storage medium comprising instructions, characterized in that: When the instruction is executed on the user terminal, the method according to any one of claims 8 to 10 is executed.

Images