News recommendation method and system based on user portrait dynamic configuration recall strategy

Abstract

The invention relates to a news recommendation method and system based on a user portrait dynamic configuration recall strategy, and the method comprises the steps: collecting the historical behavior data of a user, constructing a user portrait, and extracting the features of the user portrait; dynamically configuring a recall strategy based on user portrait features, and selecting an optimal recall channel by calculating weights and scores of recall channels; and according to user portrait features and a recall strategy determined based on the optimal recall channel, recalling news from the news database, generating a personalized recommendation list through a sorting model, and according to user behavior feedback, optimizing a recommendation result in real time. By collecting and analyzing the user behavior data, constructing the accurate user portrait, dynamically configuring the recall strategy and optimizing the recommendation result according to the real-time feedback of the user, the news recommendation accuracy and the user satisfaction can be remarkably improved, and the user experience is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of news recommendation, and in particular to a news recommendation method and system for dynamically configuring a recall strategy based on user portraits. Background Art

[0002] In the modern information society, users' demand for news and information is increasing. However, faced with a huge amount of information, how to push the news that best suits users' interests and needs to users has become an important technical challenge. Existing news recommendation systems usually rely on fixed recommendation algorithms and strategies, which are difficult to respond to changes in user interests in real time, resulting in low accuracy of recommendation results and low user satisfaction.

[0003] Traditional recommendation methods are mainly based on collaborative filtering, content-based recommendation and hybrid recommendation strategies. These methods have the following shortcomings: First, the collaborative filtering method relies on a large amount of user behavior data and is difficult to provide accurate recommendations in cold start situations; second, although the content-based recommendation method can solve the cold start problem to a certain extent, its capture of user interests is relatively static and it is difficult to dynamically reflect changes in user interests; finally, although the hybrid recommendation method combines multiple recommendation strategies, it is highly complex and has poor real-time performance, making it difficult to dynamically adjust according to user feedback. Summary of the invention

[0004] The purpose of the present invention is to provide a news recommendation method and system for dynamically configuring a recall strategy based on user portraits, so as to solve the problems of poor accuracy and real-time performance of the prior art results.

[0005] To achieve one of the above-mentioned purposes of the invention, an embodiment of the present invention provides a news recommendation method for dynamically configuring a recall strategy based on a user profile, the method comprising: Collect users' historical behavior data to build user portraits and extract user portrait features; Based on user profile features, dynamically configure the recall strategy and select the optimal recall channel by calculating the weight and score of the recall channel; According to the user portrait characteristics and the recall strategy determined based on the optimal recall channel, news is recalled from the news database, a personalized recommendation list is generated through the sorting model, and the recommendation results are optimized in real time based on user behavior feedback.

[0006] As a further improvement of an embodiment of the present invention, the method further includes that the “collecting historical behavior data of the user to construct a user portrait, and extracting user portrait features” includes: The collected user historical behavior data includes user browsing history, click history, search history, subscription history, sharing behavior, comments and likes, and stay time data; Preprocessing the historical behavior data of the user to construct a user profile; the preprocessing includes data cleaning and filtering noise data; Perform feature extraction on the preprocessed user's historical behavior data to generate m user portrait features ;in, is the total number of user portrait features; The feature extraction includes extracting the user's points of interest, active time periods, active areas, and preference categories.

[0007] As a further improvement of an embodiment of the present invention, the method further includes that the dynamic configuration of the recall strategy based on the user portrait features includes: based on User portrait features are determined Recall Channel ; Recall Channel From m_i user portrait features Determine, where m_i is the number of user portrait features based on the i-th recall channel, and m_i≤m, i represents the index of the recall channel; The update time corresponding to each user portrait feature u_ij is .

[0008] As a further improvement of an embodiment of the present invention, the method further includes: calculating the weight of the recall channel includes: Calculate the weight of each user portrait feature using the following formula: in, Characterize user portraits The weight of is the j-th user portrait feature of the i-th recall channel, is the current time, is the update time of u_ij, The time impact period of user portrait features; Calculate the global recall weight of all user portrait features using the following formula: in, is the global recall weight of the ith channel, is an empirical constant, with a value between [0, 1], is the recommendation click rate of the i-th recall channel within the time impact period, is the maximum click rate within the time impact period of all recall channels, It is the minimum click rate within the time impact period of all recall channels.

[0009] As a further improvement of an embodiment of the present invention, the method further includes that calculating the score of the recall channel includes: Calculate the personalized recall weight of user k. The calculation formula is: in, is the weight of the j-th user portrait feature of the i-th recall channel of user k, User portrait features for user k The corresponding update time, is the personalized weight of the i-th recall channel of user k; Based on the global recall weight and the personalized recall weight, the comprehensive recall score of the recall channel is calculated using the following formula: in, is the comprehensive recall score of the i-th recall channel of user k, is the basic score of the i-th recall channel; A constant to determine whether the recall channel is an offline channel. When the recall channel is an offline channel, , otherwise ω=0; is the offline recall coefficient, is the real-time recall coefficient, is an empirical constant, ranging from [0, 1].

[0010] As a further improvement of an embodiment of the present invention, the method further includes: selecting the optimal recall channel includes: For the recall channel r_i, according to the recall score Sort in descending order and select the first n recall channels with the highest recall scores as the optimal recall channels for user k.

[0011] As a further improvement of an embodiment of the present invention, the method further includes: the “recalling news from a news database according to user portrait features and a recall strategy determined based on an optimal recall channel, and generating a personalized recommendation list through a ranking model” includes: Preliminarily screening candidate news from a news database according to the user portrait features, and obtaining a recalled news list for each user according to the recall strategy; By calculating the comprehensive recall score of each candidate news item in the recalled news list, the candidate news list is prioritized, and a portion of the news items with the highest scores are selected to generate a recommendation list.

[0012] To achieve one of the above-mentioned purposes of the invention, an embodiment of the present invention further provides a news recommendation system for dynamically configuring a recall strategy based on a user portrait, the system comprising a collection module, a calculation module and a recommendation module; The collection module is used to collect the user's historical behavior data to construct a user portrait and extract user portrait features; The calculation module is used to dynamically configure the recall strategy based on the user portrait features, and select the optimal recall channel by calculating the weights and scores of the recall channels; The recommendation module is used to recall news from the news database according to user portrait features and a recall strategy determined based on the optimal recall channel, generate a personalized recommendation list through a sorting model, and optimize the recommendation results in real time according to user behavior feedback.

[0013] To achieve one of the above-mentioned purposes of the invention, an embodiment of the present invention further provides an electronic device, comprising a memory and a processor, characterized in that the memory stores a computer program that can be run on the processor, and when the program is executed on the processor, the steps in the news recommendation method for dynamically configuring the recall strategy based on the user portrait as described above are implemented.

[0014] To achieve one of the above-mentioned purposes of the invention, an embodiment of the present invention further provides a storage medium, wherein the storage medium stores a computer program, and wherein the computer program, when executed by a processor, implements the steps in the news recommendation method for dynamically configuring a recall strategy based on a user portrait as described above.

[0015] Compared with the prior art, the present invention provides a news recommendation method and system for dynamically configuring a recall strategy based on user portraits. By collecting and analyzing user behavior data, an accurate user portrait is constructed, a recall strategy is dynamically configured, and recommendation results are optimized according to real-time user feedback. This can significantly improve the accuracy of news recommendations and user satisfaction, and enhance user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is an overall flow chart of the news recommendation method of the present invention that dynamically configures the recall strategy based on user portraits.

[0017] Figure 2 It is a schematic diagram of the architecture of the news recommendation system for dynamically configuring the recall strategy based on user portraits according to the present invention. DETAILED DESCRIPTION

[0018] The present invention will be described in detail below in conjunction with the specific embodiments shown in the accompanying drawings. However, these embodiments do not limit the present invention, and any structural, methodological, or functional changes made by a person skilled in the art based on these embodiments are all within the scope of protection of the present invention.

[0019] The embodiments of the present invention are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be understood as limiting the present invention.

[0020] In the first embodiment of the present invention, an implementation mode of the present invention provides a news recommendation method for dynamically configuring a recall strategy based on a user profile, such as Figure 1 As shown, the method includes, S1: Collect historical behavior data of users to build user profiles and extract user profile features; S2: Dynamically configure the recall strategy based on user profile features, and select the optimal recall channel by calculating the weight and score of the recall channel; S3: Based on the user portrait features and the recall strategy determined based on the optimal recall channel, news is recalled from the news database, a personalized recommendation list is generated through the sorting model, and the recommendation results are optimized in real time based on user behavior feedback.

[0021] In a specific embodiment of the present invention, historical behavior data of users is collected to construct user portraits, and user portrait features are extracted, specifically, The collected user historical behavior data includes user browsing history, click history, search history, subscription history, sharing behavior, comments and likes, and stay time data; Preprocessing the historical behavior data of the user to construct a user profile; the preprocessing includes data cleaning and filtering noise data; Perform feature extraction on the preprocessed user's historical behavior data to generate m user portrait features ;in, is the total number of user portrait features; The feature extraction includes extracting the user's points of interest, active time periods, active areas, and preference categories.

[0022] It should be noted that before feature extraction, the user's historical behavior data needs to be preprocessed. Preprocessing includes data cleaning and filtering noise data to ensure the accuracy and reliability of subsequent analysis. Data cleaning mainly removes invalid, erroneous or duplicate data, and filtering noise data excludes interference data that is irrelevant to the construction of user portraits. After preprocessing, the feature extraction stage begins. Feature extraction includes extracting key features from the user's behavior data, such as the user's points of interest (i.e., the type of content that the user browses and clicks most frequently), active time periods (the time period in a day when the user is most active), active areas (the geographical location where the user is most active), and preference categories (the content category that the user is most interested in). These features can reflect the user's behavior patterns and interest tendencies from multiple perspectives, together forming a user portrait, describing in detail the interests and behavior patterns of each user, and providing an accurate data foundation for subsequent recommendation algorithms.

[0023] In a specific embodiment of the present invention, based on the user portrait features, the recall strategy is dynamically configured, specifically, based on User portrait features are determined Recall Channel ; Recall Channel From m_i user portrait features Determine, where m_i is the number of user portrait features based on the i-th recall channel, and m_i≤m, i represents the index of the recall channel; The update time corresponding to each user portrait feature u_ij is .

[0024] It should be noted that the update time corresponding to each user portrait feature reflects the latest level of user behavior data. By analyzing the update time, the timeliness of each feature can be evaluated to ensure that the recall channel can dynamically respond to changes in user interests and provide the latest and most relevant news content.

[0025] In a specific embodiment of the present invention, the weight of the recall channel is calculated as follows: Calculate the weight of each user portrait feature using the following formula: in, Characterize user portraits The weight of is the j-th user portrait feature of the i-th recall channel, is the current time, is the update time of u_ij, The time impact period of user portrait features; Calculate the global recall weight of all user portrait features using the following formula: in, is the global recall weight of the ith channel, is an empirical constant, with a value between [0, 1], is the recommendation click rate of the i-th recall channel within the time impact period, is the maximum click rate within the time impact period of all recall channels, It is the minimum click rate within the time impact period of all recall channels.

[0026] It should be noted that in order to more comprehensively evaluate the collinearity of each recall channel and provide more reliable weights for subsequent fusion sorting, it is necessary to comprehensively consider the timeliness of user portrait features, the overall performance of the channel, and the adjustment of experience parameters; Furthermore, the contribution of each user portrait feature to the current recommendation is measured by calculating the weight of the user portrait feature. From the formula, we can see that the weight of the user portrait feature decays linearly over time. The newer the user, the higher the weight. When the update time of the user portrait feature exceeds , its weight is considered to be 0 and no longer affects the recommendation.

[0027] Furthermore, by calculating the global recall weight, the overall weight of each recall channel is calculated, taking into account the weight of the user portrait feature and the overall performance of the channel; the first item calculates the average value of the weights of all user portrait features, reflecting the overall quality of the user portrait features of the channel, and the second item calculates the relative position of the click-through rate of the channel among all channels, reflecting the overall performance of the channel; by adjusting the value of β, the influence ratio of the weight of the user portrait feature and the channel click-through rate in the final weight can be controlled; when β is close to 1, the weight of the user portrait feature has a greater impact; when β is close to 0, the channel click-through rate has a greater impact.

[0028] In a specific embodiment of the present invention, the score of the recall channel is calculated as follows: Calculate the personalized recall weight of user k. The calculation formula is: in, is the weight of the j-th user portrait feature of the i-th recall channel of user k, User portrait features for user k The corresponding update time, is the personalized weight of the i-th recall channel of user k; Based on the global recall weight and the personalized recall weight, the comprehensive recall score of the recall channel is calculated using the following formula: in, is the comprehensive recall score of the i-th recall channel of user k, is the basic score of the i-th recall channel; A constant to determine whether the recall channel is an offline channel. When the recall channel is an offline channel, , otherwise ω=0; is the offline recall coefficient, is the real-time recall coefficient, is an empirical constant, ranging from [0, 1].

[0029] It should be noted that by calculating the comprehensive recall score, the basic score of the recall channel, the coefficients of offline and real-time recall, and the influence of global and personalized weights are taken into account, and the final comprehensive recall score is calculated by weighted average. This method can more accurately evaluate the comprehensive score of each recall channel by combining global and personalized weights and considering the different characteristics of offline and real-time recall, thereby selecting the optimal recall channel in the news recommendation process and improving the accuracy of recommendation results and user satisfaction.

[0030] In a specific embodiment of the present invention, the optimal recall channel is selected, specifically, For the recall channel r_i, according to the recall score Sort in descending order and select the first n recall channels with the highest recall scores as the optimal recall channels for user k.

[0031] It should be noted that the sorting is in reverse order, that is, the recall channels with higher scores are arranged in front. In this way, it is possible to intuitively see which recall channels have higher recommendation value and effect based on the current user portrait characteristics and historical behavior data. The top n recall channels with the highest scores are selected from the sorted recall channels as the optimal recall channels for user k. These optimal recall channels will serve as the main channels for news recall in the subsequent recommendation process. By selecting the top n channels with the highest scores, it can be ensured that the recommended news content meets the user's interests and preferences as much as possible, thereby improving the accuracy of the recommendation results and user satisfaction.

[0032] In a specific embodiment of the present invention, news is recalled from a news database according to user portrait features and a recall strategy determined based on an optimal recall channel, and a personalized recommendation list is generated through a sorting model, specifically, Preliminarily screening candidate news from a news database according to the user portrait features, and obtaining a recalled news list for each user according to the recall strategy; By calculating the comprehensive recall score of each candidate news item in the recalled news list, the candidate news list is prioritized, and a portion of the news items with the highest scores are selected to generate a recommendation list.

[0033] It should be noted that the degree of match between each news item and the user's interest is determined by calculating the comprehensive recall score of the candidate news items. The calculation of the comprehensive recall score combines multiple factors, including the relevance of the news content, the timeliness of the news, the user's historical behavior data, etc. Through such calculation, each candidate news item will be given a specific score, reflecting its recommendation value to the current user. All candidate news items are prioritized according to the comprehensive recall score. The sorting is reversed, that is, the news with the higher comprehensive recall score is arranged first. This ensures that the most relevant and user-friendly news is displayed to the user first. Select a part of the news items with the highest comprehensive recall score to generate a personalized recommendation list. Determine the specific number of recommended news based on the user's reading habits and the number of news required. The generated recommendation list will give priority to the news with the highest score, ensuring the high quality and high relevance of the recommended content, thereby improving the user's reading experience and satisfaction.

[0034] In the second embodiment of the present invention, the present invention provides a news recommendation system for dynamically configuring a recall strategy based on a user profile, such as Figure 2 As shown, the system includes a collection module 1, a calculation module 2 and a recommendation module 3; The acquisition module 1 is used to collect the user's historical behavior data to construct a user portrait and extract user portrait features; The calculation module 2 is used to dynamically configure the recall strategy based on the user portrait features, and select the optimal recall channel by calculating the weight and score of the recall channel; The recommendation module 3 is used to recall news from the news database according to user portrait features and a recall strategy determined based on the optimal recall channel, generate a personalized recommendation list through a sorting model, and optimize the recommendation results in real time according to user behavior feedback.

[0035] In a third embodiment of the present invention, the present invention provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the program is executed on the processor, the steps in the news recommendation method for dynamically configuring a recall strategy based on user portraits as described above are implemented.

[0036] In a fourth embodiment of the present invention, the present invention provides a storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the steps of the news recommendation method for dynamically configuring a recall strategy based on a user portrait as described above.

[0037] In summary, the present invention provides a news recommendation method and system for dynamically configuring a recall strategy based on user portraits. By collecting and analyzing user behavior data, building accurate user portraits, dynamically configuring recall strategies, and optimizing recommendation results based on real-time user feedback, the accuracy of news recommendations can be significantly improved, as well as user satisfaction, thereby enhancing user experience.

[0038] It should be understood that although this specification is described according to implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each implementation mode may also be appropriately combined to form other implementation modes that can be understood by those skilled in the art.

[0039] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the modules described above can refer to the corresponding process in the aforementioned method implementation, and will not be repeated here.

[0040] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present implementation scheme.

[0041] In addition, each functional module in each embodiment of the present application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The above integrated modules can be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0042] The above-mentioned integrated module implemented in the form of a software function module can be stored in a computer-readable storage medium. The above-mentioned software function module is stored in a storage medium, including a number of instructions for a computer system (which can be a personal computer, a server, or a network system, etc.) or a processor to perform some steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program codes.

[0043] Finally, it should be noted that the above implementation modes are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned implementation modes, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned implementation modes, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various implementation modes of the present application.

Claims

1. A news recommendation method for dynamically configuring a recall strategy based on user portraits, characterized in that: include, Collect users' historical behavior data to build user portraits and extract user portrait features; Based on user profile features, dynamically configure the recall strategy and select the optimal recall channel by calculating the weight and score of the recall channel; According to the user portrait characteristics and the recall strategy determined based on the optimal recall channel, news is recalled from the news database, a personalized recommendation list is generated through the sorting model, and the recommendation results are optimized in real time based on user behavior feedback.

2. The news recommendation method based on user portrait dynamic configuration recall strategy according to claim 1 is characterized by: The "collecting historical behavior data of users to construct user portraits and extracting user portrait features" includes: The collected user historical behavior data includes user browsing history, click history, search history, subscription history, sharing behavior, comments and likes, and stay time data; Preprocessing the historical behavior data of the user to construct a user profile; The preprocessing includes data cleaning and filtering noise data; Perform feature extraction on the preprocessed user's historical behavior data to generate m user portrait features ;in, is the total number of user portrait features; The feature extraction includes extracting the user's points of interest, active time periods, active areas, and preference categories.

3. The news recommendation method based on user portrait dynamic configuration recall strategy according to claim 2 is characterized by: The dynamic configuration recall strategy based on user portrait features includes: based on User portrait features are determined Recall Channel ; Recall Channel From m_i user portrait features Determine, where m_i is the number of user portrait features based on the i-th recall channel, and m_i≤m, i represents the index of the recall channel; The update time corresponding to each user portrait feature u_ij is .

4. The news recommendation method based on user portrait dynamic configuration recall strategy according to claim 3 is characterized by: Calculating the weight of the recall channel includes, Calculate the weight of each user portrait feature using the following formula: ， in, Characterize user portraits The weight of is the j-th user portrait feature of the i-th recall channel, is the current time, is the update time of u_ij, The time impact period of user portrait features; Calculate the global recall weight of all user portrait features using the following formula: ， in, is the global recall weight of the ith channel, is an empirical constant, with a value between [0, 1], is the recommendation click rate of the i-th recall channel within the time impact period, is the maximum click rate within the time impact period of all recall channels, It is the minimum click rate within the time impact period of all recall channels.

5. The news recommendation method based on user portrait dynamic configuration recall strategy according to claim 4 is characterized by: Calculating the recall channel score includes, Calculate the personalized recall weight of user k. The calculation formula is: ， ， in, is the weight of the j-th user portrait feature of the i-th recall channel of user k, User portrait features for user k The corresponding update time, is the personalized weight of the i-th recall channel of user k; Based on the global recall weight and the personalized recall weight, the comprehensive recall score of the recall channel is calculated using the following formula: ， in, is the comprehensive recall score of the i-th recall channel of user k, is the basic score of the i-th recall channel; A constant used to determine whether the recall channel is an offline channel. When the recall channel is an offline channel, , otherwise ω=0; is the offline recall coefficient, is the real-time recall coefficient, is an empirical constant, ranging from [0, 1].

6. The news recommendation method based on user portrait dynamic configuration recall strategy according to claim 5 is characterized by: The selecting of the optimal recall channel includes: For the recall channel r_i according to the recall score Sort in descending order and select the first n recall channels with the highest recall scores as the optimal recall channels for user k.

7. The news recommendation method based on user portrait dynamic configuration recall strategy according to claim 1 is characterized by: The "recalling news from the news database based on user portrait features and a recall strategy determined based on an optimal recall channel, and generating a personalized recommendation list through a sorting model" includes: Preliminarily screening candidate news from a news database according to the user portrait features, and obtaining a recalled news list for each user according to the recall strategy; By calculating the comprehensive recall score of each candidate news item in the recalled news list, the candidate news list is prioritized, and a portion of the news items with the highest scores are selected to generate a recommendation list.

8. A news recommendation system with dynamic configuration of recall strategy based on user portrait, characterized by: It includes acquisition module, calculation module and recommendation module; The collection module is used to collect the user's historical behavior data to construct a user portrait and extract user portrait features; The calculation module is used to dynamically configure the recall strategy based on the user portrait features, and select the optimal recall channel by calculating the weights and scores of the recall channels; The recommendation module is used to recall news from the news database according to user portrait features and a recall strategy determined based on the optimal recall channel, generate a personalized recommendation list through a sorting model, and optimize the recommendation results in real time according to user behavior feedback.

9. An electronic device, comprising a memory and a processor, characterized in that: The memory stores a computer program that can be run on the processor, and when the program is executed on the processor, the steps in the news recommendation method for dynamically configuring a recall strategy based on a user portrait as described in any one of claims 1 to 7 are implemented.

10. A storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the news recommendation method for dynamically configuring a recall strategy based on a user portrait as described in any one of claims 1 to 7 are implemented.

Images