Information content recommendation method and device, computer device, and storage medium

Abstract

Embodiments of the present application disclose information content recommendation method and device, computer equipment and storage medium. The method comprises: setting the proportion value of the feature classification in the user portrait in the information recommendation, and setting the latest information proportion value; filtering information content meeting a first requirement by using the most important feature label in the user portrait, filtering information content meeting a second requirement by using the behavior data label in the user portrait; filtering information content meeting a third requirement by using the basic attribute data label in the user portrait; filtering information content meeting a fourth requirement according to the information publishing time; performing a merging operation to obtain an operation result; sorting the operation result; and sending the sorted result to a terminal. The method can improve the demand hit rate of users viewing information content, reduce the information cocoon house with smaller and smaller recommended information range, and improve the activity rate and retention rate of users.

Description

TECHNICAL FIELD

[0001] The present application relates to computers, and more particularly to an information content recommendation method and device, a computer device and a storage medium. BACKGROUND

[0002] Intelligent recommendation of information based on user portraits is a method of recommending information. Generally, user data is obtained, the user is tagged, the platform content is also tagged, the user tag and the platform content tag are matched, and the content with high matching degree is recommended.

[0003] In the prior art, user portrait data is generated based on user browsing behavior records. One problem is that the recommended content is difficult to reach the user demand because the user browsing content often has uncertainty. Another problem is that after the user browses a type of content, the user portrait has the content tag of this type, and the recommendation system continues to push the content according to the tag, which is very easy to make the user enter the information cocoon house. The two problems ultimately lead to the loss of users.

[0004] Therefore, it is necessary to design a new method to improve the demand hit rate of users viewing information content, reduce the information cocoon house with a smaller and smaller range of recommended information, and improve the activity rate and retention rate of users. SUMMARY

[0005] The present application aims to overcome the defects of the prior art and provide an information content recommendation method, device, computer device and storage medium.

[0006] To achieve the above-mentioned purpose, the present application adopts the following technical scheme: an information content recommendation method, comprising:

[0007] Setting a feature classification proportion value in the user portrait to obtain a feature proportion value;

[0008] Setting a latest information proportion value;

[0009] Using the most important feature tag in the user portrait to filter information content meeting the first requirement from the information database to obtain first information content;

[0010] Using the behavior data tag in the user portrait to filter information content meeting the second requirement from the information database to obtain second information content;

[0011] Using the basic attribute data tag in the user portrait to filter information content meeting the third requirement from the information database to obtain third information content;

[0012] Filtering information content meeting the fourth requirement according to the information publishing time to obtain fourth information content;

[0013] Merging the first information content, the second information content, the third information content and the fourth information content to obtain an operation result;

[0014] Sorting the operation result to obtain a sorting result;

[0015] Sending the sorting result to a terminal to display the information content meeting the requirements in the sorting result on the terminal.

[0016] Further technical solutions thereof are as follows: the first information content is obtained by screening information content meeting the first requirement from the information database by using the most important feature label in the user portrait, and the method comprises the following steps:

[0017] The information content corresponding to the label matching is obtained from the information database according to the feature label in the user portrait to obtain a first matching result, wherein the number of the first matching result is N*i*feature proportion value, N is the number of information lists displayed on the user terminal at a time, and i is an integer greater than zero;

[0018] The information read by the user is filtered from the first matching result to obtain a first filtering result;

[0019] It is judged whether the number of the first filtering result is less than a value set by the first requirement;

[0020] If the number of the first filtering result is less than the value set by the first requirement, i is increased by one, and the information content corresponding to the label matching is obtained from the information database according to the feature label in the user portrait to obtain a first matching result, wherein the number of the first matching result is N*i*feature proportion value, N is the number of information lists displayed on the user terminal at a time, and i is an integer greater than zero;

[0021] If the number of the first filtering result is not less than the value set by the first requirement, the first filtering result is temporarily stored in a computer storage medium to obtain the first information content.

[0022] Further technical solutions thereof are as follows: the second information content is obtained by screening information content meeting the second requirement from the information database by using the behavior data label in the user portrait, and the method comprises the following steps:

[0023] The information content corresponding to the label matching is obtained from the information database based on the behavior data label in the user portrait to obtain a second matching result, wherein the number of the second matching result is N*i*feature proportion value, N is the number of information lists displayed on the user terminal at a time, and i is an integer greater than zero;

[0024] The information read by the user is filtered from the second matching result to obtain a second filtering result;

[0025] determining whether the number of the second filtered results is less than a number set by a second requirement;

[0026] if the number of the second filtered results is less than the number set by the second requirement, then i is increased by one, and the third matching results are obtained by matching the corresponding information contents from the information database based on the basic attribute data tags in the user portrait, wherein the number of the third matching results is N*i*basic attribute proportion value, N is the number of information lists displayed on the user terminal at one time, and i is an integer greater than zero;

[0027] if the number of the second filtered results is not less than the number set by the second requirement, then the second filtered results are temporarily stored in the computer storage medium to obtain the second information contents.

[0028] A further technical solution is that the information contents meeting a third requirement are screened from the information database based on the basic attribute data tags in the user portrait to obtain third information contents, which includes:

[0029] the third matching results are obtained by matching the corresponding information contents from the information database based on the basic attribute data tags in the user portrait, wherein the number of the third matching results is N*i*basic attribute proportion value, N is the number of information lists displayed on the user terminal at one time, and i is an integer greater than zero;

[0030] the third matching results are filtered to obtain third filtered results;

[0031] determining whether the number of the third filtered results is less than a number set by a third requirement;

[0032] if the number of the third filtered results is less than the number set by the third requirement, then i is increased by one, and the third matching results are obtained by matching the corresponding information contents from the information database based on the basic attribute data tags in the user portrait, wherein the number of the third matching results is N*i*basic attribute proportion value, N is the number of information lists displayed on the user terminal at one time, and i is an integer greater than zero;

[0033] if the number of the third filtered results is not less than the number set by the third requirement, then the third filtered results are temporarily stored in the computer storage medium to obtain the third information contents.

[0034] A further technical solution is that the information contents meeting a fourth requirement are screened according to the information publishing time to obtain fourth information contents, which includes:

[0035] According to the information release time, a plurality of information contents newly released are taken out to obtain a taking-out result, wherein the number of the taking-out result is N*i*latest information proportion value, N is the number of information list displayed by the user terminal at one time, and i is an integer greater than zero;

[0036] The taking-out result is filtered to obtain a fourth filtering result;

[0037] It is judged whether the fourth filtering result is less than a fourth requirement set value;

[0038] If the fourth filtering result is less than the fourth requirement set value, i is increased by one, and according to the information release time, a plurality of information contents newly released are taken out to obtain a taking-out result, wherein the number of the taking-out result is N*i*latest information proportion value, N is the number of information list displayed by the user terminal at one time, and i is an integer greater than zero;

[0039] If the fourth filtering result is not less than the fourth requirement set value, the fourth filtering result information is temporarily stored in the computer storage medium to obtain the fourth information content.

[0040] Further technical solutions of the present application are as follows:

[0041] The operation result is randomly rearranged, and a plurality of information contents after rearrangement are taken out to obtain a sorting result.

[0042] The present application also provides an information content recommendation device, comprising:

[0043] A first setting unit is configured to set a feature classification proportion value in a user portrait in information recommendation to obtain a feature proportion value;

[0044] A second setting unit is configured to set a latest information proportion value;

[0045] A first screening unit is configured to screen information contents meeting a first requirement from an information database by using a most important feature label in a user portrait to obtain first information contents;

[0046] A second screening unit is configured to screen information contents meeting a second requirement from the information database by using a behavior data label in the user portrait to obtain second information contents;

[0047] A third screening unit is configured to screen information contents meeting a third requirement from the information database by using a basic attribute data label in the user portrait to obtain third information contents;

[0048] A fourth screening unit is configured to screen information contents meeting a fourth requirement according to information release time to obtain fourth information contents;

[0049] The merging unit is used to perform a merging operation on the first information content, the second information content, the third information content, and the fourth information content to obtain the operation result;

[0050] A sorting unit is used to sort the operation results to obtain a sorted result;

[0051] A sending unit is used to send the sorting results to a terminal so that the terminal can display the information content that meets the requirements in the sorting results.

[0052] The further technical solution is as follows: The first screening unit includes:

[0053] The first matching subunit is used to match the corresponding information content from the information database based on the feature tags in the user profile to obtain the first matching result. The number of the first matching results is N*i*feature weight value, where N is the number of information lists displayed by the user at one time, and i is an integer greater than zero.

[0054] The first filtering subunit is used to filter out information that the user has already read from the first matching result to obtain the first filtering result;

[0055] The first judgment subunit is used to determine whether the number of the first filtering results is less than the value set by the first requirement;

[0056] An additional subunit is added, which is used to increment i by one if the number of the first filtering results is less than the value set by the first requirement, and to perform the matching of the corresponding information content from the information database based on the feature tags in the user profile to obtain the first matching result, wherein the number of the first matching results is N*i*feature weight value, N is the number of information lists displayed by the user terminal at one time, and i is an integer greater than zero.

[0057] The first temporary storage subunit is used to temporarily store the first filtering results in a computer storage medium to obtain the first information content if the number of the first filtering results is not less than the value set by the first requirement.

[0058] The present invention also provides a computer device, the computer device including a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the above-described method.

[0059] The present invention also provides a storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0060] The beneficial effects of this invention compared with the prior art are as follows: This invention improves the recommendation hit rate by setting the recommendation weight value of user profile feature classification, filtering information content related to the weight value, increasing the recommendation weight value of the latest information content, and filtering information content related to the recommendation weight value of the latest information content. This improves the hit rate of users' information viewing needs, reduces the increasingly narrow information cocoon of recommended information, and improves user activity and retention rates.

[0061] The present invention will be further described below with reference to the accompanying drawings and specific embodiments. Attached Figure Description

[0062] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0063] Figure 1 This is a schematic diagram illustrating an application scenario of the information content recommendation method provided in this embodiment of the invention;

[0064] Figure 2 A flowchart illustrating the information content recommendation method provided in an embodiment of the present invention;

[0065] Figure 3 A schematic diagram of a sub-process of the information content recommendation method provided in an embodiment of the present invention;

[0066] Figure 4 A schematic diagram of a sub-process of the information content recommendation method provided in an embodiment of the present invention;

[0067] Figure 5 A schematic diagram of a sub-process of the information content recommendation method provided in an embodiment of the present invention;

[0068] Figure 6 A schematic diagram of a sub-process of the information content recommendation method provided in an embodiment of the present invention;

[0069] Figure 7 A schematic block diagram of an information content recommendation device provided in an embodiment of the present invention;

[0070] Figure 8 A schematic block diagram of the first filtering unit of the information content recommendation device provided in the embodiments of the present invention;

[0071] Figure 9 A schematic block diagram of the second filtering unit of the information content recommendation device provided in the embodiments of the present invention;

[0072] Figure 10A schematic block diagram of the third filtering unit of the information content recommendation device provided in the embodiments of the present invention;

[0073] Figure 11 A schematic block diagram of the fourth filtering unit of the information content recommendation device provided in the embodiments of the present invention;

[0074] Figure 12 A schematic block diagram of a computer device provided for an embodiment of the present invention. Detailed Implementation

[0075] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0076] It should be understood that, when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0077] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0078] It should also be further understood that the term "and / or" as used in this specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0079] Please see Figure 1 and Figure 2 , Figure 1 This is a schematic diagram illustrating an application scenario of the information content recommendation method provided in an embodiment of the present invention. Figure 2 This is a schematic flowchart illustrating the information content recommendation method provided in an embodiment of the present invention. The method is applied in a server. The server interacts with the terminal, and by setting recommendation weights for multiple feature types in the user profile within the recommendation system, it increases the hit rate of users' information content viewing needs; simultaneously, it increases the weight of the latest information recommendations, reducing the increasingly narrow information cocoon effect; through these two recommendation effects, it improves user activity and retention rates.

[0080] Figure 2 This is a flowchart illustrating the information content recommendation method provided in an embodiment of the present invention. For example... Figure 2 As shown, the method includes the following steps S110 to S190.

[0081] S110. Set the weight value of feature classification in user profile in information recommendation to obtain the feature weight value.

[0082] In this embodiment, the feature weight values ​​include the weight values ​​of the most important features, the weight values ​​of behavioral data features, and the weight values ​​of basic attributes.

[0083] For the most important feature weight value, such as the user's disease diagnosis tag, which can be considered the user's most important feature, set the coefficient value that the scores corresponding to the user's diagnosis tag can be multiplied. For example, if it is set to 5, then the weight value of the most important feature is 5.

[0084] For the weighting value of behavioral data features, such as the data tags formed by users' click-reading and rating behavior of popular science articles, set the coefficient value that the scores corresponding to the user behavioral data tags can be multiplied. For example, if it is set to 2, the weighting value of the behavioral data features is 2.

[0085] For the weighting value of basic attributes, information such as user gender, current age, and city are used as data labels that users do not change frequently. The default score of the basic attribute label is 1. Set the coefficient value that the scores of the user's basic attribute labels can be multiplied. For example, if it is set to 1, the weighting value of the basic attribute is 1.

[0086] Specifically, in the information content recommendation system, the weight value of feature classification in user profiles in information recommendation is set to an integer greater than 0 and less than 10.

[0087] S120, Set the weight value of the latest information.

[0088] For the weighting of the latest information, such as the daily hot news content, the default weighting is 1. You can set a coefficient that the weighting of the latest information content that the user can accept can be multiplied. For example, if you set it to 5, the user's acceptable weighting of the latest information is 5.

[0089] In this embodiment, the weight value of the latest information refers to the weight value of the latest information.

[0090] Specifically, in the information content recommendation system, a weight value for the latest information is set, which is an integer greater than 0 and less than 10.

[0091] S130. Use the most important feature tags in the user profile to filter information content that meets the first requirement from the information database to obtain the first information content.

[0092] In this embodiment, the first information content refers to the amount of information content related to the feature weight value, which is selected based on the most important feature tags in the user profile.

[0093] In one embodiment, please refer to Figure 3 The above-mentioned step S130 may include steps S131 to S135.

[0094] S131. Based on the feature tags in the user profile, the information content corresponding to the tags is matched from the information database to obtain the first matching result. The number of the first matching results is N*i*feature weight value, where N is the number of information lists displayed by the user at one time, and i is an integer greater than zero.

[0095] In this embodiment, the first matching result refers to the information content in the information database that is matched with the corresponding number of N*i*feature weight values ​​based on the feature tags in the user profile.

[0096] S132. Filter out the information that the user has already read from the first matching result to obtain the first filtering result.

[0097] In this embodiment, the first filtering result refers to the information content remaining after filtering out the information that the user has already read from the first matching result.

[0098] S133. Determine whether the number of the first filtering results is less than the value set by the first requirement;

[0099] S134. If the number of the first filtering results is less than the value set by the first requirement, then increment i by one and execute step S131.

[0100] S135. If the number of the first filtering results is not less than the value set by the first requirement, the first filtering results are temporarily stored in the computer storage medium to obtain the first information content.

[0101] Specifically, based on the most important feature tags in the user profile, such as health feature tags, (N*i*health feature weight value) pieces of information content are matched from the information database, where N is the number of information lists displayed to the user at one time, i can be an integer greater than 0, and the health feature weight value is the value set in S11. The results retrieved in S131 are filtered to remove information that the user has already read. If the number of filtered information items is less than (N*health feature weight value), the value of i in S131 is incremented by 1, and S131 is re-executed. The (N*i*health feature weight value) pieces of information from S132 are then retrieved and temporarily stored in the computer storage medium.

[0102] S140. Use the behavioral data tags in the user profile to filter information content that meets the second requirement from the information database to obtain the second information content.

[0103] In this embodiment, the second information content refers to the amount of information content related to the feature weight value, which is filtered based on the behavioral data tags in the user profile.

[0104] In one embodiment, please refer to Figure 4 The above-mentioned step S140 may include steps S141 to S145.

[0105] S141. Based on the behavioral data tags in the user profile, the information content corresponding to the tags is matched from the information database to obtain the second matching result. The number of the second matching results is N*i*feature weight value, where N is the number of information lists displayed by the user in a single session, and i is an integer greater than zero.

[0106] In this embodiment, the second matching result refers to the information content in the information database that is matched with the corresponding number of N*i*feature weight values ​​based on the behavioral data tags in the user profile.

[0107] S142. Filter out the information that the user has already read from the second matching result to obtain the second filtering result;

[0108] In this embodiment, the second filtering result refers to the information content remaining after filtering out the information that the user has already read from the second matching result.

[0109] S143. Determine whether the number of the second filtering results is less than the value set by the second requirement;

[0110] S144. If the number of the second filtering results is less than the value set by the second requirement, then increment i by one and execute step S141.

[0111] S145. If the number of the second filtering results is not less than the value set by the second requirement, the second filtering results are temporarily stored in the computer storage medium to obtain the second information content.

[0112] Specifically, based on the behavioral data tags in the user profile, (N*i*behavioral feature weight value) pieces of information content are matched from the information database by the tags, where N is the number of information lists displayed by the user at one time, i can be set to an integer greater than 0, and the behavioral feature weight value is the value set in S110.

[0113] The results retrieved in S142 are filtered to remove information that the user has already read. If the number of filtered information is less than (N * behavioral feature weight value), the value of i in S142 is incremented by 1, and then S142 is re-executed. The information in S143 is retrieved as (N * behavioral feature weight value) and temporarily stored in the computer storage medium.

[0114] S150. Use the basic attribute data tags in the user profile to filter information content that meets the third requirement from the information database to obtain the third information content.

[0115] In this embodiment, the third information content refers to the amount of information content related to the feature weight value, which is filtered based on the basic attribute data tags in the user profile.

[0116] In one embodiment, please refer to Figure 5 The above-mentioned step S150 may include steps S151 to S155.

[0117] S151. Based on the basic attribute data tags in the user profile, the information content corresponding to the tags is matched from the information database to obtain the third matching result. The number of the third matching results is N*i*basic attribute weight value, where N is the number of information lists displayed by the user at one time, and i is an integer greater than zero.

[0118] In this embodiment, the third matching result refers to the information content in the information database that is matched with the corresponding number of tags, which is N*i*the weight value of the basic attributes, based on the basic attribute data tags in the user profile.

[0119] S152. Filter out the information that the user has already read from the third matching result to obtain the third filtering result.

[0120] In this embodiment, the third filtering result refers to the remaining information content after filtering out the information that the user has already read from the third matching result.

[0121] S153. Determine whether the number of the third filtering results is less than the value set by the third requirement;

[0122] S154. If the number of the third filtering results is less than the value set by the third requirement, then increment i by one and execute S151.

[0123] S155. If the number of the third filtering results is not less than the value set by the third requirement, the third filtering results are temporarily stored in the computer storage medium to obtain the third information content.

[0124] Specifically, based on the basic attribute data tags in the user profile, (N*i*basic attribute weight value) pieces of information content are matched from the information database by tags, where N is the number of information lists displayed to the user at one time, i can be set to an integer greater than 0, and the basic attribute weight value is the value set in S11; the results retrieved in S151 are filtered to remove information that the user has already read. If the number of filtered information is less than (N*basic attribute weight value), the value of i in S151 is incremented by 1, and then S151 is re-executed; (N*basic attribute weight value) pieces of information are obtained in S152 and temporarily stored in the computer storage medium.

[0125] S160. Filter the information content that meets the fourth requirement based on the information release time to obtain the fourth information content.

[0126] In this embodiment, the fourth matching result refers to the information content that is filtered according to the information release time, with a corresponding quantity of N*i*the latest information weight value.

[0127] In one embodiment, please refer to Figure 6 The above-mentioned step S160 may include steps S161 to S165.

[0128] S161. Extract several newly released news items based on their release time to obtain extraction results. The number of extraction results is N*i*the weight value of the latest news, where N is the number of news items displayed on the user terminal at one time, and i is an integer greater than zero.

[0129] In this embodiment, the fourth matching result refers to retrieving the latest published information content with a quantity of N*i*the latest information weight value based on the information publication time.

[0130] S162. Filter out the information that the user has already read from the extracted results to obtain a fourth filtering result.

[0131] In this embodiment, the third filtering result refers to the remaining information content after filtering out the information that the user has already read from the third matching result.

[0132] S163. Determine whether the fourth filtering result is less than the value set by the fourth requirement;

[0133] S164. If the fourth filtering result is less than the value set by the fourth requirement, then increment i by one and execute S165.

[0134] S165. If the fourth filtering result is not less than the value set by the fourth requirement, the fourth filtering result information is temporarily stored in the computer storage medium to obtain the fourth information content.

[0135] Specifically, based on the information release time, extract the latest (N*i*latest information weight value) pieces of information, where N is the number of information lists displayed by the user at one time, i can be set to an integer greater than 0, and the latest information weight value is the value set in S11;

[0136] The results retrieved in S161 are filtered to remove information that the user has already read. If the number of filtered information is less than (N * the weight of the latest information), the value of i in S161 is incremented by 1, and then S161 is re-executed. The (N * the weight of the latest information) pieces of information in S162 are retrieved and temporarily stored in the computer storage medium.

[0137] S170. Merge the first information content, the second information content, the third information content, and the fourth information content to obtain the operation result;

[0138] In this embodiment, the operation result refers to the result formed by merging the first information content, the second information content, the third information content, and the fourth information content.

[0139] The merge operation is as follows:

[0140] The first pieces of information that can be recommended to users are page 1, page 2, page 3, page 4, and page 5;

[0141] The second pieces of information that can be recommended to users are page 1, page 6, page 7, page 8, and page 9;

[0142] Third-party information that can be recommended to users includes pages 3, 8, 10, 11, and 12.

[0143] The fourth information content that can be recommended to users includes page 1, page 12, page 13, page 14, and page 15;

[0144] After deduplicating and merging the above four pieces of information, we get page1, page2, page3, page4, page5, page6, page7, page8, page9, page10, page11, page12, page13, page14, and page15.

[0145] S180. Sort the operation results to obtain a sorting result;

[0146] In this embodiment, the sorting result refers to several pieces of information content that are randomly rearranged and then filtered out from the operation results.

[0147] Specifically, the operation results are randomly rearranged, and several rearranged information items are extracted to obtain the sorting result.

[0148] The information content list in S170 is randomly rearranged, and the top N information items in the list are displayed on the user's device.

[0149] S190. Send the sorting result to the terminal to display the information content that meets the requirements in the sorting result on the terminal.

[0150] The method in this embodiment increases the recommendation weight of user profile feature classification in a recommendation system that recommends information based on user profiles, thereby improving the recommendation hit rate; at the same time, it increases the recommendation weight of the latest information content, reducing the probability that the scope of recommended information will become increasingly narrow.

[0151] The aforementioned information content recommendation method improves the recommendation hit rate by setting the recommendation weight value of user profile feature classification, filtering information content related to the weight value, increasing the recommendation weight value of the latest information content, and filtering information content related to the recommendation weight value of the latest information content. This improves the hit rate of users' information content viewing needs, reduces the increasingly narrow information cocoon of recommended information, and improves user activity and retention rates.

[0152] Figure 7 This is a schematic block diagram of an information content recommendation device 300 provided in an embodiment of the present invention. Figure 7 As shown, corresponding to the above information content recommendation method, the present invention also provides an information content recommendation device 300. This information content recommendation device 300 includes a unit for executing the above information content recommendation method, and the device can be configured in a server. Specifically, please refer to... Figure 7 The information content recommendation device 300 includes a first setting unit 301, a second setting unit 302, a first filtering unit 303, a second filtering unit 304, a third filtering unit 305, a fourth filtering unit 306, a merging unit 307, a sorting unit 308, and a sending unit 309.

[0153] The first setting unit 301 is used to set the weight value of feature classification in the user profile in information recommendation, so as to obtain the feature weight value; the second setting unit 302 is used to set the weight value of the latest information; the first filtering unit 303 is used to filter information content that meets the first requirement from the information database using the most important feature tags in the user profile, so as to obtain the first information content; the second filtering unit 304 is used to filter information content that meets the second requirement from the information database using behavioral data tags in the user profile, so as to obtain the second information content; the third filtering unit 305 is used to use basic attribute data in the user profile The tag filters information content that meets the third requirement from the information database to obtain the third information content; the fourth filtering unit 306 is used to filter information content that meets the fourth requirement based on the information publication time to obtain the fourth information content; the merging unit 307 is used to perform a merging operation on the first information content, the second information content, the third information content, and the fourth information content to obtain the operation result; the sorting unit 308 is used to sort the operation result to obtain the sorting result; and the sending unit 309 is used to send the sorting result to the terminal to display the information content that meets the requirements in the sorting result on the terminal.

[0154] In one embodiment, such as Figure 8 As shown, the first filtering unit 303 includes a first matching subunit 3031, a first filtering subunit 3032, a first judgment subunit 3033, an addition subunit 3034, and a first temporary storage subunit 3035.

[0155] The first matching subunit 3031 is used to match the corresponding information content from the information database based on the feature tags in the user profile to obtain a first matching result, wherein the number of first matching results is N*i*feature weight value, where N is the number of information lists displayed by the user at one time, and i is an integer greater than zero; the first filtering subunit 3032 is used to filter out information that the user has already read from the first matching result to obtain a first filtering result; the first judgment subunit 3033 is used to judge whether the number of the first filtering results is less than the value set by the first requirement; the addition subunit 3034. If the number of the first filtering results is less than the value set by the first requirement, then i is incremented by one, and the first matching result is obtained by matching the corresponding information content from the information database based on the feature tags in the user profile. The number of the first matching results is N*i*feature weight value, where N is the number of information lists displayed by the user terminal at one time, and i is an integer greater than zero. The first temporary storage subunit 3035 is used to temporarily store the first filtering results in the computer storage medium if the number of the first filtering results is not less than the value set by the first requirement, so as to obtain the first information content.

[0156] In one embodiment, such asFigure 9 As shown, the second filtering unit 304 includes a second matching subunit 3041, a second filtering subunit 3042, a second judgment subunit 3043, a second addition subunit 3044, and a second temporary storage subunit 3045.

[0157] The second matching subunit 3041 is used to match the corresponding information content from the information database based on the behavioral data tags in the user profile to obtain a second matching result. The number of second matching results is N*i*feature weight value, where N is the number of information items displayed to the user at a time, and i is a positive integer. The second filtering subunit 3042 is used to filter out information that the user has already read from the second matching results to obtain a second filtering result. The second judgment subunit 3043 is used to determine whether the number of the second filtering results is less than the value set by the second requirement. The second adding subunit 304... 4. If the number of the second filtering results is less than the value set by the second requirement, then i is incremented by one, and the information content corresponding to the information is matched with the tags from the information database based on the behavioral data tags in the user profile to obtain the second matching result, wherein the number of the second matching results is N*i*feature weight value, N is the number of information lists displayed by the user terminal at one time, and i is an integer greater than zero; the second temporary storage subunit 3045 is used to temporarily store the second filtering results in the computer storage medium to obtain the second information content if the number of the second filtering results is not less than the value set by the second requirement.

[0158] In one embodiment, such as Figure 10 As shown, the third filtering unit 305 includes a third matching subunit 3051, a third filtering subunit 3052, a third judgment subunit 3053, a third addition subunit 3054, and a third temporary storage subunit 3055.

[0159] The third matching subunit 3051 is used to match the corresponding information content from the information database based on the basic attribute data tags in the user profile, so as to obtain the third matching result. The number of third matching results is N*i*basic attribute weight value, where N is the number of information lists displayed to the user at one time, and i is a positive integer. The third filtering subunit 3052 is used to filter out information that the user has already read from the third matching results, so as to obtain the third filtering result. The third judgment subunit 3053 is used to determine whether the number of the third filtering results is less than the value set by the third requirement. The third adding subunit 305... 4. If the number of the third filtering results is less than the value set by the third requirement, then i is incremented by one, and the information content corresponding to the information is matched with tags from the information database based on the basic attribute data tags in the user profile to obtain the third matching result, wherein the number of the third matching results is N*i*basic attribute weight value, N is the number of information lists displayed by the user terminal at one time, and i is an integer greater than zero; the third temporary storage subunit 3055 is used to temporarily store the third filtering results in the computer storage medium to obtain the third information content if the number of the third filtering results is not less than the value set by the third requirement.

[0160] In one embodiment, such as Figure 11 As shown, the fourth filtering unit 306 includes a fourth matching subunit 3061, a fourth filtering subunit 3062, a fourth judgment subunit 3063, a fourth addition subunit 3064, and a fourth temporary storage subunit 3065.

[0161] The fourth matching subunit 3061 is used to extract several newly published news items based on their publication time to obtain an extraction result, wherein the number of extraction results is N*i*the weight value of the latest news, where N is the number of news items displayed to the user at a time, and i is an integer greater than zero; the fourth filtering subunit 3062 is used to filter out news items that the user has already read from the extraction result to obtain a fourth filtering result; the fourth judgment subunit 3063 is used to determine whether the fourth filtering result is less than the value set by the fourth requirement; the fourth adding subunit 30... 64, used to increment i by one if the fourth filtering result is less than the value set by the fourth requirement, and to retrieve a number of the latest published information items based on the information release time to obtain the retrieval result, wherein the number of the retrieval results is N*i*the latest information weight value, N is the number of information lists displayed by the user terminal at one time, and i is an integer greater than zero; the fourth temporary storage subunit 3065, used to temporarily store the fourth filtering result information in the computer storage medium if the fourth filtering result is not less than the value set by the fourth requirement, to obtain the fourth information content.

[0162] In one embodiment, the sorting unit 308 is used to randomly rearrange the operation result and extract several rearranged information contents to obtain a sorting result.

[0163] It should be noted that those skilled in the art can clearly understand that the specific implementation process of the above-mentioned information content recommendation device 300 and each unit can be referred to the corresponding description in the foregoing method embodiments. For the sake of convenience and brevity, it will not be repeated here.

[0164] The aforementioned information content recommendation device 300 can be implemented as a computer program, which can, for example... Figure 12 It runs on the computer device shown.

[0165] Please see Figure 12 , Figure 12 This is a schematic block diagram of a computer device provided in an embodiment of this application. The computer device 500 can be a server, wherein the server can be a standalone server or a server cluster composed of multiple servers.

[0166] See Figure 12 The computer device 500 includes a processor 502, a memory, and a network interface 505 connected via a system bus 501. The memory may include a non-volatile storage medium 503 and internal memory 504.

[0167] The non-volatile storage medium 503 may store an operating system 5031 and a computer program 5032. The computer program 5032 includes program instructions that, when executed, cause the processor 502 to perform an information content recommendation method.

[0168] The processor 502 provides computing and control capabilities to support the operation of the entire computer device 500.

[0169] The internal memory 504 provides an environment for the execution of the computer program 5032 in the non-volatile storage medium 503. When the computer program 5032 is executed by the processor 502, the processor 502 can execute an information content recommendation method.

[0170] This network interface 505 is used for network communication with other devices. Those skilled in the art will understand that... Figure 12 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device 500 to which the present application is applied. The specific computer device 500 may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0171] The processor 502 is used to run a computer program 5032 stored in the memory to perform the following steps:

[0172] The weight values ​​of feature categories in the user profile are set to obtain feature weight values; the weight value of the latest information is set; information content that meets the first requirement is filtered from the information database using the most important feature tags in the user profile to obtain the first information content; information content that meets the second requirement is filtered from the information database using behavioral data tags in the user profile to obtain the second information content; information content that meets the third requirement is filtered from the information database using basic attribute data tags in the user profile to obtain the third information content; information content that meets the fourth requirement is filtered based on the information publication time to obtain the fourth information content; the first, second, third, and fourth information content are merged to obtain the operation result; the operation result is sorted to obtain the sorting result; the sorting result is sent to the terminal to display the information content that meets the requirements in the sorting result on the terminal.

[0173] In one embodiment, when the processor 502 implements the step of filtering information content that meets the first requirement from the information database using the most important feature tags in the user profile to obtain the first information content, the specific implementation steps are as follows:

[0174] Based on the feature tags in the user profile, the information content corresponding to the tags is matched from the information database to obtain a first matching result. The number of first matching results is N*i*feature weight value, where N is the number of information lists displayed to the user at a time, and i is a positive integer. Information already read by the user is filtered out from the first matching results to obtain a first filtered result. It is determined whether the number of the first filtered results is less than a value set by a first requirement. If the number of the first filtered results is less than the value set by the first requirement, i is incremented by one, and the process of matching the information content corresponding to the tags in the information database based on the feature tags in the user profile to obtain a first matching result is repeated. The number of first matching results is N*i*feature weight value, where N is the number of information lists displayed to the user at a time, and i is a positive integer. If the number of the first filtered results is not less than the value set by the first requirement, the first filtered results are temporarily stored in a computer storage medium to obtain the first information content.

[0175] In one embodiment, when the processor 502 implements the step of filtering information content that meets the second requirement from the information database using behavioral data tags in the user profile to obtain the second information content, the specific implementation steps are as follows:

[0176] Based on behavioral data tags in the user profile, the information content in the information database is matched using tags to obtain a second matching result. The number of second matching results is N*i*feature weight value, where N is the number of information lists displayed to the user at a time, and i is a positive integer. Information already read by the user is filtered out from the second matching results to obtain a second filtered result. It is determined whether the number of the second filtered results is less than a value set by a second requirement. If the number of the second filtered results is less than the value set by the second requirement, i is incremented by one, and the process of matching information content in the information database using tags based on behavioral data tags in the user profile to obtain a second matching result is repeated. The number of second matching results is N*i*feature weight value, where N is the number of information lists displayed to the user at a time, and i is a positive integer. If the number of the second filtered results is not less than the value set by the second requirement, the second filtered results are temporarily stored in a computer storage medium to obtain the second information content.

[0177] In one embodiment, when the processor 502 implements the step of filtering information content that meets the third requirement from the information database using basic attribute data tags in the user profile to obtain the third information content, the specific steps are as follows:

[0178] Based on the basic attribute data tags in the user profile, the information content corresponding to the tags is matched from the information database to obtain a third matching result. The number of third matching results is N*i*basic attribute weight value, where N is the number of information lists displayed to the user at a time, and i is a positive integer. Information already read by the user is filtered out from the third matching results to obtain a third filtered result. It is determined whether the number of third filtered results is less than a value set by the third requirement. If the number of third filtered results is less than the value set by the third requirement, i is incremented by one, and the process of matching the information content corresponding to the tags in the information database based on the basic attribute data tags in the user profile to obtain a third matching result is repeated. The number of third matching results is N*i*basic attribute weight value, where N is the number of information lists displayed to the user at a time, and i is a positive integer. If the number of third filtered results is not less than the value set by the third requirement, the third filtered results are temporarily stored in computer storage to obtain the third information content.

[0179] In one embodiment, when the processor 502 implements the step of filtering the information content according to the fourth requirement based on the information publication time to obtain the fourth information content, the following steps are specifically implemented:

[0180] The process involves retrieving several newly published news items based on their publication time to obtain a retrieval result. The number of retrieval results is defined as N*i*the weight value of the latest news, where N is the number of news items displayed to the user at a time, and i is a positive integer. News items already read by the user are filtered out from the retrieval results to obtain a fourth filtering result. It is then determined whether the fourth filtering result is less than a value set by the fourth requirement. If the fourth filtering result is less than the value set by the fourth requirement, i is incremented by one, and the process of retrieving several newly published news items based on their publication time is repeated to obtain a retrieval result. The number of retrieval results is defined as N*i*the weight value of the latest news, where N is the number of news items displayed to the user at a time, and i is a positive integer. If the fourth filtering result is not less than the value set by the fourth requirement, the fourth filtering result information is temporarily stored in computer storage to obtain the fourth news content.

[0181] In one embodiment, when the processor 502 implements the step of sorting the operation results to obtain a sorted result, it specifically implements the following steps:

[0182] The operation results are randomly rearranged, and several rearranged information entries are extracted to obtain the sorting result.

[0183] It should be understood that in the embodiments of this application, the processor 502 may be a central processing unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0184] It will be understood by those skilled in the art that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program includes program instructions and can be stored in a storage medium, which is a computer-readable storage medium. The program instructions are executed by at least one processor in the computer system to implement the process steps of the embodiments of the above methods.

[0185] Therefore, the present invention also provides a storage medium. This storage medium can be a computer-readable storage medium. The storage medium stores a computer program, wherein when executed by a processor, the computer program causes the processor to perform the following steps:

[0186] The weight values ​​of feature categories in the user profile are set to obtain feature weight values; the weight value of the latest information is set; information content that meets the first requirement is filtered from the information database using the most important feature tags in the user profile to obtain the first information content; information content that meets the second requirement is filtered from the information database using behavioral data tags in the user profile to obtain the second information content; information content that meets the third requirement is filtered from the information database using basic attribute data tags in the user profile to obtain the third information content; information content that meets the fourth requirement is filtered based on the information publication time to obtain the fourth information content; the first, second, third, and fourth information content are merged to obtain the operation result; the operation result is sorted to obtain the sorting result; the sorting result is sent to the terminal to display the information content that meets the requirements in the sorting result on the terminal.

[0187] In one embodiment, when the processor executes the computer program to implement the step of filtering information content that meets the first requirement from the information database using the most important feature tags in the user profile to obtain the first information content, the processor specifically implements the following steps:

[0188] Based on the feature tags in the user profile, the information content corresponding to the tags is matched from the information database to obtain a first matching result. The number of first matching results is N*i*feature weight value, where N is the number of information lists displayed to the user at a time, and i is a positive integer. Information already read by the user is filtered out from the first matching results to obtain a first filtered result. It is determined whether the number of the first filtered results is less than a value set by a first requirement. If the number of the first filtered results is less than the value set by the first requirement, i is incremented by one, and the process of matching the information content corresponding to the tags in the information database based on the feature tags in the user profile to obtain a first matching result is repeated. The number of first matching results is N*i*feature weight value, where N is the number of information lists displayed to the user at a time, and i is a positive integer. If the number of the first filtered results is not less than the value set by the first requirement, the first filtered results are temporarily stored in a computer storage medium to obtain the first information content.

[0189] In one embodiment, when the processor executes the computer program to implement the step of filtering information content that meets the second requirement from the information database using behavioral data tags in the user profile to obtain the second information content, the processor specifically implements the following steps:

[0190] Based on behavioral data tags in the user profile, the information content in the information database is matched using tags to obtain a second matching result. The number of second matching results is N*i*feature weight value, where N is the number of information lists displayed to the user at a time, and i is a positive integer. Information already read by the user is filtered out from the second matching results to obtain a second filtered result. It is determined whether the number of the second filtered results is less than a value set by a second requirement. If the number of the second filtered results is less than the value set by the second requirement, i is incremented by one, and the process of matching information content in the information database using tags based on behavioral data tags in the user profile to obtain a second matching result is repeated. The number of second matching results is N*i*feature weight value, where N is the number of information lists displayed to the user at a time, and i is a positive integer. If the number of the second filtered results is not less than the value set by the second requirement, the second filtered results are temporarily stored in a computer storage medium to obtain the second information content.

[0191] In one embodiment, when the processor executes the computer program to implement the step of filtering information content that meets the third requirement from the information database using basic attribute data tags in the user profile to obtain the third information content, the specific implementation is as follows:

[0192] Based on the basic attribute data tags in the user profile, the information content corresponding to the tags is matched from the information database to obtain a third matching result. The number of third matching results is N*i*basic attribute weight value, where N is the number of information lists displayed to the user at a time, and i is a positive integer. Information already read by the user is filtered out from the third matching results to obtain a third filtered result. It is determined whether the number of third filtered results is less than a value set by the third requirement. If the number of third filtered results is less than the value set by the third requirement, i is incremented by one, and the process of matching the information content corresponding to the tags in the information database based on the basic attribute data tags in the user profile to obtain a third matching result is repeated. The number of third matching results is N*i*basic attribute weight value, where N is the number of information lists displayed to the user at a time, and i is a positive integer. If the number of third filtered results is not less than the value set by the third requirement, the third filtered results are temporarily stored in computer storage to obtain the third information content.

[0193] In one embodiment, when the processor executes the computer program to implement the step of filtering information content according to the fourth requirement based on the information publication time to obtain the fourth information content, the processor specifically implements the following steps:

[0194] The process involves retrieving several newly published news items based on their publication time to obtain a retrieval result. The number of retrieval results is defined as N*i*the weight value of the latest news, where N is the number of news items displayed to the user at a time, and i is a positive integer. News items already read by the user are filtered out from the retrieval results to obtain a fourth filtering result. It is then determined whether the fourth filtering result is less than a value set by the fourth requirement. If the fourth filtering result is less than the value set by the fourth requirement, i is incremented by one, and the process of retrieving several newly published news items based on their publication time is repeated to obtain a retrieval result. The number of retrieval results is defined as N*i*the weight value of the latest news, where N is the number of news items displayed to the user at a time, and i is a positive integer. If the fourth filtering result is not less than the value set by the fourth requirement, the fourth filtering result information is temporarily stored in computer storage to obtain the fourth news content.

[0195] In one embodiment, when the processor executes the computer program to sort the operation results to obtain a sorted result, it specifically implements the following steps:

[0196] The operation results are randomly rearranged, and several rearranged information entries are extracted to obtain the sorting result.

[0197] The storage medium can be any computer-readable storage medium capable of storing program code, such as a USB flash drive, portable hard drive, read-only memory (ROM), magnetic disk, or optical disk.

[0198] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0199] In the several embodiments provided by this invention, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For example, the division of each unit is merely a logical functional division, and there may be other division methods in actual implementation. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed.

[0200] The steps in the method of this invention can be adjusted, merged, or reduced in order according to actual needs. The units in the device of this invention can be merged, divided, or reduced according to actual needs. Furthermore, the functional units in the various embodiments of this invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0201] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, a terminal, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention.

[0202] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and these modifications or substitutions should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. An information content recommendation method, characterized in that, include: Set the weight value of feature classification in user profile in information recommendation to obtain the feature weight value; Set the weight value for the latest information; The most important feature tags in the user profile are used to filter information content that meets the first requirement from the information database to obtain the first information content; By using behavioral data tags from user profiles, information content that meets the second requirement is filtered from the information database to obtain the second information content; By using the basic attribute data tags in the user profile, information content that meets the third requirement is filtered from the information database to obtain the third information content; The information content that meets the fourth requirement is filtered based on the information release time to obtain the fourth information content; The first, second, third, and fourth information contents are merged to obtain the operation result; The results of the operation are sorted to obtain a sorting result; The sorting results are sent to the terminal so that the information content that meets the requirements in the sorting results can be displayed on the terminal. The step of using the most important feature tags in the user profile to filter information content from the information database that meets the first requirement to obtain the first information content includes: Based on the feature tags in the user profile, the information content corresponding to the tags is matched from the information database to obtain the first matching result. The number of the first matching results is N*i*feature weight value, where N is the number of information lists displayed by the user in a single session, and i is an integer greater than zero. The first matching result is filtered to remove information that the user has already read, so as to obtain the first filtered result; Determine whether the number of the first filtering results is less than the value set by the first requirement; If the number of the first filtering results is less than the value set by the first requirement, then i is incremented by one, and the first matching result is obtained by matching the corresponding information content from the information database based on the feature tags in the user profile. The number of the first matching results is N*i*feature weight value, where N is the number of information lists displayed by the user terminal at one time, and i is an integer greater than zero. If the number of the first filtering results is not less than the value set by the first requirement, the first filtering results are temporarily stored in the computer storage medium to obtain the first information content. The step of using behavioral data tags from user profiles to filter information content that meets the second requirement from the information database to obtain the second information content includes: Based on the behavioral data tags in the user profile, the information content in the information database is matched with the tags to obtain the second matching result. The number of the second matching results is N*i*feature weight value, where N is the number of information lists displayed by the user in a single session, and i is an integer greater than zero. The second matching result is filtered to remove information that the user has already read, thus obtaining the second filtered result; Determine whether the number of the second filtering results is less than the value set by the second requirement; If the number of the second filtering results is less than the value set by the second requirement, then i is incremented by one, and the process of matching the corresponding information content from the information database based on the behavioral data tags in the user profile is executed to obtain the second matching result. The number of the second matching results is N*i*feature weight value, where N is the number of information lists displayed by the user terminal at one time, and i is an integer greater than zero. If the number of the second filtering results is not less than the value set by the second requirement, the second filtering results are temporarily stored in the computer storage medium to obtain the second information content.

2. The information content recommendation method according to claim 1, characterized in that, The step of using basic attribute data tags from user profiles to filter information content that meets the third requirement from the information database to obtain the third information content includes: Based on the basic attribute data tags in the user profile, the information content is matched with the tags in the information database to obtain the third matching result. The number of the third matching results is N*i*basic attribute weight value, where N is the number of information lists displayed by the user at one time, and i is an integer greater than zero. The third matching result is filtered to remove information that the user has already read, thus obtaining the third filtering result; Determine whether the number of the third filtering results is less than the value set by the third requirement; If the number of the third filtering results is less than the value set by the third requirement, then i is incremented by one, and the matching of the corresponding information content from the information database based on the basic attribute data tags in the user profile is performed to obtain the third matching result. The number of the third matching results is N*i*basic attribute weight value, where N is the number of information lists displayed by the user at one time, and i is an integer greater than zero. If the number of the third filtering results is not less than the value set by the third requirement, the third filtering results are temporarily stored in the computer storage medium to obtain the third information content.

3. The information content recommendation method according to claim 1, characterized in that, The process of filtering information content according to the fourth requirement based on the information release time to obtain the fourth information content includes: Based on the information release time, extract several of the latest published information items to obtain the extraction result. The number of extraction results is N*i*the weight value of the latest information, where N is the number of information items displayed on the user terminal at one time, and i is an integer greater than zero. The retrieved results are filtered to remove information that the user has already read, to obtain a fourth filtering result; Determine whether the fourth filtering result is less than the value set by the fourth requirement; If the fourth filtering result is less than the value set by the fourth requirement, then i is incremented by one, and the latest published information content is extracted according to the information release time to obtain the extraction result. The number of extraction results is N*i*the latest information weight value, where N is the number of information lists displayed by the user at one time, and i is an integer greater than zero. If the fourth filtering result is not less than the value set by the fourth requirement, the fourth filtering result information is temporarily stored in the computer storage medium to obtain the fourth information content.

4. The information content recommendation method according to claim 1, characterized in that, The process of sorting the operation results to obtain a sorting result includes: The operation results are randomly rearranged, and several rearranged information entries are extracted to obtain the sorting result.

5. An information content recommendation device, characterized in that, The device uses the information content recommendation method as described in any one of claims 1 to 4, including: The first setting unit is used to set the weight value of feature classification in information recommendation in user profile, so as to obtain the feature weight value; The second setting unit is used to set the weight value of the latest information. The first filtering unit is used to filter information content that meets the first requirement from the information database using the most important feature tags in the user profile, so as to obtain the first information content. The second filtering unit is used to filter information content that meets the second requirement from the information database using behavioral data tags in the user profile, so as to obtain the second information content. The third filtering unit is used to filter information content that meets the third requirement from the information database using the basic attribute data tags in the user profile, so as to obtain the third information content. The fourth filtering unit is used to filter the information content that meets the fourth requirement based on the information release time, so as to obtain the fourth information content; The merging unit is used to perform a merging operation on the first information content, the second information content, the third information content, and the fourth information content to obtain the operation result; A sorting unit is used to sort the operation results to obtain a sorted result; A sending unit is used to send the sorting result to a terminal so that the terminal can display the information content that meets the requirements in the sorting result. The first filtering unit includes: The first matching subunit is used to match the corresponding information content from the information database based on the feature tags in the user profile to obtain the first matching result. The number of the first matching results is N*i*feature weight value, where N is the number of information lists displayed by the user at one time, and i is an integer greater than zero. The first filtering subunit is used to filter out information that the user has already read from the first matching result to obtain the first filtering result; The first judgment subunit is used to determine whether the number of the first filtering results is less than the value set by the first requirement; An additional subunit is added, which is used to increment i by one if the number of the first filtering results is less than the value set by the first requirement, and to perform the matching of the corresponding information content from the information database based on the feature tags in the user profile to obtain the first matching result, wherein the number of the first matching results is N*i*feature weight value, N is the number of information lists displayed by the user terminal at one time, and i is an integer greater than zero. The first temporary storage subunit is used to temporarily store the first filtering results in a computer storage medium to obtain the first information content if the number of the first filtering results is not less than the value set by the first requirement.

6. A computer device, characterized in that, The computer device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method as described in any one of claims 1 to 4.

7. A storage medium, characterized in that, The storage medium stores a computer program that, when executed by a processor, implements the method as described in any one of claims 1 to 4.

Images