Information recommendation method and device, equipment and storage medium

Abstract

The invention provides an information recommendation method and device, equipment and a storage medium, and relates to the technical field of big data. In some embodiments of the invention, a target user type of which the user number of a set user level meets a set number condition is selected from candidate user types; the first user corresponding to the set user level in the target user type and the second user corresponding to the selected user type are used as target users, and the selected user type refers to the user type with the highest information recommendation receiving degree. The matching degree between the user and the recommendation information is improved; determining an individual browsing type preference of each target user and a group browsing type preference of a user type to which each target user belongs according to the historical browsing record of the target user; and information recommendation is performed according to the personal browsing type preference and the group browsing type preference corresponding to each target user, so that the information recommendation precision is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of big data technology, and in particular to an information recommendation method, device, equipment and storage medium. Background Art

[0002] With the rapid development of digital media and information technology, users' exposure to and consumption of media content are becoming increasingly diverse, and media playback formats are also gradually diversifying.

[0003] Short video platforms rely on traditional data statistics and user survey methods to obtain user preference information, and recommend short videos based on the analyzed user preference information, which to a certain extent meets the personalized needs of users.

[0004] Currently, the match between recommended information and users is low, and the accuracy of information recommendation is low. Summary of the invention

[0005] The present disclosure provides an information recommendation method, apparatus, device and storage medium to at least solve the problem that the existing recommended information has a low matching degree with users and the accuracy of information recommendation is low.

[0006] The technical solution of the present disclosure is as follows:

[0007] The present disclosure provides an information recommendation method, including:

[0008] Get the number of users of a set user level in each candidate user type;

[0009] Selecting a target user type from the candidate user types, the number of users of the set user level meeting a set number condition;

[0010] The first user corresponding to the set user level and the second user corresponding to the selected user type in the target user type are used as target users, wherein the selected user type refers to the user type with the highest degree of receiving information recommendation;

[0011] Determine, based on the target user's historical browsing records, the individual browsing type preference of each target user and the group browsing type preference of the user type to which each target user belongs;

[0012] Recommend target information to the target user according to the personal browsing type preference and the group browsing type preference.

[0013] Optionally, after recommending target information to the target user according to the individual browsing type preference and the group browsing type preference, the method further includes:

[0014] Collecting playback data and call data of the target user for the target information within a preset period;

[0015] Calculating a playback effect evaluation index within the preset period according to the playback data and call data;

[0016] When the playback effect evaluation index is less than a preset threshold, updating the historical browsing record of the target user;

[0017] Recommend information to the target user based on the target user's updated historical browsing record.

[0018] Optionally, the method further comprises:

[0019] When the playback effect evaluation index is greater than or equal to the preset threshold, it is determined that the playback effect of the target information is up to standard.

[0020] Optionally, the playback data includes: the number of playback cancellations and the actual duration of continuous playback; the call data includes: the number of outgoing calls, the response time of each outgoing call, and the number of interactions during each outgoing call; the calculation of the playback effect evaluation index within the preset period based on the playback data and call data includes:

[0021] Calculating a play cancellation rate according to the number of outgoing calls and the number of play cancellations within the preset period;

[0022] Calculate the average playback completion rate based on the response time of each outgoing call, the actual continuous playback time and the number of outgoing calls within the preset period;

[0023] Calculate the average playback interaction rate based on the number of interactions during each outgoing call and the number of outgoing calls within the preset period;

[0024] The playback effect evaluation index is calculated according to the playback cancellation rate, the average playback completion rate and the average playback interaction rate.

[0025] Optionally, determining the personal browsing type preference of each target user and the group browsing type preference of the user type to which each target user belongs according to the historical browsing records of the target user includes:

[0026] Classifying the historical browsing records to obtain browsing categories of the historical browsing records;

[0027] Calculate the video browsing completeness based on the video browsing time and total video time of the kth video in the jth feature word in the ith browsing category by the vth target user;

[0028] Calculate the video attention based on the video browsing completeness, video repeated playback times, video like times, video collection times, video comment times, and video forwarding times of the kth video in the jth feature word in the ith browsing category of the vth target user;

[0029] The copy reading completeness is calculated based on the number of words read by the vth target user in the jth feature word in the ith browsing category and the total number of words in the copy;

[0030] The copy attention is calculated based on the copy reading completeness, copy repeated reading times, copy like times, copy collection times, copy comment times, and copy forwarding times of the kth copy in the jth feature word in the ith browsing category by the vth target user;

[0031] Calculate the personal browsing type preference of the vth target user in the i-th browsing category according to the video attention, the text attention, the number of videos and texts in the j-th feature word of the vth target user in the i-th browsing category, and the number of feature words of the vth target user in the i-th browsing category;

[0032] The group browsing type preference is calculated according to the number of users of the user type to which the j-th target user belongs and the individual browsing type preference.

[0033] Optionally, the recommending target information to the target user according to the individual browsing type preference and the group browsing type preference includes:

[0034] Calculate the browsing type recommendation coefficient of the vth target user in the i-th browsing category based on the personal browsing type preference of the vth target user in the i-th browsing category, the group browsing type preference of the i-th browsing category of the corresponding group of the vth target user, the group browsing type preference weight coefficient and the personal browsing type preference weight coefficient;

[0035] Arrange the browsing categories in descending order according to the browsing type recommendation coefficients to obtain an arrangement order of the browsing categories;

[0036] The browsing type recommendation coefficients of each browsing category are reduced in ratio according to the arrangement order to obtain the simplest order integer ratio relationship between the browsing types, wherein the integer corresponding to each browsing type is the recommendation quantity, and the arrangement order of the browsing categories is the recommendation order;

[0037] According to the recommended quantity of the browsing categories and the arrangement order of the browsing categories, target information is recommended to the target user.

[0038] The present disclosure also provides an information recommendation device, including:

[0039] An acquisition module, used to acquire the number of users of a set user level in each candidate user type;

[0040] A selection module, configured to select a target user type from among the candidate user types, the number of users of the set user level meeting a set number condition;

[0041] A selection module, used to select the first user corresponding to the set user level and the second user corresponding to the selected user type in the target user type as the target user, wherein the selected user type refers to the user type with the highest degree of receiving information recommendation;

[0042] A determination module, used to determine the individual browsing type preference of each target user and the group browsing type preference of the user type to which each target user belongs according to the historical browsing records of the target user;

[0043] A recommendation module is used to recommend target information to the target user according to the individual browsing type preference and the group browsing type preference.

[0044] The present disclosure also provides an electronic device, including:

[0045] processor;

[0046] a memory for storing instructions executable by the processor;

[0047] The processor is configured to execute the instructions to implement each step in the above method.

[0048] The embodiment of the present disclosure further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, each step in the above method is implemented.

[0049] The embodiment of the present disclosure further provides a computer program product, including a computer program / instruction, which implements each step of the above method when executed by a processor.

[0050] The technical solution provided by the embodiments of the present disclosure brings at least the following beneficial effects:

[0051] In some embodiments of the present disclosure, the number of users of a set user level in each candidate user type is obtained; a target user type whose number of users of the set user level meets the set number condition is selected from the candidate user types; a first user corresponding to the set user level in the target user type and a second user corresponding to the selected user type are used as target users, wherein the selected user type refers to the user type with the highest degree of reception of information recommendation, and the present disclosure selects users of the target user type and the selected user type for information recommendation to improve the matching degree between the user and the recommended information; based on the historical browsing records of the target users, the personal browsing type preference of each target user and the group browsing type preference of the user type to which each target user belongs are determined; based on the personal browsing type preference and the group browsing type preference, the target information is recommended to the target user; information is recommended based on the personal browsing type preference and the group browsing type preference corresponding to each target user to improve the accuracy of information recommendation.

[0052] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] The drawings herein are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the description are used to explain the principles of the present disclosure, and do not constitute improper limitations on the present disclosure.

[0054] Figure 1 A flowchart of an information recommendation method provided for an exemplary embodiment of the present disclosure;

[0055] Figure 2 A schematic diagram of the structure of an information recommendation device provided by an exemplary embodiment of the present disclosure;

[0056] Figure 3 A schematic structural diagram of an electronic device provided by an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0057] In order to enable ordinary persons in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings.

[0058] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure.

[0059] It should be noted that the user information involved in this disclosure includes but is not limited to: user device information and user personal information; the collection, storage, use, processing, transmission, provision and disclosure of user information in this disclosure comply with the relevant laws and regulations and do not violate public order and good morals.

[0060] In response to the above technical problems, in some embodiments of the present disclosure, the number of users of a set user level in each candidate user type is obtained; a target user type whose number of users of the set user level meets the set number condition is selected from the candidate user types; a first user corresponding to the set user level in the target user type and a second user corresponding to the selected user type are used as target users, wherein the selected user type refers to the user type with the highest degree of reception of information recommendation, and the present disclosure selects users of the target user type and the selected user type for information recommendation, thereby improving the matching degree between the user and the recommended information; based on the historical browsing records of the target users, the personal browsing type preferences of each target user and the group browsing type preferences of the user type to which each target user belongs are determined; based on the personal browsing type preferences and the group browsing type preferences, target information is recommended to the target user; information is recommended based on the personal browsing type preferences and the group browsing type preferences corresponding to each target user, thereby improving the accuracy of information recommendation.

[0061] The technical solutions provided by various embodiments of the present disclosure are described in detail below in conjunction with the accompanying drawings.

[0062] Figure 1 The following is a flow chart of an information recommendation method provided by an exemplary embodiment of the present disclosure. Figure 1 As shown, the method includes:

[0063] S101: Obtain the number of users with a set user level in each candidate user type;

[0064] S102: Selecting a target user type from candidate user types, the number of users of a set user level meeting a set number condition;

[0065] S103: taking a first user corresponding to a set user level and a second user corresponding to a selected user type in the target user type as target users, wherein the selected user type refers to a user type with the highest degree of receiving information recommendation;

[0066] S104: determining the individual browsing type preference of each target user and the group browsing type preference of the user type to which each target user belongs according to the historical browsing records of the target user;

[0067] S105: Recommend target information to target users based on the individual browsing type preference and the group browsing type preference.

[0068] In this embodiment, the execution subject of the above method may be a terminal device or a server.

[0069] Among them, the terminal device includes but is not limited to a mobile station (MS), a mobile terminal, a mobile phone, a handset and a portable equipment, etc. The terminal device can communicate with one or more core networks via a radio access network (RAN). For example, the terminal device can be a mobile phone (or a "cellular" phone), a computer with a wireless communication function, etc. The terminal device can also be a computer with a wireless transceiver function, a virtual reality (VR) terminal device, an AR terminal device, a wireless terminal in industrial control, a wireless terminal in self driving, a wireless terminal in remote medical, a wireless terminal in a smart grid, a wireless terminal in transportation safety, a wireless terminal in a smart city, a wireless terminal in a smart home, etc., and the operating system installed on the terminal device includes but is not limited to: IOS, Android, windows, linux, Mac OS and other operating systems. In different networks, the terminal may be called different names, such as user equipment, mobile station, subscriber unit, station, cellular phone, personal digital assistant, wireless modem, wireless communication device, handheld device, laptop computer, cordless phone, wireless local loop station, television, etc. For the convenience of description, it is referred to as terminal equipment in this embodiment.

[0070] In this embodiment, the implementation form of the server is not limited. For example, the server can be a conventional server, a cloud server, a cloud host, a virtual center, or other server devices. The server mainly includes a processor, a hard disk, a memory, a system bus, etc., and a general computer architecture type.

[0071] In this embodiment, the number of users of a set user level in each candidate user type is obtained; a target user type whose number of users of the set user level meets the set number condition is selected from the candidate user types; a first user corresponding to the set user level in the target user type and a second user corresponding to the selected user type are used as target users, wherein the selected user type refers to a user type with the highest degree of reception of information recommendation, and the present disclosure selects users of the target user type and the selected user type for information recommendation, thereby improving the matching degree between the user and the recommended information; based on the historical browsing records of the target users, the personal browsing type preference of each target user and the group browsing type preference of the user type to which each target user belongs are determined; based on the personal browsing type preference and the group browsing type preference, target information is recommended to the target user; information is recommended based on the personal browsing type preference and the group browsing type preference corresponding to each target user, thereby improving the accuracy of information recommendation.

[0072] The present disclosure classifies users, extracts distribution data of users of set user levels in different user types, locates target users based on a first user corresponding to the set user level and a second user corresponding to the selected user type, and can achieve accurate product delivery, reduce product promotion cycles, and improve product popularization efficiency. The present disclosure can dynamically adjust media content recommendation strategies based on analysis results to enhance user experience, evaluate whether playback effects within a preset fixed period meet standards, update target users' historical browsing data when playback effects do not meet standards, and update personalized push plans based on this, thereby improving personalized service levels.

[0073] In some embodiments of the present disclosure, the users of the platform are classified, the number of users with set user levels among users of different user types is extracted, and the target users are located based on the number of users with set user levels and the selected user type. It should be noted that user types include, but are not limited to: campus, social youth, community elders, community backbone families, rural left-behind families, civil servants rural migrant workers, doctors, teachers, white-collar workers and riders, among which campus includes colleges, universities, primary and secondary schools. Setting user levels means that the platform divides the users of the platform into different levels from high to low according to its own level classification rules. For example, platinum members, gold members, silver members and bronze members, etc. Different platforms have different user level classification rules, which are not limited in the present disclosure.

[0074] In some embodiments of the present disclosure, a target user type whose number of users of a set user level meets a set number condition is selected from the candidate user types. Optionally, a target user type whose number of users of the set user level ranks in the first set number of digits is selected from the candidate user types.

[0075] In the disclosed embodiment, the selected user type refers to the user type with the highest degree of information recommendation reception. For example, colleges and universities are the most popular user type, that is, the user type with the highest degree of information recommendation reception, and colleges and universities are selected as the user type.

[0076] For example, count the number of platinum members in different candidate user types; sort the number of platinum members in different candidate user types from high to low, and keep the top three candidate user types. When counting the distribution of platinum members, the proportion of platinum members corresponding to the youth customer group, the elderly customer group, and the rural left-behind families is prominent. When promoting the product in cities, the platinum members corresponding to the youth customer group, the elderly customer group, and the rural left-behind families will be used as the first users of the product. The university customer group, as the most popular user group, will be the second user of the selected user type.

[0077] In some embodiments of the present disclosure, the personal browsing type preference of each target user and the group browsing type preference of the user type to which each target user belongs are determined based on the historical browsing records of the target users. One achievable method is to classify the historical browsing records to obtain the browsing categories of the historical browsing records; calculate the video browsing completeness based on the video browsing time and total video time of the kth video in the jth feature word in the ith browsing category of the vth target user; calculate the video attention based on the video browsing completeness, video repeat playback times, video like times, video collection times, video comment times, and video forwarding times of the kth video in the jth feature word in the ith browsing category of the vth target user; calculate the copy reading completeness based on the number of words read and the total number of words in the copy of the kth copy in the jth feature word in the ith browsing category of the vth target user. The degree of attention of the copy is calculated according to the completeness of the copy reading, the number of repeated readings, the number of likes, the number of collections, the number of comments and the number of forwarding of the copy of the kth copy in the jth feature word of the vth target user in the i-th browsing category; the personal browsing type preference of the vth target user in the i-th browsing category is calculated according to the video attention, the copy attention, the number of videos and the number of copies in the jth feature word of the vth target user in the i-th browsing category, and the number of feature words of the vth target user in the i-th browsing category; the group browsing type preference is calculated according to the number of users of the user type to which the jth target user belongs and the personal browsing type preference. It should be noted that the historical browsing records include: video browsing records and text browsing records.

[0078] Optionally, the video browsing records and text browsing records of the target users in different software within a preset historical period are periodically retrieved, and the retrieved information is classified and counted. The video browsing records and text browsing records of target users of different user types in different software within a preset historical period are periodically retrieved to classify the retrieved historical browsing records, and at the same time, the feature word range of the subordinate level of the category is set; feature words are extracted from the retrieved historical browsing records and the historical browsing records are matched with the corresponding categories with reference to the feature word range of the subordinate level of different categories; and the historical video browsing data and historical text browsing data of each target user for each browsing category are counted. The present invention periodically retrieves the video browsing records and text browsing records of the target users in different software within a preset historical period, and classifies and counts the retrieved information, which increases the scope of data collection, ensures the real-time nature of the target user-related data, and is conducive to improving the accuracy of preference analysis.

[0079] Among them, historical video browsing data includes but is not limited to: video browsing time, total video time, number of video repeated playback times, number of video likes, number of video collections, number of video comments and number of video forwarding times; historical text browsing data includes but is not limited to: number of words read in the copy, total number of words in the copy, number of times the copy is repeatedly read, number of text likes, number of text collections, number of text comments and number of text forwarding times.

[0080] In some embodiments of the present disclosure, the personal browsing type preference of each target user and the group browsing type preference of the user type to which each target user belongs are determined based on the historical video browsing data and historical text browsing data of each target user for each browsing category.

[0081] Optionally, based on the video browsing time T of the kth video in the jth feature word of the vth target user in the i-th browsing category, Aavijk and the total video duration T Azvijk , calculate the corresponding video browsing completeness α Aavijk , the calculation formula is:

[0082]

[0083] The video browsing completeness α based on the kth video in the jth feature word of the vth target user in the i-th browsing category Aavijk 、Number of video replays Acbvijk 、Number of video likes Adzvijk 、Number of video collections Ascvijk 、Number of video comments Aplvijk , and the number of times the video is forwarded n Azfvijk , calculate the video attention α Agvijk , the calculation formula is:

[0084]

[0085] Based on the number of words M read by the kth copy in the jth feature word of the vth target user in the ith browsing category Wavijk Total word count of the copy M Wzvijk , calculate the copy reading completeness α Wavijk , the calculation formula is:

[0086]

[0087] The copy reading completeness α of the kth copy in the jth feature word of the vth target user in the i-th browsing category Wavijk 、Number of times the copy is read repeatedly Wcyvijk 、Number of likes for the copywriting Wdzvijk 、Number of times the copy was collected Wscvijk 、Number of copywriting comments n Wplvijk , and the number of times the copy was forwarded n Wzfvijk , calculate the copywriting attention α Wgvijk , the calculation formula is:

[0088]

[0089] Based on the video attention α of the kth video in the jth feature word of the vth target user in the i-th browsing category Agvijk , the copywriting attention of the kth copywriting in the jth feature word of the vth target user in the i-th browsing category α Wgvijk , the number of videos n in the jth feature word of the vth target user in the i-th browsing category svij 、Number of copywriting bvij , and the number of characteristic words n of the vth target user in the i-th browsing category cvi , calculate the personal browsing type preference P of the vth target user in the i-th browsing category Lvi , the calculation formula is:

[0090]

[0091] The number of users n based on the user type to which the j-th target user belongs qj and personal browsing type preference P Lvi , calculate the group browsing type preference, the calculation formula is:

[0092]

[0093] The group browsing type preferences of the j-th target user group are ranked from high to low according to the numerical values, and the individual browsing type preferences of the v-th target user are also ranked from high to low according to the numerical values.

[0094] In some embodiments of the present disclosure, target information is recommended to target users based on personal browsing type preferences and group browsing type preferences. One achievable method is to calculate the browsing type recommendation coefficient of the vth target user in the i-th browsing category based on the personal browsing type preference of the vth target user in the i-th browsing category, the group browsing type preference of the i-th browsing category of the group corresponding to the vth target user, the group browsing type preference weight coefficient and the personal browsing type preference weight coefficient; arrange the browsing categories in order from high to low according to the browsing type recommendation coefficients to obtain the browsing category arrangement order; reduce the ratio of the browsing type recommendation coefficients of each browsing category according to the arrangement order to obtain the simplest order integer ratio relationship between the browsing types, wherein the integer corresponding to each browsing type is the recommendation quantity, and the browsing category arrangement order is the recommendation order; recommend the target information to the target user based on the recommended quantity of the browsing categories and the browsing category arrangement order.

[0095] Optionally, receiving the target user group browsing type preference ranking information and each target user's individual browsing type preference ranking information; setting the group browsing type preference weight coefficient q a and the personal browsing type preference weight coefficient q b ;

[0096] Based on the personal browsing type preference P of the vth target user in the i-th browsing category Lvi , the group browsing type preference P of the i-th browsing category of the v-th target user teji , Group browsing type preference weight coefficient q a and the personal browsing type preference weight coefficient, calculate the browsing type recommendation coefficient Q of the vth target user in the i-th browsing category tvi , the calculation formula is:

[0097]

[0098] The browsing categories are arranged in descending order according to the browsing type recommendation coefficient to obtain the browsing category arrangement order; the browsing type recommendation coefficient of each browsing category is reduced by ratio according to the arrangement order to obtain the simplest sequential integer proportional relationship between the browsing types, wherein the integer corresponding to each browsing type is the recommendation quantity, and the browsing category arrangement order is the recommendation order; when the recommendation quantity of a browsing category reaches a preset recommendation quantity threshold, the recommendation of the next browsing category is entered, and personalized recommendations are performed according to the recommendation order and the recommendation quantity; after a recommendation cycle ends, the browsing categories are restarted according to the recommendation rules.

[0099] It should be noted that the group browsing type preference P of the i-th browsing category of the v-th target user is tejiWhere j is a known value. There is a many-to-one data relationship between the target user and its group. When the target user is determined, the corresponding target user group can be known. In actual calculation, the number of the target user's corresponding group can be entered. However, there are numerical differences between different target users, and the group browsing type preference P appears in actual calculation. teji The values ​​are the same, personal browsing type preference P Lvi The difference in values ​​is reasonable.

[0100] It should be noted that in order to facilitate the understanding of the above recommended rules, the following data is used for explanation:

[0101] Assume that there are 6 browsing types. After the ranking from high to low, the corresponding browsing type recommendation coefficients of the target users are Qt1 = 2.98, Qt2 = 2.46, Qt3 = 2.24, Qt4 = 1.92, Qt5 = 1.62, Qt6 = 1.18. The ratios according to the order of arrangement are 2.98: 2.46: 2.24: 1.92: 1.62: 1.18. After reduction, the simplest order integer ratio relationship between different browsing types is 149: 123:112:96:81:59, the total number of recommendations is 620. When the number of outgoing calls of the target user is less than or equal to 620, each browsing type is recommended in turn according to the recommendation order and the number of recommendations. When the number of outgoing calls of the target user is less than or equal to 149, only the first-ranked browsing category is recommended. When the number of outgoing calls of the target user is greater than 149 and less than or equal to 149+123, only the second-ranked browsing category is recommended. When the number of outgoing calls of the target user is greater than 149 and less than or equal to 149+123, only the second-ranked browsing category is recommended. When the number of outgoing calls of the target user is greater than 149+123 and less than or equal to 149+123+112, only the third-ranked browsing category is recommended; when the number of outgoing calls of the target user is greater than 149+123+112 and less than or equal to 149+123+112+96, only the fourth-ranked browsing category is recommended; when the number of outgoing calls of the target user is greater than 149+123+112+96 and less than or equal to 149+123+112+96+81, only Recommendations are made for the fifth-ranked browsing category. When the target user's outgoing phone calls are greater than 149+123+112+96+81 and less than or equal to 149+123+112+96+81+59, only recommendations are made for the sixth-ranked browsing category. When the target user's outgoing phone calls are greater than 620, a recommendation cycle ends, and the second recommendation cycle begins from the 621th outgoing phone call. The recommendation order and number of recommendations in the second recommendation cycle are the same as those in the first recommendation cycle.

[0102] In some embodiments of the present disclosure, the playback data and call data of the target user for the target information within a preset period are collected; the playback effect evaluation index within the preset period is calculated based on the playback data and call data; when the playback effect evaluation index is less than a preset threshold, the historical browsing record of the target user is updated; and information is recommended to the target user based on the updated historical browsing record of the target user.

[0103] It should be noted that the playback data includes: the number of playback cancellations and the actual duration of continuous playback; the call data includes: the number of outgoing calls, the response time for each outgoing call, and the number of interactions during each outgoing call;

[0104] Optionally, the number of playback cancellations, actual continuous playback duration, and playback interaction times are collected regularly, and interactive behaviors include but are not limited to likes, comments, and favorites; the number of outgoing phone calls of the target user and the response time of each outgoing call are retrieved regularly. The playback data of the target user for the personalized recommendation plan and the call data of the target user collected regularly are processed to calculate the playback effect evaluation index within the preset period and compare it with the preset value to determine whether the playback effect meets the standard, and different operations are performed based on the determination result.

[0105] Optionally, the collected playback data and call data of the target user for the personalized recommendation scheme are received. Based on the number of outgoing calls m of the target user within a preset period hc and the number of playback cancellations m bq , calculate the play cancellation rate β bq , the calculation formula is:

[0106]

[0107] Based on the response time t of the i-th outgoing call within the preset period hci , actual continuous playback time t sci And the number of outgoing calls m hc , calculate the average playback completion rate β be , the calculation formula is:

[0108]

[0109] Based on the number of interactions m during the i-th outgoing call within the preset period hdi and the number of outgoing calls m hc Calculate the average playback interaction rate β he , the calculation formula is:

[0110]

[0111] Based on the play cancellation rate β within a preset period bq , average playback completion rate β beand the average play interaction rate β he , calculate the playback effect evaluation index X bg , the calculation formula is:

[0112]

[0113] If the playback effect evaluation index is greater than or equal to the preset threshold, it is determined that the playback effect of the target information is up to standard. If the playback effect evaluation index is less than the preset threshold, it is determined that the playback effect of the target information is not up to standard, and the historical browsing record of the target user is updated, and information is recommended to the target user according to the updated historical browsing record of the target user.

[0114] Figure 2 FIG. 2 is a schematic diagram of the structure of an information recommendation device 20 provided by an exemplary embodiment of the present disclosure. Figure 2 As shown, the information recommendation device 20 includes: an acquisition module 21, a selection module 22, a selection module 23, a determination module 24 and a recommendation module 25.

[0115] The acquisition module 21 is used to acquire the number of users with set user levels in each candidate user type;

[0116] A selection module 22, configured to select a target user type from among the candidate user types, the number of users of a set user level meeting a set number condition;

[0117] A selection module 23, configured to select a first user corresponding to a set user level and a second user corresponding to a selected user type in the target user type as a target user, wherein the selected user type refers to a user type with the highest degree of receiving information recommendation;

[0118] A determination module 24, configured to determine the individual browsing type preference of each target user and the group browsing type preference of the user type to which each target user belongs based on the historical browsing records of the target user;

[0119] The recommendation module 25 is used to recommend target information to target users according to individual browsing type preferences and group browsing type preferences.

[0120] Optionally, after recommending target information to target users according to individual browsing type preferences and group browsing type preferences, the recommendation module 25 may also be used to:

[0121] Collect the target user's playback data and call data for the target information within a preset period;

[0122] Calculate the playback effect evaluation index within a preset period based on the playback data and call data;

[0123] When the playback effect evaluation index is less than a preset threshold, the historical browsing record of the target user is updated;

[0124] Recommend information to target users based on their updated historical browsing records.

[0125] Optionally, the recommendation module 25 may also be used to:

[0126] When the playback effect evaluation index is greater than or equal to a preset threshold, it is determined that the playback effect of the target information is up to standard.

[0127] Optionally, the play data includes: the number of play cancellations and the actual continuous play duration, and the call data includes: the number of outgoing calls, the response time of each outgoing call, and the number of interactions during each outgoing call; when the recommendation module 25 calculates the play effect evaluation index within a preset period based on the play data and the call data, it is used to:

[0128] Calculate the play cancellation rate based on the number of outgoing calls and the number of play cancellations within a preset period;

[0129] Calculate the average playback completion rate based on the response time of each outgoing call, the actual continuous playback time and the number of outgoing calls within the preset period;

[0130] Calculate the average playback interaction rate based on the number of interactions during each outgoing call and the number of outgoing calls within a preset period;

[0131] The playback effect evaluation index is calculated based on the playback cancellation rate, average playback completion rate and average playback interaction rate.

[0132] Optionally, when determining the individual browsing type preference of each target user and the group browsing type preference of the user type to which each target user belongs based on the historical browsing records of the target user, the determination module 24 is configured to:

[0133] Classify the historical browsing records to obtain browsing categories of the historical browsing records;

[0134] Calculate the video browsing completeness based on the video browsing time and total video time of the kth video in the jth feature word in the ith browsing category by the vth target user;

[0135] Calculate the video attention based on the video browsing completeness, video repeated playback times, video like times, video collection times, video comment times, and video forwarding times of the kth video in the jth feature word in the ith browsing category of the vth target user;

[0136] The copy reading completeness is calculated based on the number of words read by the vth target user in the jth feature word in the ith browsing category and the total number of words in the copy;

[0137] The copy attention is calculated based on the copy reading completeness, copy repeated reading times, copy like times, copy collection times, copy comment times, and copy forwarding times of the kth copy in the jth feature word in the ith browsing category by the vth target user;

[0138] Calculate the personal browsing type preference of the vth target user in the i-th browsing category based on the video attention, text attention, the number of videos and texts in the j-th feature word of the vth target user in the i-th browsing category, and the number of feature words of the vth target user in the i-th browsing category;

[0139] According to the number of users of the user type to which the j-th target user belongs and the individual browsing type preference, the group browsing type preference is calculated.

[0140] Optionally, when recommending target information to a target user according to the individual browsing type preference and the group browsing type preference, the recommendation module 25 is used to:

[0141] Calculate the browsing type recommendation coefficient of the vth target user in the i-th browsing category based on the personal browsing type preference of the vth target user in the i-th browsing category, the group browsing type preference of the i-th browsing category of the corresponding group of the vth target user, the group browsing type preference weight coefficient and the personal browsing type preference weight coefficient;

[0142] Arrange the browsing categories in descending order according to the browsing type recommendation coefficients to obtain the browsing category arrangement order;

[0143] The recommended coefficients of each browsing category are divided by ratio according to the order of arrangement to obtain the simplest integer ratio relationship between the browsing types, where the integer corresponding to each browsing type is the recommended quantity, and the order of arrangement of the browsing categories is the recommendation order;

[0144] Recommend target information to target users based on the number of recommendations in the browsing categories and the order in which the browsing categories are arranged.

[0145] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0146] Figure 3 FIG. 1 is a schematic diagram of a structure of an electronic device provided by an exemplary embodiment of the present disclosure. Figure 3 As shown, the electronic device includes: a memory 31 and a processor 32. In addition, the electronic device also includes a power supply component 33 and a communication component 34.

[0147] The memory 31 is used to store computer programs and can be configured to store various other data to support operations on the electronic device. Examples of such data include instructions for any application program or method operating on the electronic device.

[0148] The memory 31 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0149] The communication component 34 is used for data transmission with other devices.

[0150] The processor 32 can execute computer instructions stored in the memory 31 to: obtain the number of users of the set user level in each candidate user type; select a target user type whose number of users of the set user level meets the set number condition from the candidate user types; use a first user corresponding to the set user level in the target user type and a second user corresponding to the selected user type as target users, wherein the selected user type refers to a user type with the highest degree of reception of information recommendation; determine the personal browsing type preference of each target user and the group browsing type preference of the user type to which each target user belongs based on the historical browsing records of the target users; and recommend target information to the target users based on the personal browsing type preference and the group browsing type preference.

[0151] Accordingly, the present disclosure also provides a computer-readable storage medium storing a computer program. When the computer-readable storage medium stores the computer program and the computer program is executed by one or more processors, the one or more processors execute Figure 1 Each step in the method embodiment.

[0152] Accordingly, the present disclosure also provides a computer program product, the computer program product includes a computer program / instruction, the computer program / instruction is executed by a processor Figure 1 Each step in the method embodiment.

[0153] Above Figure 3The communication component in is configured to facilitate wired or wireless communication between the device where the communication component is located and other devices. The device where the communication component is located can access a wireless network based on a communication standard, such as WiFi, 2G, 3G, 4G / LTE, 5G and other mobile communication networks, or a combination thereof. In an exemplary embodiment, the communication component receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0154] Above Figure 3 The power supply component in the device provides power to various components of the device where the power supply component is located. The power supply component may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the device where the power supply component is located.

[0155] The electronic device also includes a display screen and an audio component.

[0156] The display screen includes a screen, and the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation.

[0157] The audio component may be configured to output and / or input audio signals. For example, the audio component includes a microphone (MIC), and when the device where the audio component is located is in an operating mode, such as a call mode, a recording mode, and a speech recognition mode, the microphone is configured to receive an external audio signal. The received audio signal may be further stored in a memory or sent via a communication component. In some embodiments, the audio component also includes a speaker for outputting an audio signal.

[0158] In the above-mentioned apparatus, device, storage medium and computer program product embodiments of the present disclosure, the number of users of set user levels in each candidate user type is obtained; a target user type whose number of users of set user levels meets the set number condition is selected from the candidate user types; a first user corresponding to the set user level in the target user type and a second user corresponding to the selected user type are used as target users, wherein the selected user type refers to the user type with the highest degree of reception of information recommendation, and the present disclosure selects users of the target user type and the selected user type for information recommendation to improve the matching degree between the user and the recommended information; based on the historical browsing records of the target users, the personal browsing type preference of each target user and the group browsing type preference of the user type to which each target user belongs are determined; based on the personal browsing type preference and the group browsing type preference, the target information is recommended to the target user; information is recommended based on the personal browsing type preference and the group browsing type preference corresponding to each target user to improve the accuracy of information recommendation.

[0159] Those skilled in the art will appreciate that the embodiments of the present disclosure may be provided as methods, systems, or computer program products. Therefore, the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present disclosure may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0160] The present disclosure is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present disclosure. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0161] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0162] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0163] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0164] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0165] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0166] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0167] The above are only specific embodiments of the present disclosure, so that those skilled in the art can understand or implement the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to these embodiments herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An information recommendation method, characterized in that: include: Get the number of users of a set user level in each candidate user type; Selecting a target user type from the candidate user types, the number of users of the set user level meeting a set number condition; The first user corresponding to the set user level and the second user corresponding to the selected user type in the target user type are used as target users, wherein the selected user type refers to the user type with the highest degree of receiving information recommendation; Determine, based on the target user's historical browsing records, the individual browsing type preference of each target user and the group browsing type preference of the user type to which each target user belongs; Recommend target information to the target user according to the personal browsing type preference and the group browsing type preference.

2. The method according to claim 1, characterized in that After recommending target information to the target user according to the individual browsing type preference and the group browsing type preference, the method further includes: Collecting playback data and call data of the target user for the target information within a preset period; Calculating a playback effect evaluation index within the preset period according to the playback data and call data; When the playback effect evaluation index is less than a preset threshold, updating the historical browsing record of the target user; Recommend information to the target user based on the target user's updated historical browsing record.

3. The method according to claim 2, characterized in that The method further comprises: When the playback effect evaluation index is greater than or equal to the preset threshold, it is determined that the playback effect of the target information is up to standard.

4. The method according to claim 2, characterized in that: The playback data includes: the number of playback cancellations and the actual duration of continuous playback; the call data includes: the number of outgoing calls, the response time for each outgoing call, and the number of interactions for each outgoing call; the calculation of the playback effect evaluation index within the preset period based on the playback data and call data includes: Calculating a play cancellation rate according to the number of outgoing calls and the number of play cancellations within the preset period; Calculate the average playback completion rate based on the response time of each outgoing call, the actual continuous playback time and the number of outgoing calls within the preset period; Calculate the average playback interaction rate based on the number of interactions during each outgoing call and the number of outgoing calls within the preset period; The playback effect evaluation index is calculated according to the playback cancellation rate, the average playback completion rate and the average playback interaction rate.

5. The method according to claim 1, characterized in that Determining the individual browsing type preference of each target user and the group browsing type preference of the user type to which each target user belongs according to the historical browsing records of the target user includes: Classifying the historical browsing records to obtain browsing categories of the historical browsing records; Calculate the video browsing completeness based on the video browsing time and total video time of the kth video in the jth feature word in the ith browsing category by the vth target user; Calculate the video attention based on the video browsing completeness, video repeated playback times, video like times, video collection times, video comment times, and video forwarding times of the kth video in the jth feature word in the ith browsing category of the vth target user; The copy reading completeness is calculated based on the number of words read by the vth target user in the jth feature word in the ith browsing category and the total number of words in the copy; The copy attention is calculated based on the copy reading completeness, copy repeated reading times, copy like times, copy collection times, copy comment times, and copy forwarding times of the kth copy in the jth feature word in the ith browsing category by the vth target user; Calculate the personal browsing type preference of the vth target user in the i-th browsing category according to the video attention, the text attention, the number of videos and texts in the j-th feature word of the vth target user in the i-th browsing category, and the number of feature words of the vth target user in the i-th browsing category; The group browsing type preference is calculated according to the number of users of the user type to which the j-th target user belongs and the individual browsing type preference.

6. The method according to claim 1, characterized in that The recommending target information to the target user according to the individual browsing type preference and the group browsing type preference includes: Calculate the browsing type recommendation coefficient of the vth target user in the i-th browsing category based on the personal browsing type preference of the vth target user in the i-th browsing category, the group browsing type preference of the i-th browsing category of the corresponding group of the vth target user, the group browsing type preference weight coefficient and the personal browsing type preference weight coefficient; Arrange the browsing categories in descending order according to the browsing type recommendation coefficients to obtain an arrangement order of the browsing categories; The browsing type recommendation coefficients of each browsing category are reduced in ratio according to the arrangement order to obtain the simplest order integer ratio relationship between the browsing types, wherein the integer corresponding to each browsing type is the recommendation quantity, and the arrangement order of the browsing categories is the recommendation order; According to the recommended quantity of the browsing categories and the arrangement order of the browsing categories, target information is recommended to the target user.

7. An information recommendation device, characterized in that: include: An acquisition module, used to acquire the number of users of a set user level in each candidate user type; A selection module, configured to select a target user type from among the candidate user types, the number of users of the set user level meeting a set number condition; A selection module, used to select the first user corresponding to the set user level and the second user corresponding to the selected user type in the target user type as the target user, wherein the selected user type refers to the user type with the highest degree of receiving information recommendation; A determination module, used to determine the individual browsing type preference of each target user and the group browsing type preference of the user type to which each target user belongs according to the historical browsing records of the target user; A recommendation module is used to recommend target information to the target user according to the individual browsing type preference and the group browsing type preference.

8. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement each step in the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, each step of the method according to any one of claims 1 to 6 is implemented.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the steps in the method according to any one of claims 1 to 6 are implemented.

Images