Content recommendation method, device, electronic device and computer readable medium

Abstract

The embodiments of the present disclosure disclose a content recommendation method, device, electronic device and medium. A specific implementation of the method includes: determining a first-form content sequence corresponding to a content acquisition request, and the first-form content in the first-form content sequence has associated item information; selecting a first target number of second-form content from a second-form content pool to obtain a second-form content sequence; matching a second target number of first-form content ranked at the top of the first-form content sequence with the second-form content sequence to determine the first-form content with a matching second-form content; replacing at least one first-form content with a matching second-form content in the first-form content sequence with the corresponding second-form content to obtain a recommended content sequence; pushing the recommended content sequence to a terminal. This implementation can push recommended content information with richer forms and more user-friendly to the terminal used by the user.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of computer technology, and in particular to a content recommendation method, device, electronic device, and computer-readable medium. Background Art

[0002] With the continuous development of streaming media, content recommendation methods are also becoming more diverse. When facing the scenario of item recommendation, the commonly used recommendation method is: using a single form of item content recommendation, for example, usually using pictures and texts to recommend items.

[0003] However, when using the above method to recommend item content, the following technical problems often occur:

[0004] Since the content of the items is too simple, users are less interested in the recommended items, which will result in fewer and fewer users using the target application, and correspondingly reduce the network traffic consumption of the target application. Summary of the invention

[0005] The content of this disclosure is used to introduce concepts in a brief form, which will be described in detail in the detailed implementation section below. The content of this disclosure is not intended to identify the key features or essential features of the technical solution claimed for protection, nor is it intended to limit the scope of the technical solution claimed for protection.

[0006] Some embodiments of the present disclosure propose content recommendation methods, devices, electronic devices, and computer-readable media to solve one or more of the technical problems mentioned in the above background technology section.

[0007] In a first aspect, some embodiments of the present disclosure provide a content recommendation method, comprising: in response to receiving a content acquisition request for a first channel sent by a terminal, determining a first form content sequence corresponding to the content acquisition request, wherein the first form content in the first form content sequence has associated item information; based on the content quality score of the second form content, selecting a first target number of second form content from a second form content pool to obtain a second form content sequence, wherein the second form content has associated item information; matching a second target number of first form content ranked at the top in the first form content sequence with the second form content sequence according to the associated item information to determine the first form content with matching second form content; replacing at least one first form content with matching second form content in the first form content sequence with the corresponding second form content to obtain a recommended content sequence; and pushing the recommended content sequence to the terminal.

[0008] Optionally, the content quality score of the second form of content is obtained by determining a weighted sum of an author quality index, a user feedback index, and a timeliness index of the second form of content.

[0009] Optionally, before selecting a first target number of second form contents from a second form content pool based on the content quality score of the second form contents to obtain a second form content sequence, the method further includes: deleting the second form contents that have been effectively played on the second channel from the second form content pool; and / or deleting the second form contents whose associated item information does not meet preset conditions from the second form content pool.

[0010] Optionally, before pushing the recommended content sequence to the terminal, the method further includes: reordering the recommended content sequence so that the obtained rearranged recommended content sequence satisfies at least one of the following constraints: any two second-form contents are not adjacent and the interval between them satisfies a preset condition; the item information corresponding to any two adjacent contents is not the same; and pushing the recommended content sequence to the terminal includes: pushing the rearranged recommended content sequence to the terminal.

[0011] Optionally, the method further includes: in response to receiving a content acquisition request for the second channel sent by the terminal, performing the following content filtering operations to obtain a filtered content sequence: dividing the content pool into a focused content pool and a non-focused content pool according to the focus list of the user corresponding to the terminal; for the focused content pool, dividing according to the content form to obtain a first focused content group, a second focused content group and a third focused content group; for the non-focused content pool, dividing according to the content form to obtain a first non-focused content group, a second non-focused content group and a third non-focused content group; sorting each content group in each content group according to the content quality score to obtain each content sequence; filtering the content with a relevance score less than the target value from each content sequence to obtain each filtered content sequence; interspersing the content between each content sequence according to a first preset ratio to obtain the filtered content sequence.

[0012] Optionally, the relevance score of each content in the above-mentioned content sequences is generated by the following steps: determining a target tag set corresponding to the above-mentioned content; determining score information corresponding to each target tag in the above-mentioned target tag set; and determining the score information corresponding to each target tag as the relevance score of the above-mentioned content.

[0013] Optionally, the determining of the score information corresponding to each target tag in the target tag set includes: acquiring a historical content set within a target time period; segmenting the historical content set to obtain a word set; and determining the score information corresponding to each target tag in the target tag set based on the word set.

[0014] Optionally, the above-mentioned determination of the target tag set corresponding to the above-mentioned content includes: obtaining the tag set of the above-mentioned content; integrating at least one tag of the object information associated with the above-mentioned content into the tag set of the above-mentioned content to obtain an integrated tag set; and filtering out at least one tag of the target level from the above-mentioned integrated tag set as the above-mentioned target tag set.

[0015] In a second aspect, some embodiments of the present disclosure provide a content recommendation device, including: a determination unit, configured to, in response to receiving a content acquisition request for a first channel sent by a terminal, determine a first form content sequence corresponding to the above content acquisition request, and the first form content in the above first form content sequence has associated item information; a selection unit, configured to select a first target number of second form contents from a second form content pool based on content quality scores of the second form contents, to obtain a second form content sequence, wherein the above second form contents have associated item information; a matching unit, configured to match a second target number of first form contents ranked at the top in the above first form content sequence with the above second form content sequence according to the associated item information, to determine the first form content with the matching second form content; a replacement unit, configured to replace at least one first form content with the matching second form content in the above first form content sequence with the corresponding second form content, to obtain a recommended content sequence; and a push unit, configured to push the above recommended content sequence to the above terminal.

[0016] Optionally, the content quality score of the second form of content is obtained by determining a weighted sum of an author quality index, a user feedback index, and a timeliness index of the second form of content.

[0017] Optionally, the above-mentioned device also includes: deleting the second form content that has been effectively played on the second channel from the above-mentioned second form content pool; and / or deleting the second form content whose associated item information does not meet the preset conditions from the above-mentioned second form content pool.

[0018] Optionally, the above-mentioned device also includes: re-ordering the above-mentioned recommended content sequence so that the obtained rearranged recommended content sequence satisfies at least one of the following constraints: any two second-form contents are not adjacent and the interval between them satisfies a preset condition; the item information corresponding to any two adjacent contents is not the same; and the pushing unit is further configured to: push the above-mentioned rearranged recommended content sequence to the above-mentioned terminal.

[0019] Optionally, the above-mentioned device also includes: in response to receiving the content acquisition request for the second channel sent by the above-mentioned terminal, performing the following content filtering operations to obtain the filtered content sequence: dividing the content pool into a focused content pool and a non-focused content pool according to the focus list of the user corresponding to the above-mentioned terminal; for the above-mentioned focused content pool, dividing it according to the content form to obtain a first focused content group, a second focused content group and a third focused content group; for the above-mentioned non-focused content pool, dividing it according to the content form to obtain a first non-focused content group, a second non-focused content group and a third non-focused content group; sorting each content group in each content group according to the content quality score to obtain each content sequence; filtering the content with a relevance score less than the target value from the above-mentioned each content sequence to obtain each filtered content sequence; interspersing the content between each content sequence according to a first preset ratio to obtain the above-mentioned filtered content sequence.

[0020] Optionally, the relevance score of each content in the above-mentioned content sequences is generated by the following steps: determining a target tag set corresponding to the above-mentioned content; determining score information corresponding to each target tag in the above-mentioned target tag set; and determining the score information corresponding to each target tag as the relevance score of the above-mentioned content.

[0021] Optionally, the determining of the score information corresponding to each target tag in the target tag set includes: acquiring a historical content set within a target time period; segmenting the historical content set to obtain a word set; and determining the score information corresponding to each target tag in the target tag set based on the word set.

[0022] Optionally, the above-mentioned determination of the target tag set corresponding to the above-mentioned content includes: obtaining the tag set of the above-mentioned content; integrating at least one tag of the object information associated with the above-mentioned content into the tag set of the above-mentioned content to obtain an integrated tag set; and filtering out at least one tag of the target level from the above-mentioned integrated tag set as the above-mentioned target tag set.

[0023] In a third aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation manner in the first aspect.

[0024] In a fourth aspect, some embodiments of the present disclosure provide a computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the method described in any implementation manner in the first aspect is implemented.

[0025] The above-mentioned embodiments of the present disclosure have the following beneficial effects: the content recommendation method of some embodiments of the present disclosure can push recommended content information with richer forms and more preferred by users to the terminal used by the user. Specifically, due to the overly single form of the content of the item, the user has little interest in the recommended content of the item. The viscosity of the user using the target application is reduced in a side manner, thereby greatly reducing the user traffic for the target application. Based on this, the content recommendation method of some embodiments of the present disclosure can first respond to the content acquisition request for the first channel sent by the terminal, determine the first form content sequence corresponding to the above content acquisition request, and the first form content in the above first form content sequence has associated item information. Here, the above first form content sequence can be a sequence of item content that the corresponding user of the terminal may like more. By determining the first form content sequence, it can be guaranteed that the content pushed subsequently is likely to be the content that the target user likes. The user viscosity is improved in a side manner and the user traffic for the target application is increased. Then, based on the content quality score of the second form content, the first target number of second form content is selected from the second form content pool to obtain the second form content sequence. Among them, the above second form content has associated item information. Here, by the content quality score of the second form content, the second form content in the selected second form content sequence is made more popular with the user. In addition, by selecting the second form content sequence, it is used for the subsequent generation of a recommended content sequence including multiple content forms. Furthermore, according to the associated item information, the first form content of the second target number ranked first in the above-mentioned first form content sequence is matched with the above-mentioned second form content sequence to determine the first form content with the matching second form content. Here, by matching the first form content sequence with the second form content sequence, it can be guaranteed that the recommended content in the subsequent recommended content sequence of multiple content forms is the content that the corresponding user of the terminal may like, and can also be of high content quality. Then, replace at least one first form content with a matching second form content in the above-mentioned first form content sequence with the corresponding second form content to obtain a recommended content sequence. Here, by replacing the first form content sequence with the second form content sequence, a recommended content sequence with high content quality that the corresponding user of the terminal may like can be generated. In addition, the user stickiness is improved and the user traffic for the target application is increased. Finally, the recommended content information with richer forms and more favorite by users is pushed to the terminal used by the user. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.

[0027] Figure 1 is a schematic diagram of an application scenario of a content recommendation method according to some embodiments of the present disclosure;

[0028] Figure 2 is a flow chart of some embodiments of the content recommendation method according to the present disclosure;

[0029] Figure 3 is a schematic diagram of a second form of content replacement in some embodiments of the content recommendation method according to the present disclosure;

[0030] Figure 4 are flow charts of other embodiments of the content recommendation method according to the present disclosure;

[0031] Figure 5 is a schematic diagram of the structure of some embodiments of the content recommendation device according to the present disclosure;

[0032] Figure 6 It is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION

[0033] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0034] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present disclosure can be combined with each other.

[0035] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0036] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0037] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0038] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0039] Figure 1 It is a schematic diagram of an application scenario of the content recommendation method according to some embodiments of the present disclosure.

[0040] exist Figure 1In an application scenario, in response to receiving a content acquisition request for a first channel sent by a terminal 102, the electronic device 101 may determine a first form content sequence 103 corresponding to the content acquisition request, and the first form content in the first form content sequence 103 has associated item information. In this application scenario, the first form content sequence 103 may include: first form content 1031, first form content 1032, and first form content 1033. The item information corresponding to the first form content 1031 may be item information 104. The item information corresponding to the first form content 1032 may be item information 105. The item information corresponding to the first form content 1033 may be item information 107. Item information 104 may be a "hat". Item information 105 may be a "shoe". Item information 107 may be a "key chain". Then, the electronic device 101 may select a first target number of second form contents from a second form content pool 108 based on the content quality score of the second form contents, and obtain a second form content sequence 109. The second form contents have associated item information. In this application scenario, the second form content sequence 109 may include: second form content 1091, second form content 1092, and third form content 1093. The content quality score corresponding to the second form content 1091 may be: 0.9. The content quality score corresponding to the second form content 1092 may be: 0.78. The content quality score corresponding to the second form content 1093 may be: 0.6. The item information corresponding to the second form content 1091 may be item information 104. The item information corresponding to the second form content 1092 may be item information 106. The item information corresponding to the second form content 1093 may be item information 107. Among them, the item information 106 may be: tops. Furthermore, the electronic device 101 may match the first form content of the second target number of first form contents ranked first in the first form content sequence 103 with the second form content sequence 109 according to the associated item information, so as to determine the first form content with the matching second form content. In this application scenario, the first form content with matching second form content may include: first form content 1031 and first form content 1033. The second form content matching the first form content 1031 may be second form content 1091. The first form content 1031 and the second form content 1091 have the same associated item information 104. Then, the electronic device 101 replaces at least one first form content with matching second form content in the first form content sequence 103 with the corresponding second form content, and obtains a recommended content sequence 113.The first form content 1031 in the first form content sequence 103, which has a matching second form content, is replaced with the corresponding second form content 1091, to obtain recommended content 1131. The first form content 1032 in the first form content sequence 103, which has a matching second form content, is replaced with the corresponding second form content 1093, to obtain recommended content 1133. The recommended content sequence 113 includes: recommended content 1131, recommended content 1132, and recommended content 1133. The recommended content 1132 may be the second form content 1092. Finally, the electronic device 101 may push the recommended content sequence 113 to the terminal 102.

[0041] It should be noted that the electronic device 101 can be hardware or software. When the electronic device is hardware, it can be implemented as a distributed cluster consisting of multiple servers or terminal devices, or it can be implemented as a single server or a single terminal device. When the electronic device is embodied as software, it can be installed in the hardware devices listed above. It can be implemented as multiple software or software modules for providing distributed services, for example, or it can be implemented as a single software or software module. No specific limitation is made here.

[0042] It should be understood that Figure 1 The number of electronic devices in the embodiment is only for illustration. Any number of electronic devices may be provided according to implementation requirements.

[0043] Continue to refer Figure 2 , shows a process 200 of some embodiments of the content recommendation method according to the present disclosure. The content recommendation method comprises the following steps:

[0044] Step 201: in response to receiving a content acquisition request for a first channel sent by a terminal, determining a first format content sequence corresponding to the content acquisition request.

[0045] In some embodiments, in response to receiving a content acquisition request for the first channel sent by the terminal, an execution subject (eg, Figure 1 The electronic device shown in the figure can determine a first form content sequence corresponding to the above-mentioned content acquisition request. The above-mentioned terminal can be a terminal used by the target user. For example, a mobile terminal used by the target user. The above-mentioned first channel can be a channel used to display the second form content. The above-mentioned first form content can be content of the first target form. As an example, the above-mentioned first form content can be content in the form of pictures and texts. The content acquisition request for the above-mentioned first channel can be a request triggered by the target user logging in to the first channel on the terminal. The above-mentioned first form content sequence can be a content sequence that is pre-screened for the target user and liked by the target user.

[0046] It should be noted that for the first channel mentioned above, automatic playback is performed according to the user's sliding position, and only the second form of content displayed on the current screen corresponding to the first channel is played. When the user finishes sliding, it is necessary to determine whether to start / stop playing. If the user does not leave the current screen corresponding to the first channel, loop playback is performed. If the user leaves the current screen, the previous video being played is paused. If the user slides back to the current screen, playback continues.

[0047] In addition, the information (feeds) stream page of the first channel can be set to be muted by default. The user can jump to the corresponding video details page by clicking a card corresponding to a second form of content in the information stream page of the first channel.

[0048] It should be noted that the user's operations on the second channel and the first channel may be the same.

[0049] As an example, if the target user is more interested in sports-related content, the first form sequence may be: "graphic and text content related to basketball, graphic and text content related to football, graphic and text content related to table tennis, and graphic and text content related to rugby".

[0050] As another example, in response to receiving a content acquisition request for a first channel sent by a terminal, the execution subject determining a first-format content sequence corresponding to the content acquisition request may include the following steps:

[0051] The first step is to determine the identification information corresponding to the above terminal.

[0052] As an example, the execution entity may determine the identification information corresponding to the terminal by querying a database.

[0053] The second step is to determine the user tag set of the user corresponding to the terminal according to the identification information. Here, the execution subject can obtain the user tag set through the user's historical browsing content.

[0054] In the third step, according to the user tag set, a predetermined number of first-form contents are selected from the first-form content pool as a first-form content sequence. Here, the execution subject can select a predetermined number of first-form contents from the first-form content pool according to the overlapping tags between the tags of the first-form contents and the user tag set, and sort the predetermined number of first-form contents.

[0055] Step 202 : Based on the content quality scores of the second-format contents, a first target number of second-format contents are selected from a second-format content pool to obtain a second-format content sequence.

[0056] In some embodiments, the execution subject may select a first target number of second form contents from a second form content pool based on the content quality score of the second form contents to obtain a second form content sequence. The second form contents may be second target form contents. As an example, the second target form contents may be video form contents. For example, the second target form contents may be short video form contents. The content quality score of the second form contents may represent the popularity of the second form contents or user feedback information. The first target number may be preset. For example, the first target number may be 3. The second form contents pool stores various second form contents for various items.

[0057] As an example, the content quality score of each second form content in the above-mentioned second form content pool can be determined by the number of likes of the second form content. For example, the second form content with a like number between 0-100 is scored as 30 points. The second form content with a like number between 100-1000 is scored as 60 points. The second form content with a like number between 1000-10000 is scored as 80 points. The second form content with a like number between 10000-100000 is scored as 90 points. The second form content with a like number of 100000+ is scored as 100 points.

[0058] As another example, the execution subject may select a first target number of second-form contents with high content quality scores from the second-form content pool to obtain a second-form content set. Then, the execution subject may sort the second-form content set in descending order of content quality scores to obtain a second-form content sequence.

[0059] In some optional implementations of some embodiments, the content quality score of the second form of content is obtained by determining the weighted sum of the author quality index, user feedback index, and timeliness index of the second form of content. The value range of the author quality index, user feedback index, and timeliness index may be between (0, 1).

[0060] Among them, the above author quality index can be obtained by the following formula:

[0061]

[0062] Wherein, w may be the author quality indicator of the second form of content, and C may be the number of fans of the user.

[0063] It should be noted that only authors with second-form content output are counted. For authors with second-form content output but no fans, the content weight can be downgraded.

[0064] The above user feedback index can be obtained by the following formula:

[0065]

[0066] in, A valid play is one that lasts for 10 seconds or longer. The plays mentioned in the above formula are all counted as valid plays. The above execution entities can enhance the rights of the second-form content of different authors. For example, platform operation C*1.2>brand C*1.15>United warehouse live broadcast C*1.1>POP merchant C*1.05>account manager C.

[0067] Among them, the above timeliness index can be determined by the following formula:

[0068]

[0069] Among them, Ln is the logarithm with base 10. The release time is the time interval between the video release date and the current date. The unit can be day. The time is calculated in natural days, and less than one day is recorded as 1. Here, if the release time is 0, the timeliness value is 1. Among them, for the content released recently, the earlier it is recalled.

[0070] As an example, the content quality score of the second form of content can be calculated by the following formula:

[0071] The content quality score of the second form of content = author quality index*20%+user feedback index*50%+timeliness index*30%.

[0072] Step 203 , according to the associated item information, a second target number of first form contents ranked at the top in the first form content sequence are matched with the second form content sequence to determine first form contents with matching second form contents.

[0073] In some embodiments, the execution subject may match the first form content of the second target number ranked first in the first form content sequence with the second form content sequence according to the associated item information to determine the first form content with which the second form content matches. The second target number may be preset. For example, the second target number may be 50.

[0074] As an example, the execution entity may match the second target number of first form contents ranked at the top in the first form content sequence with the second form content sequence by database query according to the associated item information to determine the first form contents with which there are matching second form contents.

[0075] Step 204: replace at least one first-form content in the first-form content sequence that has a matching second-form content with the corresponding second-form content to obtain a recommended content sequence.

[0076] In some embodiments, the execution entity may replace at least one first-form content in the first-form content sequence that has a matching second-form content with the corresponding second-form content to obtain a recommended content sequence.

[0077] As an example, if there is at least one matching first form content for the second form content, the above-mentioned execution entity can replace the first form content with the highest ranking in at least one matching first form content in the first form content sequence with the above-mentioned second form content, and the remaining first form content in the at least one matching first form content will not be changed in the first form content sequence.

[0078] It should be noted that, in response to the number of first-form contents in the first-form content sequence having at least one matching second-form content being greater than a preset first number, the execution subject may replace the second-form content with a second number of first-form contents with higher content quality scores, wherein the first number is greater than or equal to the second number.

[0079] In response to the fact that the number of first form contents in the above-mentioned first form content sequence that has at least one matching second form content is less than a preset first number, the above-mentioned execution entity may not replace the second form content, but directly insert the second form content to be replaced into a fixed position in the first form content sequence.

[0080] like Figure 3 As shown, the first form content sequence 301 may be: "first form content 3011, first form content 3012, first form content 3013". The first form content 3011 and the first form content 3013 both correspond to the second form content 302. Since the first form content 3011 in the first form content sequence 301 is located before the first form content 3012, the first form content 3011 is replaced with the second form content 302 to obtain a recommended content sequence 303. The recommended content sequence 303 may be: "second form content 302, first form content 3012, first form content 3013".

[0081] Step 205: Push the recommended content sequence to the terminal.

[0082] In some embodiments, the execution entity may push the recommended content sequence to the terminal.

[0083] In some optional implementations of some embodiments, before the above step 205, the above steps further include:

[0084] The execution subject may reorder the recommended content sequence so that the obtained reordered recommended content sequence satisfies at least one of the following constraints:

[0085] (1) Any two second-format contents are not adjacent and the interval between them meets the preset conditions.

[0086] As an example, the interval between any two second-form contents may be 6 first-form contents.

[0087] (2) The item information corresponding to any two adjacent contents is different.

[0088] To further illustrate, the item information corresponding to two adjacent first-format contents may be different, and the item information corresponding to the adjacent first-format contents and second-format contents may also be different.

[0089] And the above-mentioned pushing the above-mentioned recommended content sequence to the above-mentioned terminal may include the following steps:

[0090] The execution entity may push the rearranged recommended content sequence to the terminal.

[0091] In some optional implementations of some embodiments, the above steps further include:

[0092] The first step is to perform the following content screening operations in response to receiving the content acquisition request for the second channel sent by the terminal to obtain a screening content sequence:

[0093] In the first sub-step, according to the attention list of the user corresponding to the terminal, the content pool is divided into an attention content pool and an unattention content pool.

[0094] In some embodiments, the execution subject may divide the content pool into a focused content pool and an unfocused content pool according to the focused list of the user corresponding to the terminal. The focused content pool stores the content of each author in the user's focused list. The unfocused content pool stores the content of each author in the user's unfocused list.

[0095] As an example, the execution subject may determine the attention list of the user corresponding to the terminal by querying the target database. Furthermore, the execution subject may divide the content pool into an attention content pool and an unattention content pool.

[0096] In the second sub-step, the execution subject can divide the above-mentioned content pool according to the content form to obtain a first content group, a second content group and a third content group. The first content in the first content group, the second content in the second content group and the third content in the third content group can be different forms of content.

[0097] As an example, the first content of interest in the first content group may be content in the form of a live broadcast preview. The second content of interest in the second content group may be content in the form of a short video. The third content of interest in the third content group may be content in the form of a graphic or text.

[0098] In the third sub-step, the execution subject may divide the unattended content pool into a first unattended content group, a second unattended content group, and a third unattended content group according to the content form. The first unattended content in the first unattended content group, the second unattended content in the second unattended content group, and the third unattended content in the third unattended content group may be content of different forms.

[0099] As an example, the first unfollowed content in the first unfollowed content group may also be content in the form of a live broadcast preview. The second unfollowed content in the second unfollowed content group may be content in the form of a short video. The third unfollowed content in the third unfollowed content group may be content in the form of a graphic or text.

[0100] In a fourth sub-step, the execution entity may sort each content group in each content group according to the content quality score to obtain each content sequence.

[0101] As an example, the execution entity may sort each content group in each content group in descending order of content quality score.

[0102] In a fifth sub-step, the execution subject may filter the contents whose relevance scores are less than the target value from the above-mentioned content sequences to obtain the respective filtered content sequences. The above-mentioned target value may be preset. The relevance score of the above-mentioned content may be the score of each tag in the tag set corresponding to the content. The score of the tag may represent the relevance degree between the tag and the content.

[0103] As an example, when the score of a tag is between (0-0.4), it can be said that the tag is irrelevant to the content. When the score of a tag is between [0.4-0.6), it can be said that the tag is weakly correlated to the content. When the score of a tag is between [0.6-0.8), it can be said that the tag is highly correlated to the content. When the score of a tag is between [0.8-1), it can be said that the tag is strongly correlated to the content.

[0104] In the second step, the contents between the content sequences are interspersed according to the first preset ratio to obtain the above-mentioned filtered content sequence.

[0105] As an example, the execution subject may interleave the contents between the content sequences according to the first preset ratio through the following steps:

[0106] In the first step, the content sequences in the non-focused content pool and the content sequences in the focused content pool are interspersed with each other according to the first target ratio, so that the focused content pool contains 1 / 3 of the non-focused content in the non-focused content pool, and the non-focused content pool contains some of the focused content in the focused content pool. The first target ratio can be preset.

[0107] Here, the non-focused content inserted into the above-mentioned focused content pool may be the non-focused content that ranks high in each content sequence in the non-focused content pool.

[0108] In the second step, each content sequence in the interleaved content pool is interleaved with each other according to the second target ratio and the content quality score to obtain a screening content sequence. The second target ratio may be preset.

[0109] For example, the sequences of each content in the interspersed content pool are: content sequence in the form of preview live broadcast, content sequence in the form of short video, and content sequence in the form of pictures and texts. Among them, the content sequence in the preview live broadcast form is: first preview live broadcast content, second preview live broadcast content. The quality score of the first preview live broadcast content is higher than that of the second preview live broadcast content. The content sequence in the short video form is: first short video content, second short video content. The quality score of the first short video content is higher than that of the second short video content. The content sequence in the picture and text form is: first picture and text content, second picture and text content. The quality score of the first picture and text content is higher than that of the second picture and text content. Finally, the screening content sequence can be: first preview live broadcast content, first short video content, first picture and text content, second preview live broadcast content, second short video content, and second picture and text content.

[0110] Optionally, the relevance score of each content in the above-mentioned content sequences is generated by the following steps:

[0111] The first step is to determine the target label set corresponding to the above content.

[0112] As an example, the execution subject may receive the target tag set corresponding to the content by means of expert tagging.

[0113] For example, the content is related to sports introduction, and the target tag set corresponding to the content may include: "basketball" tag, "football" tag, "table tennis" tag.

[0114] The second step is to determine the score information corresponding to each target label in the above target label set.

[0115] As an example, the execution subject may score each target tag based on the frequency of each target tag appearing in the content. For example, in the content, the frequency of the "basketball" tag appearing is 5 times. The frequency of the "football" tag appearing is 3 times. The frequency of the "table tennis" tag appearing is 2 times. Then the execution subject may determine the score corresponding to the "basketball" tag as 0.5, the score corresponding to the "football" tag as 0.3, and the score corresponding to the "table tennis" tag as 0.2.

[0116] In the third step, the score information corresponding to each of the above target tags is determined as the relevance score of the above content.

[0117] Optionally, the determining of the score information corresponding to each target tag in the target tag set may include the following steps:

[0118] The first step is to obtain the historical content set within the target time period.

[0119] As an example, the execution subject may obtain the historical content set within the target time period from the database storing the user's browsed content. The target time period may be preset, for example, half a year.

[0120] The second step is to segment the above historical content set into words to obtain a word set.

[0121] As an example, the execution subject may use Jieba word segmentation to segment each historical content in the historical content set to obtain a word set, wherein the word set may contain multiple repeated words.

[0122] The third step is to determine the score information corresponding to each target tag in the target tag set based on the above word set.

[0123] As an example, the above-mentioned execution entity can determine the frequency of each target word in the word set corresponding to the first-level category word, the second-level category word, the third-level category word, the brand word, and the feature word. Then, the number of occurrences of each target word / the number of words in the current content type word bag is used to obtain the first probability. The above-mentioned first probability can characterize the importance of the target word in the current historical content set. Next, the second probability of the number of documents in which this target word appears / the total number of documents can be determined, representing the importance of this word in all documents. Finally, the first probability corresponding to the target word is multiplied by the second probability to obtain the probability value of the target word, that is, the score information of the target tag.

[0124] For example, the content of the past six months can be 2 short videos and 2 pictures and texts.

[0125]

[0126]

[0127] Among them, there are 11 target words corresponding to short videos and 12 target words corresponding to pictures and texts.

[0128] The above target words include: United**, Wang**ji, water and dairy products, beverages, carbonated beverages, bubbles, tea beverages, coffee, bottled, Mc**di, pet life, cat and dog food, cat and dog snacks, deep-sea fish, salmon.

[0129] Then, for the short video content: the first probability corresponding to the joint ** is: the number of times the joint ** appears / the number of target words corresponding to the short video = 1 / 11. The first probability corresponding to water and dairy products is: the number of times water and dairy products appear in the two short videos / the number of target words corresponding to the short videos = 2 / 11. Similarly, the first probabilities of the remaining target words in the short video can be obtained, which will not be repeated here.

[0130] Similarly, for the content of the picture and text: the first probability corresponding to Mc**di is: the number of Mc**di appearances / the number of target words corresponding to the picture and text = 1 / 12. The first probability corresponding to water and milk products is: the number of water and milk products appearances / the number of target words corresponding to the picture and text = 1 / 12.

[0131] Then, for the short video content: the second probability corresponding to water, beverages and dairy products is: the number of short videos with water, beverages and dairy products / the number of all short videos = 2 / 2. The second probability corresponding to joint ** is: the number of short videos with joint ** / the number of all short videos = 1 / 2. Similarly, the first probabilities of the remaining target words in the short video can be obtained, which will not be repeated here.

[0132] Similarly, for the content of pictures and texts: the second probability corresponding to water and milk products is: the number of pictures and texts containing water and milk products / the number of all pictures and texts = 1 / 2. The second probability corresponding to Mc**di is: the number of pictures and texts containing Mc**di / the number of all pictures and texts = 1 / 2.

[0133] Then, for the short video content: the probability value corresponding to the joint ** is: 1 / 11*1 / 2=1 / 22. The probability value corresponding to water and dairy products is: 2 / 11*2 / 2=2 / 11.

[0134] Similarly, for the graphic content: the probability value corresponding to McDuck is: 1 / 12*1 / 2=1 / 24. The probability value corresponding to water and dairy products is: 1 / 12*1 / 2=1 / 24.

[0135] The above-mentioned embodiments of the present disclosure have the following beneficial effects: the content recommendation method of some embodiments of the present disclosure can push recommended content information with richer forms and more preferred by users to the terminal used by the user. Specifically, due to the overly single form of the content of the item, the user has little interest in the recommended content of the item. The viscosity of the user using the target application is reduced in a side manner, thereby greatly reducing the user traffic for the target application. Based on this, the content recommendation method of some embodiments of the present disclosure can first respond to the content acquisition request for the first channel sent by the terminal, determine the first form content sequence corresponding to the above content acquisition request, and the first form content in the above first form content sequence has associated item information. Here, the above first form content sequence can be a sequence of item content that the corresponding user of the terminal may like more. By determining the first form content sequence, it can be guaranteed that the content pushed subsequently is likely to be the content that the target user likes. The user viscosity is improved in a side manner and the user traffic for the target application is increased. Then, based on the content quality score of the second form content, the first target number of second form content is selected from the second form content pool to obtain the second form content sequence. Among them, the above second form content has associated item information. Here, by the content quality score of the second form content, the second form content in the selected second form content sequence is made more popular with the user. In addition, by selecting the second form content sequence, it is used for the subsequent generation of a recommended content sequence including multiple content forms. Furthermore, according to the associated item information, the first form content of the second target number ranked first in the above-mentioned first form content sequence is matched with the above-mentioned second form content sequence to determine the first form content with the matching second form content. Here, by matching the first form content sequence with the second form content sequence, it can be guaranteed that the recommended content in the subsequent recommended content sequence of multiple content forms is the content that the corresponding user of the terminal may like, and can also be of high content quality. Then, replace at least one first form content with a matching second form content in the above-mentioned first form content sequence with the corresponding second form content to obtain a recommended content sequence. Here, by replacing the first form content sequence with the second form content sequence, a recommended content sequence with high content quality that the corresponding user of the terminal may like can be generated. In addition, the user stickiness is improved and the user traffic for the target application is increased. Finally, the recommended content information with richer forms and more favorite by users is pushed to the terminal used by the user.

[0136] Further references Figure 4 , shows a process 400 of another embodiment of the content recommendation method according to the present disclosure. The content recommendation method comprises the following steps:

[0137] Step 401: in response to receiving a content acquisition request for a first channel sent by a terminal, determining a first format content sequence corresponding to the content acquisition request.

[0138] Step 402, deleting the second format content that has been effectively played on the second channel from the second format content pool; and / or deleting the second format content whose associated item information does not meet the preset conditions from the second format content pool.

[0139] In some embodiments, an execution entity (e.g. Figure 1 The electronic device shown) may delete the second form content that has been effectively played on the second channel from the second form content pool; and / or delete the second form content whose associated item information does not meet the preset conditions from the second form content pool. Among them, the basis for judging the second form content that has been effectively played on the second channel may be that the user's corresponding terminal has played the second form content before, and the playing time is greater than or equal to the target time. For example, the target time may be 5 seconds. In addition, the second form content whose associated item information does not meet the preset conditions may be the second form content whose corresponding item information is in a special state such as the item is off the shelf.

[0140] Step 403 : Based on the content quality scores of the second-format contents, a first target number of second-format contents are selected from the second-format content pool to obtain a second-format content sequence.

[0141] Step 404 , according to the associated item information, a second target number of first form contents ranked at the top in the first form content sequence are matched with the second form content sequence to determine first form contents with matching second form contents.

[0142] Step 405: Replace at least one first-form content in the first-form content sequence that has a matching second-form content with the corresponding second-form content to obtain a recommended content sequence.

[0143] Step 406: Push the recommended content sequence to the terminal.

[0144] For the specific implementation of steps 401, 403-406 and the technical effects thereof, please refer to Figure 2 The steps 201-205 in the corresponding embodiment are not described in detail here.

[0145] from Figure 4 It can be seen that Figure 2 Compared with the description of some corresponding embodiments, Figure 4The process 400 of the content recommendation method in some corresponding embodiments further highlights the specific steps of processing the second form content in the second form content pool. Therefore, the schemes described in these embodiments can make the generated recommended content sequence more likely to be liked by the user terminal, further ensuring user traffic.

[0146] Further references Figure 5 As an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a content recommendation device. These device embodiments are similar to Figure 2 Corresponding to the method embodiments shown, the device can be specifically applied to various electronic devices.

[0147] like Figure 5 As shown, a content recommendation device 500 includes: a determination unit 501, a selection unit 502, a matching unit 503, a replacement unit 504 and a push unit 505. The determination unit 501 is configured to, in response to receiving a content acquisition request for a first channel sent by a terminal, determine a first form content sequence corresponding to the content acquisition request, wherein the first form content in the first form content sequence has associated item information; the selection unit 502 is configured to select a first target number of second form contents from a second form content pool based on the content quality score of the second form content, to obtain a second form content sequence, wherein the second form content has associated item information; the matching unit 503 is configured to match a second target number of first form contents ranked at the top in the first form content sequence with the second form content sequence according to the associated item information, to determine the first form content with the matching second form content; the replacement unit 504 is configured to replace at least one first form content with the matching second form content in the first form content sequence with the corresponding second form content, to obtain a recommended content sequence; the push unit 505 is configured to push the recommended content sequence to the terminal.

[0148] In some optional implementations of some embodiments, the content quality score of the second form of content is obtained by determining a weighted sum of an author quality index, a user feedback index, and a timeliness index of the second form of content.

[0149] In some optional implementations of some embodiments, the apparatus 500 further includes: a deletion unit (not shown in the figure). The deletion unit may be configured to: delete the second form content that has been effectively played on the second channel from the second form content pool; and / or delete the second form content whose associated item information does not meet the preset condition from the second form content pool.

[0150] In some optional implementations of some embodiments, the apparatus 500 further includes: a sorting unit (not shown in the figure). The sorting unit may be configured to: re-sort the recommended content sequence so that the obtained rearranged recommended content sequence satisfies at least one of the following constraints: any two second-form contents are not adjacent and the interval between them satisfies a preset condition; any two adjacent contents have different item information. And the push unit 505 may be further configured to: push the rearranged recommended content sequence to the terminal.

[0151] In some optional implementations of some embodiments, the device 500 further includes: a screening unit (not shown in the figure). The screening unit may be configured to: in response to receiving a content acquisition request for the second channel sent by the terminal, perform the following screening operations to obtain a screening content sequence: divide the content pool into a focused content pool and a non-focused content pool according to the focus list of the user corresponding to the terminal; for the focused content pool, divide it according to the content form to obtain a first focused content group, a second focused content group and a third focused content group; for the non-focused content pool, divide it according to the content form to obtain a first non-focused content group, a second non-focused content group and a third non-focused content group; sort each content group in each content group according to the content quality score to obtain each content sequence; filter the content with a relevance score less than the target value from each content sequence to obtain each filtered content sequence; interleave the content between each content sequence according to the first preset ratio to obtain the screening content sequence.

[0152] In some optional implementations of some embodiments, the relevance score of each content in the above-mentioned content sequences is generated through the following steps: determining a target tag set corresponding to the above-mentioned content; determining score information corresponding to each target tag in the above-mentioned target tag set; and determining the score information corresponding to each target tag as the relevance score of the above-mentioned content.

[0153] In some optional implementations of some embodiments, the apparatus 500 further includes: a score information determination unit. The score information determination unit may be further configured to: obtain a historical content set within a target time period; perform word segmentation on the historical content set to obtain a word set; and determine, based on the word set, the score information corresponding to each target tag in the target tag set.

[0154] In some optional implementations of some embodiments, the device 500 further includes: a target tag determination unit. The target tag determination unit may be further configured to: obtain a tag set of the content; integrate at least one tag of the item information associated with the content into the tag set of the content to obtain an integrated tag set; and filter out at least one tag of the target level from the integrated tag set as the target tag set.

[0155] It is understood that the units described in the device 500 are similar to those described in the reference Figure 2 Therefore, the operations, features and beneficial effects described above for the method are also applicable to the device 500 and the units included therein, and will not be described in detail here.

[0156] Reference below Figure 6 , which shows an electronic device (eg, Figure 1 A schematic diagram of the structure of an electronic device (electronic device in FIG. 600). Figure 6 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0157] like Figure 6 As shown, the electronic device 600 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage device 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the electronic device 600 are also stored. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0158] Typically, the following devices may be connected to the I / O interface 605: an input device 606 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 608 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 609. The communication device 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 6 The electronic device 600 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead. Figure 6 Each block shown in the figure may represent one device, or may represent multiple devices as required.

[0159] In particular, according to some embodiments of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, some embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In some such embodiments, the computer program can be downloaded and installed from the network through the communication device 609, or installed from the storage device 608, or installed from the ROM 602. When the computer program is executed by the processing device 601, the above-mentioned functions defined in the method of some embodiments of the present disclosure are executed.

[0160] It should be noted that the computer-readable medium in some embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In some embodiments of the present disclosure, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In some embodiments of the present disclosure, the computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0161] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0162] The computer-readable medium may be included in the electronic device; or it may exist independently without being installed in the electronic device. The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: in response to receiving a content acquisition request for a first channel sent by a terminal, determine a first-form content sequence corresponding to the content acquisition request, and the first-form content in the first-form content sequence has associated item information; based on the content quality score of the second-form content, select a first target number of second-form content from a second-form content pool to obtain a second-form content sequence, wherein the second-form content has associated item information; according to the associated item information, match the second target number of first-form content ranked first in the first-form content sequence with the second-form content sequence to determine the first-form content with a matching second-form content; replace at least one first-form content with a matching second-form content in the first-form content sequence with the corresponding second-form content to obtain a recommended content sequence; push the recommended content sequence to the terminal.

[0163] Computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0164] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0165] The units described in some embodiments of the present disclosure may be implemented by software or by hardware. The described units may also be provided in a processor, for example, may be described as: a processor including a determination unit, a selection unit, a matching unit, a replacement unit, and a push unit. The names of these units do not constitute limitations on the units themselves in certain circumstances, for example, the determination unit may also be described as "a unit that, in response to receiving a content acquisition request for a first channel sent by a terminal, determines a first form of a content sequence corresponding to the above content acquisition request".

[0166] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0167] The above descriptions are only some preferred embodiments of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by a specific combination of the above-mentioned technical features, but should also cover other technical solutions formed by any combination of the above-mentioned technical features or their equivalent features without departing from the above-mentioned inventive concept. For example, the above-mentioned features are replaced with the technical features with similar functions disclosed in the embodiments of the present disclosure (but not limited to) and the technical solutions formed.

Claims

1. A content recommendation method, comprising: In response to receiving a content acquisition request for a first channel sent by a terminal, determining a first-format content sequence corresponding to the content acquisition request, wherein first-format content in the first-format content sequence has associated item information; Based on the content quality scores of the second-form contents, selecting a first target number of second-form contents from a second-form content pool to obtain a second-form content sequence, wherein the second-form contents have associated item information; According to the associated item information, a second target number of first-form contents ranked first in the first-form content sequence are matched with the second-form content sequence to determine first-form contents with matching second-form contents; Replacing at least one first-form content in the first-form content sequence that has a matching second-form content with the corresponding second-form content to obtain a recommended content sequence; The recommended content sequence is pushed to the terminal.

2. The method according to claim 1, wherein: The content quality score of the second form content is obtained by determining a weighted sum of an author quality index, a user feedback index, and a timeliness index of the second form content.

3. The method according to claim 1, wherein: Before selecting a first target number of second-format contents from a second-format content pool based on the content quality scores of the second-format contents to obtain a second-format content sequence, the method further includes: Deleting the second format content that has been effectively played on the second channel from the second format content pool; and / or The second form content whose associated item information does not meet the preset condition is deleted from the second form content pool.

4. The method according to claim 1, wherein: Before pushing the recommended content sequence to the terminal, the method further includes: The recommended content sequence is reordered so that the obtained reordered recommended content sequence satisfies at least one of the following constraints: Any two second form contents are not adjacent and the interval between them meets the preset conditions; The item information corresponding to any two adjacent contents is different; and The step of pushing the recommended content sequence to the terminal includes: The rearranged recommended content sequence is pushed to the terminal.

5. The method according to claim 4, wherein: The method further comprises: In response to receiving the content acquisition request for the second channel sent by the terminal, the following content screening operations are performed to obtain a screening content sequence: According to the attention list of the user corresponding to the terminal, the content pool is divided into an attention content pool and an unattention content pool; The concerned content pool is divided according to the content form to obtain a first concerned content group, a second concerned content group and a third concerned content group; The unattended content pool is divided according to the content form to obtain a first unattended content group, a second unattended content group and a third unattended content group; Sorting each content group in each content group according to the content quality score to obtain each content sequence; filtering contents with relevance scores less than a target value from each of the content sequences to obtain each filtered content sequence; The contents between the content sequences are interspersed according to a first preset ratio to obtain the screened content sequence.

6. The method according to claim 5, wherein: The relevance score of each content in each content sequence is generated by the following steps: Determine a target tag set corresponding to the content; Determine the score information corresponding to each target tag in the target tag set; The score information corresponding to each target tag is determined as the relevance score of the content.

7. The method according to claim 6, wherein: The determining the score information corresponding to each target tag in the target tag set includes: Obtain the historical content set within the target time period; Segmenting the historical content set to obtain a word set; According to the word set, score information corresponding to each target tag in the target tag set is determined.

8. The method according to claim 6, wherein: The determining a target tag set corresponding to the content includes: Get the tag set of the content; Integrate at least one tag of the item information associated with the content into a tag set of the content to obtain an integrated tag set; At least one label of a target level is selected from the integrated label set as the target label set.

9. A content recommendation device, comprising: a determining unit configured to, in response to receiving a content acquisition request for a first channel sent by a terminal, determine a first-format content sequence corresponding to the content acquisition request, wherein the first-format content in the first-format content sequence has associated item information; a selection unit configured to select a first target number of second-form contents from a second-form content pool based on content quality scores of the second-form contents to obtain a second-form content sequence, wherein the second-form contents have associated item information; a matching unit configured to match a second target number of first-form contents ranked first in the first-form content sequence with the second-form content sequence according to the associated item information, so as to determine first-form contents with matching second-form contents; A replacement unit, configured to replace at least one first-form content in the first-form content sequence that has a matching second-form content with a corresponding second-form content, to obtain a recommended content sequence; A pushing unit is configured to push the recommended content sequence to the terminal.

10. An electronic device, comprising: one or more processors; a storage device having one or more programs stored thereon, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 8.

11. A computer readable medium having a computer program stored thereon, wherein: When the program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images