CN115795146A - Method, device and equipment for determining resources to be recommended and storage medium - Google Patents

Method, device and equipment for determining resources to be recommended and storage medium Download PDF

Info

Publication number
CN115795146A
CN115795146A CN202211413067.9A CN202211413067A CN115795146A CN 115795146 A CN115795146 A CN 115795146A CN 202211413067 A CN202211413067 A CN 202211413067A CN 115795146 A CN115795146 A CN 115795146A
Authority
CN
China
Prior art keywords
resource
candidate
determining
gear
target
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202211413067.9A
Other languages
Chinese (zh)
Inventor
邓罗丹
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Baidu Netcom Science and Technology Co Ltd
Original Assignee
Beijing Baidu Netcom Science and Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Baidu Netcom Science and Technology Co Ltd filed Critical Beijing Baidu Netcom Science and Technology Co Ltd
Priority to CN202211413067.9A priority Critical patent/CN115795146A/en
Publication of CN115795146A publication Critical patent/CN115795146A/en
Pending legal-status Critical Current

Links

Images

Landscapes

  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The disclosure provides a method, a device, equipment and a storage medium for determining resources to be recommended, relates to the technical field of data processing, particularly relates to the technical fields of big data, information flow, intelligent recommendation and the like, and can be used in information flow recommendation scenes. The specific implementation scheme is as follows: acquiring candidate resources to be recommended; determining a first resource gear where the candidate resource is located; comparing the resource quality of the candidate resource with the quality requirement corresponding to the second resource gear to obtain a comparison result, wherein the quality requirement corresponding to the second resource gear is higher than that of the first resource gear; according to the comparison result, the recommendation weight of the candidate resource is adjusted to obtain a target recommendation weight; and determining the target resource to be recommended according to the target recommendation weight. Therefore, compared with the quality requirements of different gears, the recommended resources are pushed to incline towards high-quality resources, and the resource recommendation quality is improved.

Description

Method, device and equipment for determining resources to be recommended and storage medium
Technical Field
The present disclosure relates to the technical fields of big data, information flow, intelligent recommendation, and the like in the technical field of data processing, and may be used in an information flow recommendation scenario, and in particular, to a method, an apparatus, a device, and a storage medium for determining resources to be recommended.
Background
In an information flow recommendation scenario, a user may act as both a consumer and a producer of resources. For example, when a user writes an article, shoots a video and shares the article, the user is a producer of resources; when a user reads articles of other users on the network, the user is a consumer of resources.
In consideration of the uneven quality of resources in the information flow recommendation scene, in order to avoid the over-distribution of low-quality resources and bring adverse effects to the ecological health development of the information flow recommendation system, the quality of the resources can be scored. When information stream recommendation is performed in the related art, usually, a weight coefficient corresponding to the quality score is directly multiplied by the resource to perform recommendation weight adjustment, and then the distribution amount of the resource is adjusted.
However, the above technology cannot further tilt the information flow recommendation system toward high-quality resources, and the problem of low quality of actually recommended resources still exists.
Disclosure of Invention
The disclosure provides a method, a device, equipment and a storage medium for determining resources to be recommended, wherein the method, the device and the equipment are used for improving the quality of recommended resources.
According to a first aspect of the present disclosure, a method for determining a resource to be recommended is provided, including:
acquiring candidate resources to be recommended;
determining a first resource gear where the candidate resource is located;
comparing the resource quality of the candidate resource with a quality requirement corresponding to a second resource gear to obtain a comparison result, wherein the quality requirement corresponding to the second resource gear is higher than the quality requirement of the first resource gear;
according to the comparison result, the recommendation weight of the candidate resource is adjusted to obtain a target recommendation weight;
and determining the target resource to be recommended according to the target recommendation weight.
According to a second aspect of the present disclosure, there is provided an apparatus for determining a resource to be recommended, including:
the resource acquisition unit is used for acquiring candidate resources to be recommended;
a gear determining unit, configured to determine a first resource gear in which the candidate resource is located;
the quality comparison unit is used for comparing the resource quality of the candidate resource with a quality requirement corresponding to a second resource gear to obtain a comparison result, wherein the quality requirement corresponding to the second resource gear is higher than the quality requirement of the first resource gear;
the weight adjusting unit is used for adjusting the recommendation weight of the candidate resource according to the comparison result to obtain a target recommendation weight;
and the resource determining unit is used for determining the target resource to be recommended according to the target recommendation weight.
According to a third aspect of the present disclosure, there is provided an electronic device comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor;
wherein the memory stores instructions executable by the at least one processor, the instructions being executable by the at least one processor to enable the at least one processor to perform the method for determining a resource to be recommended of the first aspect.
According to a fourth aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute the method for determining a resource to be recommended of the first aspect.
According to a fifth aspect of the present disclosure, there is provided a computer program product comprising: a computer program, stored in a readable storage medium, from which at least one processor of an electronic device can read the computer program, and the at least one processor executes the computer program to make the electronic device execute the method for determining a resource to be recommended according to the first aspect.
According to the technical scheme provided by the disclosure, the resource can be divided into a plurality of resource gears, after a first resource gear where the candidate resource to be recommended is located is determined, the candidate resource to be recommended is compared with the quality requirement corresponding to a second resource gear, wherein the quality requirement corresponding to the second resource gear is higher than the quality requirement corresponding to the first resource gear. In this way, a cross-gear comparison of resources is achieved, in particular with gears with higher quality requirements. And adjusting the recommendation weight of the candidate resource according to the comparison result to obtain a target recommendation weight, and determining the target resource to be recommended according to the target recommendation weight, so that the recommendation weight can incline towards the candidate resource with higher quality, namely the candidate resource with higher quality can have higher recommendation weight and the recommended probability is higher. Therefore, the resource quality of the recommended resources is improved by grading the resources and performing cross-grade comparison on the resources, and particularly, the information flow recommendation system is pushed to incline towards the recommended high-quality resources, so that the information flow recommendation system is developed ecologically and healthily.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.
Drawings
The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:
FIG. 1 is a schematic diagram of an application scenario in which embodiments of the present disclosure are applicable;
fig. 2 is a first flowchart illustrating a method for determining a resource to be recommended according to an embodiment of the present disclosure;
fig. 3 is a flowchart illustrating a second method for determining a resource to be recommended according to an embodiment of the present disclosure;
fig. 4 is a third flowchart illustrating a method for determining a resource to be recommended according to an embodiment of the present disclosure;
fig. 5 is a flowchart illustrating a method for determining a resource to be recommended according to an embodiment of the present disclosure;
fig. 6 is a first schematic structural diagram of a device for determining resources to be recommended according to an embodiment of the present disclosure;
fig. 7 is a schematic structural diagram ii of a device for determining resources to be recommended according to an embodiment of the present disclosure;
fig. 8 is a schematic block diagram of an example electronic device 800 that may be used to implement embodiments of the present disclosure.
Detailed Description
Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
In order to avoid that resources with poor quality are excessively distributed to influence the ecological healthy development of the information flow recommendation system, the quality of the resources can be graded, and the distribution amount of the resources can be regulated and controlled according to the quality grading of the resources. The resource can be regulated and controlled in the resource recommendation in the following modes:
in the first mode, the right is directly adjusted. Specifically, the recommendation weight of the resource can be directly multiplied by a corresponding weight adjustment coefficient according to the quality score of the resource to adjust the recommendation weight of the resource.
And secondly, grading the resources according to the display amount or the distribution amount of the resources, comparing the quality scores of the resources in the same grade, improving the recommendation weight of the resources with higher quality scores, and reducing the recommendation weight of the resources with lower quality scores.
The first mode is simple in implementation process, but the high-quality resources and the low-quality resources have no obvious distinguishing limit, so that the resource recommendation is difficult to be pushed to further incline towards the high-quality resources, and the weighting factor is difficult to determine, so that the finally recommended resources are poor in quality; in the second mode, resource quality comparison is performed in the same file, the comparison range is limited, and from a global perspective, a resource with better quality cannot be provided with a higher recommendation weight, and a resource with lower quality is provided with a lower recommendation weight. For example, the resource quality of a certain resource belongs to a tail resource at a low level, that is, a resource with poor quality, and the recommended weight of the resource is reduced by adopting the second mode; when the distribution amount of the resource reaches the high gear, the resource may belong to a head resource, that is, a resource with better quality, and the recommendation weight of the resource is increased in the second mode, which shows that the recommendation weight of the resource cannot change towards a trend. Therefore, from the global perspective, the second method is difficult to push the resource recommendation to incline towards the high-quality resource, and the problem that the quality of the finally recommended resource is poor exists.
In order to solve the above defects, the present disclosure provides a method, an apparatus, a device, and a storage medium for determining a resource to be recommended, which are applied to the technical fields of big data, information flow, technical recommendation, and the like in the technical field of data processing. In the method for determining the resources to be recommended, the resource quality of the candidate resources to be recommended is compared with the quality requirement of a higher gear, the recommendation weight of the candidate resources is adjusted according to the comparison result to obtain the target recommendation weight, and the target resources to be recommended are determined according to the target recommendation weight. Therefore, through resource grading and cross-grade comparison of resource quality, resource recommendation is pushed to incline towards high-quality resources, the resource recommendation quality is improved, and particularly, an information flow recommendation system is pushed to incline towards the recommendation of the high-quality resources, so that the information flow recommendation system is developed ecologically and healthily.
Fig. 1 is a schematic diagram of an application scenario to which the embodiment of the present disclosure is applied, where the application scenario may be an information flow recommendation scenario. In an application scenario, the devices involved include a resource recommendation apparatus 101 and a resource database 102. The resource recommendation device 101 may be a server or a terminal, and fig. 1 takes the resource recommendation device 101 as an example; the resource database 102 stores a plurality of resources therein.
The resource recommending device 101 may obtain candidate resources to be recommended from the resource database 102, perform weight adjustment on the candidate resources in a resource grading and cross-gear comparison manner, and determine a target resource to be recommended from the candidate resources with the weight adjustment.
Optionally, the application scenario further includes the terminal 103. The terminal 103 may send a resource recommendation request to the resource recommendation device 101, and the resource recommendation device 101 may further screen the target resource and then send the target resource to the terminal 103, or may directly send the target resource to the terminal 103 for resource recommendation.
The resource recommendation device 101 and the terminal 103 may communicate by wire or wirelessly, and fig. 1 illustrates a wireless method as an example.
As an example, a user performs video refresh on a video presentation page displayed by the terminal 103, the terminal 103 sends a video recommendation request to the resource recommendation device 101 in response to a refresh operation of the user, and the resource recommendation device 101 sends a recommendation video to the terminal 103 in response to the video recommendation request.
The following describes the technical solutions of the present disclosure and how to solve the above technical problems in detail with specific embodiments. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments. Embodiments of the present disclosure will be described below with reference to the accompanying drawings.
For example, the execution subject of the embodiment of the present disclosure may be an electronic device, and the electronic device may be a server or a terminal. The server may be a centralized server, a distributed server, or a cloud server. The terminal may be a Personal Digital Assistant (PDA) device, a handheld device (e.g., a smart phone or a tablet computer) with a wireless communication function, a computing device (e.g., a Personal Computer (PC)), an in-vehicle device, a wearable device (e.g., a smart watch or a smart band), a smart home device (e.g., a smart speaker, a smart display device), and the like.
Fig. 2 is a first flowchart illustrating a method for determining a resource to be recommended according to an embodiment of the present disclosure. As shown in fig. 2, the method for determining a resource to be recommended includes:
s201, obtaining candidate resources to be recommended.
Wherein the resource may be media data. The media data may be data in the form of a single media, such as text, sound, image, etc.; and/or the media data may be data formed by multimedia synthesis, such as video, text with pictures and texts, music including melody and lyrics, and the like.
Wherein the number of the candidate resources is one or more.
In this embodiment, the candidate resource to be recommended may be obtained from the database. Wherein the database includes a plurality of resources. The method for acquiring the candidate resources to be recommended from the database may be one-by-one according to a resource storage sequence, may also be randomly acquired, and may also be acquired from high to low according to the matching degree of the user attribute and the resource, where the matching process is not described in detail here.
S202, determining a first resource gear of the candidate resource.
The number of the resource gears can be multiple, and different resource gears correspond to different gear requirements. The gear requirements corresponding to the resource gears can include flow requirements corresponding to the resource gears and quality requirements corresponding to the resource gears, and the higher the resource gears are, the higher the flow requirements corresponding to the resource gears are and the higher the quality requirements corresponding to the resource gears are. When the resource is graded, the grading can be carried out according to the resource flow of the resource and the flow requirement corresponding to the resource gear.
Wherein, the higher the resource flow of the resource, the higher the resource quality of the resource is not necessarily. For example, some resources are forwarded and reviewed many times, but not necessarily good resources. Therefore, after the resources are graded based on the resource flow of the resources, the recommendation weight of the resources can be further adjusted based on the resource quality of the resources, so that the resource flow of the resources at the future moment can be regulated and controlled, and the situation that the resources with poor quality are excessively recommended to the user is reduced.
The first resource gear refers to a resource gear corresponding to a flow requirement met by the resource flow of the candidate resource in the plurality of resource gears.
In this embodiment, the first resource gear where the candidate resource is located may be determined based on the resource traffic of the candidate resource at the historical time or the resource traffic of the candidate resource at the current time, and the accuracy of the first resource gear may be improved by determining the first resource gear where the candidate resource is located according to the resource traffic of the candidate resource at the current time in consideration of the change of the resource traffic of the candidate resource over time.
In the process of determining the first resource gear of the candidate resource according to the resource flow of the candidate resource at the current moment, the resource flow of the candidate resource at the current moment can be compared with the flow requirements respectively corresponding to the plurality of resource gears one by one to obtain the resource gear corresponding to the flow requirement met by the resource flow of the candidate resource, and the first resource gear is obtained.
S203, comparing the resource quality of the candidate resource with the quality requirement corresponding to the second resource gear to obtain a comparison result, wherein the quality requirement corresponding to the second resource gear is higher than the quality requirement of the first resource gear.
In this embodiment, after the first resource gear where the candidate resource is located is determined, that is, after the resource gear where the resource traffic of the candidate resource reaches is determined, if the candidate resource is not interfered, the resource traffic of the candidate resource will gradually increase as time progresses, the resource traffic of the candidate resource will reach a traffic requirement corresponding to a higher resource gear, for example, a traffic requirement corresponding to a second resource gear, and a situation that the resource traffic of the low-quality resource is very large is likely to occur.
In order to avoid such a situation and improve the quality of the resource recommended to the user, after the first resource gear is determined, a second resource gear can be selected from the multiple resource gears according to the first resource gear, the resource quality of the candidate resource is compared with the quality requirement corresponding to the second resource gear to obtain a comparison result, and whether the candidate resource needs to be interfered is determined according to the comparison result.
And S204, according to the comparison result, adjusting the recommendation weight of the candidate resource to obtain the target recommendation weight.
The recommendation weight of the candidate resource may be determined according to a recommendation algorithm (for example, matching the candidate resource with the user attribute to obtain a degree of interest of the user in the candidate resource, and determining the recommendation weight according to the degree of interest), where a determination process of the recommendation weight of the candidate resource is not limited.
The target recommendation weight refers to the recommendation weight after the candidate resource is adjusted.
In this embodiment, whether intervention is required to be performed on the candidate resource is determined according to a comparison result of the candidate resource and the second resource gear, and if it is determined that intervention is required to be performed on the candidate resource, the recommendation weight of the candidate resource may be increased or decreased, so that resource flow of the candidate resource at a future moment is adjusted to obtain a target recommendation weight, otherwise, the recommendation weight of the candidate resource may be kept unchanged.
S205, determining the target resource to be recommended according to the target recommendation weight.
In this embodiment, the target resource to be recommended may be selected from the candidate resources according to the target recommendation weight of the candidate resources. For example, one or more candidate resources may be selected according to the order of the target recommendation weight from high to low, and the target resource may be determined as the selected one or more candidate resources.
In the embodiment of the disclosure, the recommendation weight of the candidate resource is adjusted in a resource grading and trans-gear resource quality comparison mode, so that the accuracy and the reasonability of the recommendation weight adjustment are improved; and determining the target resource to be recommended according to the adjusted recommendation weight, and realizing the control of the resource flow of the target resource in the future, so that the probability of recommending high-quality resources is increased, the probability of recommending low-quality resources is reduced, the resource recommendation is inclined to the high-quality resources, and the resource recommendation quality is improved.
Possible implementations of some of the steps in the above embodiments are provided below.
In some embodiments, the resource recommendation process may include a plurality of resource filtering links, such as recall, rough ranking, and fine ranking, based on which one possible implementation manner of S201 includes: and in one or more resource screening links, candidate resources to be recommended are obtained. Therefore, by utilizing the embodiment of the disclosure, the accuracy and the rationality of the recommendation weight of the resources in one or more resource screening links are improved, the quality of the resources screened in one or more resource screening links is improved, and the resource recommendation quality is further improved.
In this implementation manner, in the resource screening step, the candidate resource to be recommended may be obtained from a plurality of resources before screening or a plurality of resources after screening. For example, in the recall link, a plurality of resources are recalled from the database, and candidate resources to be recommended are obtained from the plurality of resources.
In some embodiments, the resource traffic of the candidate resource includes resource statistics of the candidate resource, the resource statistics of the candidate resource being statistics of the candidate resource in terms of the resource traffic. Based on this, one possible implementation manner of S202 includes: acquiring resource statistics of candidate resources; and determining a first resource gear in the plurality of resource gears according to the resource statistics of the candidate resources and the statistic requirements respectively corresponding to the plurality of resource gears. Therefore, the characteristic of resource flow can be reflected more accurately and clearly by utilizing the resource statistics, and the accuracy of determining the first resource gear for the candidate resource is improved.
In this implementation manner, the resource statistics of the candidate resources at the current time can be compared with the statistics requirements corresponding to the resource gears, respectively, one by one, to obtain the resource gear that is satisfied by the resource statistics of the candidate resources, i.e., the first resource gear.
The statistic requirement can be a statistic threshold value or a statistic value range.
Under the condition that the statistic requirement is a statistic threshold value, the resource statistic of the candidate resources is larger than the statistic threshold value corresponding to the first resource gear and smaller than the statistic threshold value corresponding to the resource gear which is one gear higher than the first resource gear; and under the condition that the statistic requirement is a statistic value range, the resource statistic of the candidate resource is located in the statistic value range corresponding to the first resource gear.
Further, the resource statistics include a current exhibited amount of the candidate resource and/or a current distributed amount of the candidate resource. The display quantity of the resources refers to the times of displaying the resources to the user, and the display refers to display on a page and can also be understood as the times of recommending the resources to the user; the number of times that the resource is clicked by the user; the current showing quantity of the candidate resources refers to the showing quantity of the candidate resources at the current moment, and the current distribution quantity of the candidate resources refers to the distribution quantity of the candidate resources at the current moment.
Under the condition that the resource statistics comprise the current display quantity of the candidate resources, the statistics corresponding to the resource gear comprises a display quantity threshold or a display quantity range corresponding to the resource gear; and in the case that the resource statistic comprises the current distribution amount of the candidate resource, the statistic corresponding to the resource gear comprises a distribution amount threshold or a distribution amount range corresponding to the resource gear.
As an example, the resource statistic of the candidate resource at the current time may be the current forwarding amount, the current collection amount, and the like of the candidate resource, in addition to the current exposure amount and the current distribution amount.
In some embodiments, the resource quality of the candidate resource may be represented as a quality score of the candidate resource, and the quality requirement corresponding to the resource gear may be represented as a quality score threshold or a quality score value range corresponding to the resource gear. Based on this, one possible implementation manner of S203 includes: and comparing the quality of the candidate resources with a quality score threshold corresponding to the second resource gear, or comparing the quality of the candidate resources with a quality score value range corresponding to the second resource gear. Therefore, the resource quality of the candidate resource and the quality requirement corresponding to the second resource gear are compared in a mode of comparing the quality score, the quality score threshold value and the quality score value range, and the accuracy and the precision of the comparison are improved.
Besides the quality score, the resource quality of the candidate resource can be represented as a quality grade of the candidate resource, and the quality requirement corresponding to the resource gear can be represented as a quality grade requirement corresponding to the resource gear. For example, the quality grades are grade one, grade two, 8230, and the like.
In some embodiments, the second resource gear may be an adjacent resource gear to the first resource gear, in other words, the second resource gear may be a resource gear that is one gear higher than the first resource gear. Therefore, the resource quality of the candidate resources is compared with the quality requirement corresponding to the resource gear of the higher first gear of the resource gear where the candidate resources are located, the effect and the accuracy of the weight adjustment of the candidate resources are improved, the resource flow of the high-quality candidate resources after the weight adjustment can be promoted to reach the flow requirement corresponding to the resource gear of the higher first gear as soon as possible, and the resource flow of the low-quality candidate resources after the weight adjustment can be slowed down or prevented from reaching the flow requirement corresponding to the resource gear of the higher first gear.
Fig. 3 is a flowchart illustrating a second method for determining a resource to be recommended according to an embodiment of the present disclosure. As shown in fig. 3, the method for determining a resource to be recommended includes:
s301, acquiring candidate resources to be recommended.
And S302, determining a first resource gear of the candidate resource.
And S303, comparing the resource quality of the candidate resource with the quality requirement corresponding to the second resource gear to obtain a comparison result, wherein the quality requirement corresponding to the second resource gear is higher than that of the first resource gear.
The implementation principle and the technical effect of S301 to S303 may refer to the related description of the foregoing embodiments, and are not described herein again.
And S304, according to the comparison result, adjusting the recommendation weight of the candidate resource to obtain the target recommendation weight.
In this embodiment, the resource quality of the candidate resource is compared with the quality requirement corresponding to the second resource gear to obtain a comparison result, where the comparison result may be that the resource quality of the candidate resource satisfies the quality requirement corresponding to the second resource gear, the resource quality of the candidate resource is higher than the quality requirement corresponding to the second resource gear, or the resource quality of the candidate resource is lower than the quality requirement corresponding to the second resource gear. According to different comparison results, different adjustment modes can be adopted for the recommendation weight so as to improve the rationality and accuracy of the adjustment of the recommendation weight, namely the rationality and accuracy of the target recommendation weight.
As shown in fig. 3, S304 includes S3041 to S3043:
s3041, if the resource quality of the candidate resource meets the quality requirement corresponding to the second resource gear as the comparison result, determining the target recommendation weight as a first weight, where the first weight is a current recommendation weight of the candidate resource.
In this embodiment, the resource quality of the candidate resource meets the quality requirement corresponding to the second resource gear, which indicates that the resource flow of the candidate resource is suitable for meeting the flow requirement corresponding to the second resource gear. Under the condition of no intervention, the resource flow of the candidate resource reaches the flow requirement corresponding to the second resource gear along with the increase of time, so that the candidate resource can be determined to be the first weight without intervention, namely the current recommendation weight of the candidate resource is kept unchanged.
S3042, if the resource quality of the candidate resource is higher than the quality requirement corresponding to the second resource gear according to the comparison result, determining the target recommendation weight as a second weight according to the current recommendation weight of the candidate resource, wherein the second weight is larger than the current recommendation weight of the candidate resource.
In this embodiment, the resource quality of the candidate resource is higher than the quality requirement corresponding to the second resource gear, which indicates that the resource quality of the candidate resource not only meets the quality requirement corresponding to the second resource gear, but also exceeds the quality requirement corresponding to the second resource gear, and can meet the quality requirement corresponding to the resource gear higher than the second resource gear, thereby indicating that the resource flow of the candidate resource can reach the resource gear higher than the second resource gear. In this case, if no intervention is performed, the resource traffic of the candidate resource may take a longer time to reach the traffic requirement corresponding to the resource gear higher than the second resource gear, and in order to promote a faster increase of the resource traffic of the candidate resource with high quality, that is, to promote the resource with high quality to be recommended to the user more times and with a higher probability, the recommendation weight of the candidate resource may be increased. In the process of increasing the recommended resource of the candidate resource, the target recommendation weight may be determined based on the current recommendation weight of the candidate resource, and at this time, the target recommendation weight is a second weight greater than the current recommendation weight.
S3043, if the comparison result shows that the resource quality of the candidate resource is lower than the quality requirement corresponding to the second resource gear, determining the target recommendation weight as a third weight according to the current recommendation weight of the candidate resource, wherein the third weight is smaller than the current recommendation weight of the candidate resource.
In this embodiment, the resource quality of the candidate resource is lower than the quality requirement corresponding to the second resource gear, which indicates that the resource traffic of the candidate resource is not suitable for meeting the traffic requirement corresponding to the second resource gear, however, the resource traffic of the candidate resource naturally meets the traffic requirement corresponding to the second resource gear over time without intervention. Therefore, the candidate resource needs to be intervened to slow down or even organize the resource traffic of the candidate resource to reach the traffic requirement corresponding to the second resource gear. To achieve the objective, the target recommendation weight may be determined according to the current recommendation weight of the candidate resource, and at this time, the target recommendation weight is a third weight smaller than the current recommendation weight.
In one possible implementation, in the case that the resource quality of the candidate resource is expressed as a quality score, the meaning of the different comparison results is as follows:
the resource quality of the candidate resource meets the quality requirement corresponding to the second resource gear: the quality score of the candidate resource is located in the quality score value range corresponding to the second resource gear, or the quality score of the candidate resource is larger than or equal to the quality score threshold corresponding to the second resource gear and the quality score of the candidate resource is smaller than or equal to the quality score threshold corresponding to the resource gear which is higher than the second resource gear by one gear.
The resource quality of the candidate resource is higher than the quality requirement corresponding to the second resource gear: the quality score of the candidate resource is larger than the maximum value in the quality score value range corresponding to the second resource gear, or the quality score of the candidate resource is larger than the quality score threshold value corresponding to the resource gear higher than the second resource gear by one gear.
The resource quality of the candidate resources is lower than the quality requirement corresponding to the second resource gear: the quality score of the candidate resource is smaller than the minimum value in the quality score value range corresponding to the second resource gear, or the quality score of the candidate resource is smaller than the quality score threshold value corresponding to the second resource gear.
In a possible implementation manner, under the condition that the second resource gear is an adjacent resource gear of the first resource gear, if the quality score of the candidate resource is smaller than the quality score threshold corresponding to the second resource gear, it is determined that the resource quality of the candidate resource is lower than the quality requirement corresponding to the second resource gear, and the recommendation weight of the candidate resource needs to be reduced. If the quality score of the candidate resource is greater than the quality score threshold corresponding to the second resource gear, whether the quality score of the candidate resource is greater than or equal to the quality score threshold corresponding to the third resource gear can be judged, if yes, the resource quality of the candidate resource is determined to be higher than the quality requirement corresponding to the second resource gear, the recommendation weight of the candidate resource needs to be improved, and if not, the resource quality of the candidate resource is determined to meet the quality requirement corresponding to the second resource gear.
And the third resource gear is an adjacent resource gear of the second resource gear, and the quality requirement corresponding to the third resource gear is higher than that corresponding to the second resource gear.
As an example, fig. 4 is an exemplary diagram providing a gear-by-gear comparison of resources according to an embodiment of the disclosure. As shown in fig. 4, resource gear positions include first gear, second gear, third gear, \8230 \ 8230;, nth gear, and among the resources at each gear, superior resources, intermediate resources, and inferior resources may be included. Taking the first gear as an example, the resource quality of the resource in the first gear can be compared with the quality requirement corresponding to the second gear, if the quality score of the resource is lower than the quality score threshold corresponding to the second gear, the resource is determined to be a low-quality resource, and the recommended weight of the resource can be reduced, so that the low-quality resource is suppressed or filtered; if the quality score of the resource is greater than the quality score threshold corresponding to the second gear, the quality score of the resource can be compared with the quality score threshold corresponding to the third gear, if the quality score of the resource is greater than the quality score threshold corresponding to the third gear, the resource is determined to be a high-quality resource, and the recommendation weight of the resource can be increased to improve the high-quality resource; and if the quality score of the resource is greater than or equal to the quality score threshold corresponding to the second gear and less than the quality score threshold corresponding to the third gear, determining that the resource is an intermediate resource, and keeping the recommendation weight of the resource unchanged.
S305, determining the target resource to be recommended according to the target recommendation weight.
The implementation principle and the technical effect of S305 may refer to the related description of the foregoing embodiments, and are not described herein again.
In the embodiment of the disclosure, the recommendation weight of the candidate resource is adjusted in a resource grading and trans-gear resource quality comparison manner, and in the adjustment process, a targeted adjustment scheme is provided based on different comparison results, so that the purposes of improving the recommendation weight corresponding to the high-quality candidate resource and reducing the recommendation weight corresponding to the low-quality candidate resource are achieved; and determining the target resource to be recommended according to the adjusted recommendation weight, and realizing the control of the resource flow of the target resource in the future, so that the probability of recommending high-quality resources is increased, the probability of recommending low-quality resources is reduced, the resource recommendation is inclined to the high-quality resources, and the resource recommendation quality is improved.
In the embodiment shown in fig. 3, in the case that the resource quality of the candidate resource is higher than the quality requirement corresponding to the second resource gear or the resource quality of the candidate resource is lower than the quality requirement corresponding to the second resource gear as a result of the comparison, the target recommendation weight needs to be determined according to the current recommendation weight of the candidate resource, and a possible implementation manner for determining the target recommendation weight according to the current recommendation weight of the candidate resource is provided by the embodiment shown in fig. 5.
Fig. 5 is a flowchart illustrating a third method for determining a resource to be recommended according to an embodiment of the present disclosure. As shown in fig. 5, the method for determining a resource to be recommended includes:
s501, candidate resources to be recommended are obtained.
And S502, determining a first resource gear where the candidate resource is located.
S503, comparing the resource quality of the candidate resource with the quality requirement corresponding to the second resource gear to obtain a comparison result, wherein the quality requirement corresponding to the second resource gear is higher than the quality requirement of the first resource gear.
The implementation principle and the technical effect of S501 to S503 can refer to the related description of the foregoing embodiments, and are not described herein again.
S504, the resource quality of the candidate resource is determined to be higher than the quality requirement corresponding to the second resource gear or the resource quality of the candidate resource is determined to be lower than the quality requirement corresponding to the second resource gear.
And S505, determining the target distribution amount of the candidate resources at the future moment according to the resource quality of the candidate resources.
The future time can be preset, the prediction time length can be preset, and the future time can be determined according to the prediction time length and the current time.
In this embodiment, when the resource quality of the candidate resource is higher than the quality requirement corresponding to the second resource gear or the resource quality of the candidate resource is lower than the quality requirement corresponding to the second resource gear as a result of the comparison, the recommendation weight of the candidate resource needs to be adjusted, that is, the target recommendation weight needs to be determined according to the current recommendation weight of the candidate resource. In this process, a target distribution amount of the candidate resource at a future time may be determined first according to the resource quality of the candidate resource.
In one possible implementation, the traffic requirement corresponding to the resource gear includes a distribution threshold corresponding to the resource gear, and based on this, S505 may include: predicting the distribution amount of the candidate resources to obtain the predicted distribution amount of the candidate resources at a future moment; determining a target gear which is satisfied by the resource quality of the candidate resource in a plurality of resource gears; and determining the target distribution amount of the candidate resources at the future moment according to the distribution amount threshold value corresponding to the target gear and the predicted distribution amount.
In the implementation mode, the distribution amount of the candidate resources can be predicted through the distribution amount prediction model, and the predicted distribution amount which accords with the distribution rule of the candidate resources and has higher accuracy is obtained. Since the low-quality resources may have a large distribution amount, only by using the distribution amount prediction, a large predicted distribution amount may be predicted for the low-quality resources. To avoid such unreasonable situation, the predicted distribution amount can be constrained by the resource quality of the candidate resource, and a more reasonable target distribution amount is obtained: firstly, the resource quality of the candidate resource can be compared with the quality requirements corresponding to a plurality of resource gears, and the resource gear corresponding to the quality requirement met by the resource quality of the candidate resource is determined, namely the target gear is determined; considering that the resource quality of the candidate resources meets the target gear, the predicted distribution amount can be adjusted based on the distribution amount threshold corresponding to the target gear, so as to obtain the target distribution amount of the candidate resources at a future moment.
Therefore, the predicted distribution amount with higher accuracy is obtained in a distribution amount prediction mode; and based on the target gear met by the resource quality of the candidate resources, the predicted distribution amount is constrained to obtain the target distribution amount of the candidate resources at the future moment, so that the rationality of the target distribution amount is improved. In general, the accuracy and the rationality of the target distribution amount are improved.
Further, the distribution prediction model may be a time series model. Predicting the distribution amount of the candidate resource to obtain the predicted distribution amount of the candidate resource at a future moment, wherein the predicting the distribution amount of the candidate resource at the future moment comprises the following steps: and predicting the distribution quantity of the candidate resources according to the historical distribution quantity of the candidate resources at the historical moment and the time sequence model to obtain the predicted distribution quantity of the candidate resources at the future moment. Therefore, by utilizing the historical distribution amount and the time sequence model, the accuracy of distribution amount prediction is improved, and the accuracy of the predicted distribution amount is improved.
The time sequence model can be a neural network model or a fitting model obtained through a mathematical fitting mode. When the time sequence model is a neural network model, the time sequence model needs to be trained in advance, and then the predicted distribution amount of the candidate resources at the future moment is predicted through the trained time sequence model.
The number of the historical time can be multiple, and the distribution quantity of the candidate resources can be predicted according to the historical distribution quantity of the candidate resources at each historical time and the time sequence model. The historical distribution amount of the candidate resources at each historical moment can reflect the distribution amount development rule of the candidate resources, so that the predicted distribution amount of the candidate resources at the future moment also accords with the distribution amount development rule, and the accuracy is high.
In the process of determining the target distribution amount of the candidate resource at a future moment according to the distribution amount threshold corresponding to the target gear and the predicted distribution amount, a possible implementation manner is that if the predicted distribution amount is greater than or equal to the distribution amount threshold corresponding to the target gear, the target distribution amount is determined to be the distribution amount threshold corresponding to the target gear; and if the predicted distribution amount is smaller than the distribution amount threshold corresponding to the target gear, determining the target distribution amount as the predicted distribution amount. Therefore, the target distribution amount of the candidate resources at the future moment is limited within the distribution amount threshold value corresponding to the resource gear met by the resource quality of the candidate resources, the rationality of the target distribution amount is improved, and the candidate resources are prevented from reaching the distribution amount inconsistent with the quality of the candidate resources.
For example, in the plurality of resource bays, the threshold value of the dispensed amount corresponding to the first bay is 1 ten thousand, the threshold value of the dispensed amount corresponding to the second bay is 5 ten thousand, the threshold value of the dispensed amount corresponding to the third bay is 10 ten thousand, and the threshold value of the dispensed amount corresponding to the fourth bay is 50 ten thousand. And comparing the resource quality of the candidate resources with the quality requirements corresponding to each resource gear, and finding that the resource quality of the candidate resources reaches the third gear at most. The predicted distribution amount of the candidate resource at the future time may exceed the distribution amount threshold corresponding to the third gear by 10 ten thousand, so the predicted distribution amount is limited, and the obtained target distribution amount is 10 ten thousand.
In addition to the above manner, the predicted dispensing amount of the candidate resource at the future time may be increased or decreased by a preset value based on the dispensing amount threshold corresponding to the target gear, so as to obtain the target dispensing amount of the candidate resource at the future time. The distribution amount can also be predicted without adopting a distribution amount prediction model, and the target distribution amount of the candidate resource at the future time is directly determined to be the distribution amount threshold corresponding to the target gear, but the mode is rough, the distribution user range is expanded, and a plurality of ineffective distributions are generated. For example, if the resource quality of the candidate resource reaches the fourth gear, if the prediction is not performed, the target distribution amount of the candidate resource at the future time is determined according to the distribution amount threshold value 50 ten thousand corresponding to the fourth gear, and if the prediction is performed, the predicted distribution amount of the candidate resource at the future time may be predicted to be 20 ten thousand, and the target distribution amount is determined to be 20 ten thousand.
S506, determining the resource distribution speed of the candidate resource according to the difference between the target distribution amount and the current distribution amount of the candidate resource.
Here, the resource distribution rate refers to a rate at which the candidate resource is distributed to the user, and may be understood as a rate at which the distribution amount of the candidate resource increases. The greater the resource distribution speed of the candidate resource, the more frequently and more likely the candidate resource should be recommended to the user.
In this embodiment, the target distribution amount of the candidate resource at the future time may be compared with the current distribution amount of the candidate resource to obtain a difference between the target distribution amount and the current distribution amount; then, the resource distribution speed of the candidate resource can be determined according to the difference between the target distribution amount and the current distribution amount, the current time and the future time. For example, the resource distribution speed of the candidate resource is obtained by dividing the difference by the time difference between the current time and the future time.
In one possible implementation, S506 includes: determining a difference between a target distribution amount of the candidate resource at a future moment and a current distribution amount of the candidate resource; and determining the resource distribution speed of the candidate resource through a proportional-integral-derivative (PID) controller according to the difference value. Therefore, the accuracy of the resource distribution speed is improved by using the PID controller.
Wherein, the principle formula of the PID controller can be expressed as:
Figure BDA0003939486820000151
err (t) = rin (t) -rout (t)
Discretizing U (t) yields:
U(t)＝K p err(t)+K i ∑err(t)+K d (err(t)-err(t-1))
u (t) and a resource distribution speed representing the candidate resource, wherein t represents a future time, rin (t) represents a target distribution amount of the candidate resource at the future time, rout (t) identifies a current distribution amount of the candidate resource, and err (t) represents a distribution amount between the target distribution amount and the current distribution amountDifference, T 1 Denotes the integration time constant, T D Denotes the differential time constant, K p Is the proportionality coefficient, K i Is the integral coefficient, K d Are differential coefficients, all of which are hyper-parameters. Therefore, what remains to be calculated in the formula is err (t), which can be determined by the target distribution amount and the current-time distribution amount. Therefore, through the PID algorithm, the resource flow can be accurately regulated and controlled on the basis of the resource quality and the resource gear where the resource is located.
S507, determining a target recommendation weight according to the current recommendation weight of the candidate resource and the resource distribution speed of the candidate resource.
In this embodiment, the current recommendation weight of the candidate resource may be increased or decreased based on the resource distribution speed to obtain the target recommendation weight.
In one possible implementation, the resource distribution speed may be multiplied by the current recommendation weight of the candidate resource to obtain the target recommendation weight. And under the condition that the resource distribution speed is greater than 1, increasing the recommendation weight of the candidate resource is realized, and under the condition that the resource distribution speed is less than 1, reducing the recommendation weight of the candidate resource is realized. Therefore, the recommendation weight of the candidate resource is accurately adjusted through the resource distribution speed, and the rationality of the recommendation weight is improved.
And S508, determining target resources to be recommended according to the target recommendation weight.
The implementation principle and the technical effect of S508 may refer to the corresponding description of the foregoing embodiments, and are not described herein again.
In the embodiment of the disclosure, the recommendation weight of the candidate resource is adjusted by resource grading and cross-gear resource quality comparison, in the adjustment process, the resource distribution speed of the candidate resource is determined by combining the resource quality of the candidate resource, the recommendation weight of the candidate resource is adjusted based on the resource distribution speed, the accuracy and rationality of the recommendation weight adjustment are improved, the accurate control of the resource flow of the target resource in the future is realized, the recommendation probability of the high-quality resource is increased, the recommendation probability of the low-quality resource is reduced, the resource recommendation is inclined to the high-quality resource, and the resource recommendation quality is improved.
Fig. 6 is a first schematic structural diagram of a device for determining resources to be recommended according to an embodiment of the present disclosure. As shown in fig. 6, the apparatus 600 for determining a resource to be recommended includes:
a resource obtaining unit 601, configured to obtain a candidate resource to be recommended;
a gear determining unit 602, configured to determine a first resource gear in which the candidate resource is located;
a quality comparing unit 603, configured to compare the resource quality of the candidate resource with a quality requirement corresponding to the second resource gear to obtain a comparison result, where the quality requirement corresponding to the second resource gear is higher than the quality requirement of the first resource gear;
a weight adjusting unit 604, configured to adjust the recommendation weights of the candidate resources according to the comparison result, so as to obtain a target recommendation weight;
a resource determining unit 605, configured to determine a target resource to be recommended according to the target recommendation weight.
Fig. 7 is a schematic structural diagram of a device for determining resources to be recommended according to an embodiment of the present disclosure. As shown in fig. 7, the apparatus 700 for determining a resource to be recommended includes:
a resource obtaining unit 701, configured to obtain a candidate resource to be recommended;
a gear determining unit 702, configured to determine a first resource gear in which the candidate resource is located;
a quality comparing unit 703, configured to compare the resource quality of the candidate resource with a quality requirement corresponding to the second resource gear, to obtain a comparison result, where the quality requirement corresponding to the second resource gear is higher than the quality requirement of the first resource gear;
a weight adjusting unit 704, configured to adjust the recommendation weights of the candidate resources according to the comparison result, so as to obtain a target recommendation weight;
the resource determining unit 705 is configured to determine a target resource to be recommended according to the target recommendation weight.
In some embodiments, the weight adjusting unit 704 includes: a first weight determining module 7041, configured to determine the target recommendation weight as a first weight if the comparison result indicates that the resource quality of the candidate resource meets the quality requirement corresponding to the second resource gear, where the first weight is a current recommendation weight of the candidate resource; a second weight determining module 7042, configured to determine, according to the current recommendation weight, the target recommendation weight as a second weight if the comparison result is that the resource quality of the candidate resource is higher than the quality requirement corresponding to the second resource gear, where the second weight is greater than the current recommendation weight; a third weight determining module 7043, configured to determine, according to the current recommendation weight, that the target recommendation weight is a third weight if the comparison result is that the resource quality of the candidate resource is lower than the quality requirement corresponding to the second resource gear, where the third weight is smaller than the current recommendation weight.
In some embodiments, the second weight determination module 7042 and/or the third weight determination module 7043 comprises: a distribution prediction sub-module (not shown in the figure) for determining a target distribution of the candidate resource at a future time according to the resource quality of the candidate resource; a distribution speed determination sub-module (not shown in the figure) for determining a resource distribution speed of the candidate resource according to a difference between the target distribution amount and the current distribution amount of the candidate resource; and a weight determination submodule (not shown in the figure) for determining the target recommendation weight according to the current recommendation weight and the resource distribution speed.
In some embodiments, the distribution prediction sub-module is specifically configured to: predicting the distribution amount of the candidate resources to obtain the predicted distribution amount of the candidate resources at a future moment; determining a target gear which is satisfied by the resource quality of the candidate resource in a plurality of resource gears; and determining the target distribution amount according to the distribution amount threshold value corresponding to the target gear and the predicted distribution amount.
In some embodiments, in the process of predicting the distribution amount of the candidate resource to obtain the predicted distribution amount of the candidate resource at a future time, the distribution amount prediction sub-module is specifically configured to: and predicting the distribution quantity of the candidate resources according to the historical distribution quantity of the candidate resources at the historical moment and the time sequence model to obtain the predicted distribution quantity.
In some embodiments, in the process of determining the target dispensing amount according to the dispensing amount threshold corresponding to the target gear and the predicted dispensing amount, the dispensing amount prediction sub-module is specifically configured to: if the predicted distribution amount is larger than or equal to the distribution amount threshold value, determining the target distribution amount as the distribution amount threshold value; and if the predicted distribution amount is smaller than the distribution amount threshold value, determining the target distribution amount as the predicted distribution amount.
In some embodiments, the distribution speed determination submodule is specifically configured to: determining a difference between the target distribution amount and the current distribution amount; and determining the resource distribution speed through the PID controller according to the difference value.
In some embodiments, gear determination unit 702 comprises: a resource statistic obtaining module 7021, configured to obtain resource statistics of the candidate resources, where the resource statistics include current display amounts of the candidate resources and/or current distribution amounts of the candidate resources; the gear determining module 7022 is configured to determine a first resource gear among the multiple resource gears according to the resource statistics and the statistics requirements corresponding to the multiple resource gears, respectively.
The determination apparatus for resources to be recommended provided in fig. 6 to 7 may execute the corresponding method embodiment, and the implementation principle and the technical effect are similar, which are not described herein again.
According to an embodiment of the present disclosure, the present disclosure also provides an electronic device including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executable by the at least one processor to enable the at least one processor to perform the aspects provided by any of the embodiments described above.
According to an embodiment of the present disclosure, there is also provided a non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the solution provided by any of the above embodiments.
According to an embodiment of the present disclosure, the present disclosure also provides a computer program product comprising: a computer program, stored in a readable storage medium, from which at least one processor of the electronic device can read the computer program, the at least one processor executing the computer program causing the electronic device to perform the solution provided by any of the embodiments described above.
Fig. 8 is a schematic block diagram of an example electronic device 800 that may be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic devices may also represent various forms of mobile devices, such as personal digital processors, cellular telephones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not intended to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 8, the electronic device 800 includes a computing unit 801 that can perform various appropriate actions and processes in accordance with a computer program stored in a Read Only Memory (ROM), such as ROM 802, or loaded from a storage unit 808 into a Random Access Memory (RAM), such as RAM 803. In the RAM 803, various programs and data required for the operation of the electronic apparatus 800 can also be stored. The calculation unit 801, the ROM 802, and the RAM 803 are connected to each other by a bus 804. An input/output (I/O) interface (e.g., I/O interface 805) is also connected to bus 804.
A number of components in the electronic device 800 are connected to the I/O interface 805, including: an input unit 806 such as a keyboard, a mouse, or the like; an output unit 807 such as various types of displays, speakers, and the like; a storage unit 808, such as a magnetic disk, optical disk, or the like; and a communication unit 809 such as a network card, modem, wireless communication transceiver, etc. The communication unit 809 allows the electronic device 800 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.
Computing unit 801 may be a variety of general and/or special purpose processing components with processing and computing capabilities. Some examples of the computing Unit 801 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and the like. The calculation unit 801 executes the respective methods and processes described above, such as the determination method of the resource to be recommended. For example, in some embodiments, the method of determining a resource to be recommended may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 808. In some embodiments, part or all of the computer program can be loaded and/or installed onto the electronic device 800 via the ROM 802 and/or the communication unit 809. When the computer program is loaded into the RAM 803 and executed by the computing unit 801, one or more steps of the above-described method for determining a resource to be recommended may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to perform the determination method of the resource to be recommended by any other suitable means (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be realized in digital electronic circuitry, integrated circuitry, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Parts (ASSPs), system On a Chip (SOC), complex Programmable Logic Devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, 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 Compact Disc Read-Only Memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the internet.
The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The Server may be a cloud Server, also called a cloud computing Server or a cloud host, and is a host product in a cloud computing service system, so as to solve the defects of high management difficulty and weak service extensibility in a traditional physical host and VPS service ("Virtual Private Server", or "VPS" for short). The server may also be a server of a distributed system, or a server incorporating a blockchain.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be executed in parallel, sequentially or in different orders, and are not limited herein as long as the desired results of the technical aspects of the present disclosure can be achieved.
The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the protection scope of the present disclosure.

Claims (19)

1. A method for determining resources to be recommended comprises the following steps:
acquiring candidate resources to be recommended;
determining a first resource gear where the candidate resource is located;
comparing the resource quality of the candidate resource with a quality requirement corresponding to a second resource gear to obtain a comparison result, wherein the quality requirement corresponding to the second resource gear is higher than the quality requirement of the first resource gear;
according to the comparison result, the recommendation weight of the candidate resource is adjusted to obtain a target recommendation weight;
and determining the target resource to be recommended according to the target recommendation weight.
2. The determination method according to claim 1, wherein the adjusting the recommendation weight of the candidate resource according to the comparison result to obtain a target recommendation weight comprises:
if the comparison result is that the resource quality of the candidate resource meets the quality requirement corresponding to the second resource gear, determining that the target recommendation weight is a first weight, and the first weight is the current recommendation weight of the candidate resource;
if the comparison result is that the resource quality of the candidate resource is higher than the quality requirement corresponding to the second resource gear, determining the target recommendation weight as a second weight according to the current recommendation weight, wherein the second weight is larger than the current recommendation weight;
and if the comparison result is that the resource quality of the candidate resource is lower than the quality requirement corresponding to the second resource gear, determining the target recommendation weight as a third weight according to the current recommendation weight, wherein the third weight is smaller than the current recommendation weight.
3. The determination method of claim 2, wherein determining the target recommendation weight in accordance with the current recommendation weight comprises:
determining the target distribution amount of the candidate resources at the future moment according to the resource quality of the candidate resources;
determining the resource distribution speed of the candidate resource according to the difference between the target distribution amount and the current distribution amount of the candidate resource;
and determining the target recommendation weight according to the current recommendation weight and the resource distribution speed.
4. The determination method according to claim 3, wherein the determining the target distribution amount of the candidate resource at the future time according to the resource quality of the candidate resource comprises:
predicting the distribution amount of the candidate resources to obtain the predicted distribution amount of the candidate resources at the future moment;
determining a target gear which is satisfied by the resource quality of the candidate resource in a plurality of resource gears;
and determining the target distribution amount according to the distribution amount threshold corresponding to the target gear and the predicted distribution amount.
5. The determination method according to claim 4, wherein the predicting the distribution amount of the candidate resource to obtain the predicted distribution amount of the candidate resource at a future time comprises:
and predicting the distribution quantity of the candidate resources according to the historical distribution quantity of the candidate resources at the historical moment and the time sequence model to obtain the predicted distribution quantity.
6. The determination method according to claim 4, wherein the determining the target distribution amount according to the distribution amount threshold corresponding to the target gear and the predicted distribution amount comprises:
determining the target dispatch volume to be the dispatch volume threshold if the predicted dispatch volume is greater than or equal to the dispatch volume threshold;
determining the target distribution amount to be the predicted distribution amount if the predicted distribution amount is less than the distribution amount threshold.
7. The determination method according to claim 3, wherein the determining the resource distribution speed of the candidate resource according to the difference between the target distribution amount and the current distribution amount of the candidate resource comprises:
determining a difference between the target distribution amount and the current distribution amount;
and determining the resource distribution speed through a PID controller according to the difference value.
8. The method of any one of claims 1-7, wherein the determining the first resource gear in which the candidate resource is located comprises:
acquiring resource statistics of candidate resources, wherein the resource statistics comprise current display quantity of the candidate resources and/or current distribution quantity of the candidate resources;
and determining the first resource gear in a plurality of resource gears according to the resource statistics and the statistics requirements corresponding to the resource gears respectively.
9. An apparatus for determining a resource to be recommended, comprising:
the resource acquisition unit is used for acquiring candidate resources to be recommended;
the gear determining unit is used for determining a first resource gear in which the candidate resource is positioned;
the quality comparison unit is used for comparing the resource quality of the candidate resource with a quality requirement corresponding to a second resource gear to obtain a comparison result, wherein the quality requirement corresponding to the second resource gear is higher than the quality requirement of the first resource gear;
the weight adjusting unit is used for adjusting the recommendation weight of the candidate resource according to the comparison result to obtain a target recommendation weight;
and the resource determining unit is used for determining the target resource to be recommended according to the target recommendation weight.
10. The determination apparatus according to claim 9, wherein the weight adjustment unit includes:
a first weight determination module, configured to determine that the target recommendation weight is a first weight if the comparison result indicates that the resource quality of the candidate resource meets the quality requirement corresponding to the second resource gear, where the first weight is a current recommendation weight of the candidate resource;
a second weight determining module, configured to determine, according to the current recommendation weight, that the target recommendation weight is a second weight if the comparison result indicates that the resource quality of the candidate resource is higher than a quality requirement corresponding to the second resource gear, where the second weight is greater than the current recommendation weight;
a third weight determining module, configured to determine, according to the current recommendation weight, that the target recommendation weight is a third weight if the comparison result indicates that the resource quality of the candidate resource is lower than the quality requirement corresponding to the second resource gear, where the third weight is smaller than the current recommendation weight.
11. The determination apparatus according to claim 10, wherein the second weight determination module and/or the third weight determination module comprises:
the distribution quantity prediction submodule is used for determining the target distribution quantity of the candidate resources at a future moment according to the resource quality of the candidate resources;
the distribution speed determining submodule is used for determining the resource distribution speed of the candidate resource according to the difference between the target distribution amount and the current distribution amount of the candidate resource;
and the weight determining submodule is used for determining the target recommendation weight according to the current recommendation weight and the resource distribution speed.
12. The determination apparatus according to claim 11, wherein the distribution amount prediction sub-module is specifically configured to:
predicting the distribution amount of the candidate resources to obtain the predicted distribution amount of the candidate resources at a future moment;
determining a target gear which is satisfied by the resource quality of the candidate resource in a plurality of resource gears;
and determining the target distribution amount according to the distribution amount threshold corresponding to the target gear and the predicted distribution amount.
13. The apparatus according to claim 12, wherein in the process of predicting the distribution amount of the candidate resource to obtain the predicted distribution amount of the candidate resource at a future time, the distribution amount predicting sub-module is specifically configured to:
and predicting the distribution amount of the candidate resources according to the historical distribution amount and the time sequence model of the candidate resources at the historical moment to obtain the predicted distribution amount.
14. The determining apparatus according to claim 12, wherein, in the process of determining the target distribution amount according to the distribution amount threshold corresponding to the target gear and the predicted distribution amount, the distribution amount prediction sub-module is specifically configured to:
determining the target dispatch volume to be the dispatch volume threshold if the predicted dispatch volume is greater than or equal to the dispatch volume threshold;
determining the target distribution amount to be the predicted distribution amount if the predicted distribution amount is less than the distribution amount threshold.
15. The determination apparatus according to claim 11, wherein the distribution speed determination submodule is specifically configured to:
determining a difference between the target distribution amount and the current distribution amount;
and determining the resource distribution speed through a PID controller according to the difference value.
16. The determination device according to any one of claims 9 to 15, wherein the gear position determination unit includes:
a resource statistic obtaining module, configured to obtain resource statistics of candidate resources, where the resource statistics include current display amounts of the candidate resources and/or current distribution amounts of the candidate resources;
and the gear determining module is used for determining the first resource gear in a plurality of resource gears according to the resource statistics and the statistics requirements corresponding to the resource gears respectively.
17. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of determining resources to be recommended of any one of claims 1-8.
18. A non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute the method for determining a resource to be recommended according to any one of claims 1 to 8.
19. A computer program product comprising a computer program which, when being executed by a processor, carries out the steps of the method for determining a resource to be recommended according to any one of claims 1 to 8.
CN202211413067.9A 2022-11-11 2022-11-11 Method, device and equipment for determining resources to be recommended and storage medium Pending CN115795146A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211413067.9A CN115795146A (en) 2022-11-11 2022-11-11 Method, device and equipment for determining resources to be recommended and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211413067.9A CN115795146A (en) 2022-11-11 2022-11-11 Method, device and equipment for determining resources to be recommended and storage medium

Publications (1)

Publication Number Publication Date
CN115795146A true CN115795146A (en) 2023-03-14

Family

ID=85437037

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211413067.9A Pending CN115795146A (en) 2022-11-11 2022-11-11 Method, device and equipment for determining resources to be recommended and storage medium

Country Status (1)

Country Link
CN (1) CN115795146A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116719992A (en) * 2023-05-26 2023-09-08 百度(中国)有限公司 Resource recommendation method and device, electronic equipment and storage medium

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116719992A (en) * 2023-05-26 2023-09-08 百度(中国)有限公司 Resource recommendation method and device, electronic equipment and storage medium

Similar Documents

Publication Publication Date Title
CN112749344B (en) Information recommendation method, device, electronic equipment, storage medium and program product
CN110704739A (en) Resource recommendation method and device and computer storage medium
JP7208595B2 (en) Movie Success Index Prediction
CN114036398B (en) Content recommendation and ranking model training method, device, equipment and storage medium
JP2022033695A (en) Method, device for generating model, electronic apparatus, storage medium and computer program product
CN111460384B (en) Policy evaluation method, device and equipment
US11449662B2 (en) Automatic generation of layout variations based on visual flow
CN115795146A (en) Method, device and equipment for determining resources to be recommended and storage medium
CN114065864A (en) Federal learning method, federal learning device, electronic device, and storage medium
CN112561167B (en) Travel recommendation method and device, electronic equipment and storage medium
CN113657759A (en) Task processing method, device, equipment and storage medium
CN113791882A (en) Multitask deployment method and device, electronic equipment and storage medium
CN113516185A (en) Model training method and device, electronic equipment and storage medium
CN116737906A (en) Information display method, device, electronic equipment and storage medium
CN113761379B (en) Commodity recommendation method and device, electronic equipment and medium
CN113010782B (en) Demand acquisition method, device, electronic equipment and computer readable medium
CN115482116A (en) Asset investment strategy information recommendation method, device, equipment and medium
CN115185606A (en) Method, device, equipment and storage medium for obtaining service configuration parameters
CN113112311B (en) Method for training causal inference model and information prompting method and device
CN115186749A (en) Data identification method, device, equipment and storage medium
CN115203564A (en) Information flow recommendation method and device and computer program product
CN113987260A (en) Video pushing method and device, electronic equipment and storage medium
CN113326436A (en) Method and device for determining recommended resources, electronic equipment and storage medium
CN113365148B (en) Score adjustment method, score adjustment device, electronic device, storage medium, and program product
CN116188063A (en) Guest group creation method, apparatus, device and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination