CN112380388B - Video ordering method and device under search scene, electronic equipment and storage medium - Google Patents
Video ordering method and device under search scene, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN112380388B CN112380388B CN202011261872.5A CN202011261872A CN112380388B CN 112380388 B CN112380388 B CN 112380388B CN 202011261872 A CN202011261872 A CN 202011261872A CN 112380388 B CN112380388 B CN 112380388B
- Authority
- CN
- China
- Prior art keywords
- video
- feature
- ordering
- target
- target video
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 239000013598 vector Substances 0.000 claims abstract description 48
- 238000012163 sequencing technique Methods 0.000 claims abstract description 5
- 238000012545 processing Methods 0.000 claims description 22
- 238000010606 normalization Methods 0.000 claims description 15
- 238000004891 communication Methods 0.000 description 10
- 238000004590 computer program Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 230000005236 sound signal Effects 0.000 description 4
- 230000003993 interaction Effects 0.000 description 3
- 238000013507 mapping Methods 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 2
- 238000007796 conventional method Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 235000017166 Bambusa arundinacea Nutrition 0.000 description 1
- 235000017491 Bambusa tulda Nutrition 0.000 description 1
- 241001330002 Bambuseae Species 0.000 description 1
- 235000015334 Phyllostachys viridis Nutrition 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 239000011425 bamboo Substances 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 239000000969 carrier Substances 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000005755 formation reaction Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/73—Querying
- G06F16/735—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/73—Querying
- G06F16/738—Presentation of query results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/74—Browsing; Visualisation therefor
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The disclosure relates to a video ordering method, device, electronic equipment and storage medium in a search scene. The video ordering method under the search scene comprises the following steps: acquiring a target video set; wherein the target videos in the target video set comprise at least one first target video and at least one second target video; acquiring a first ordering feature corresponding to a first target video; weighting the first ordering feature according to a weight vector in a preset feature weight set to obtain a second ordering feature corresponding to a second target video; according to the first ordering feature and the second ordering feature, ordering the target videos in the target video set to obtain an ordering result; and displaying the target videos in the target video set according to the sequencing result. Therefore, the second ordering feature corresponding to the second target video can be obtained according to the first ordering feature corresponding to the first target video, and the purposes of ordering and displaying the target videos in the target video set are achieved according to the first ordering feature and the second ordering feature.
Description
Technical Field
The disclosure relates to the technical field of video processing, and in particular relates to a video ordering method, device, electronic equipment and storage medium under a search scene.
Background
With rapid progress of modern information transmission technology and popularization of video receiving devices such as smart phones, video gradually becomes one of main carriers for people to receive information daily, and various video platforms emerge like spring bamboo shoots after raining. In video platforms, it is often desirable to present videos corresponding to search terms to a user in accordance with the search terms entered by the user. When displaying videos corresponding to search words to users, a plurality of recalled videos related to the search words are generally required to be arranged and displayed according to a certain sequence, so that the users can conveniently and rapidly complete searching, and the desired video content is obtained. Conventional video ranking methods typically rank a plurality of videos related to search terms according to ranking features (or playing features, such as exposure, number of clicks, click rate, praise rate, attention rate, or finish rate, etc.) of the videos, and display the ranked videos to a user.
However, when the video is ordered and displayed by adopting the conventional method, the ordering features of the video are needed, and when the corresponding ordering features do not exist in part of the videos to be displayed, the ordering features are incomplete or the ordering features are not available, the video cannot be ordered and displayed by adopting the conventional method.
Disclosure of Invention
The disclosure provides a video ordering method, device, electronic equipment and storage medium in a search scene, so as to at least solve the problem that videos cannot be ordered and displayed in the related art. The technical scheme of the present disclosure is as follows:
according to a first aspect of an embodiment of the present disclosure, there is provided a video ordering method under a search scene, including:
acquiring a target video set; wherein the target videos in the target video set comprise at least one first target video and at least one second target video;
acquiring a first ordering feature corresponding to the first target video;
weighting the first ordering feature according to a weight vector in a preset feature weight set to obtain a second ordering feature corresponding to the second target video;
sorting the target videos in the target video set according to the first sorting feature and the second sorting feature to obtain a sorting result;
and displaying the target videos in the target video set according to the sequencing result.
In an exemplary embodiment, each of the first target videos corresponds to a first video feature, and each of the second target videos corresponds to a second video feature;
The obtaining mode of the characteristic weight set comprises the following steps:
and determining a weight vector of the second target video relative to the first target video according to the association relation between the first video feature and the second video feature, so as to obtain the feature weight set.
In an exemplary embodiment, the determining, according to the association between the first video feature and the second video feature, a weight vector of the second target video relative to the first target video, to obtain the feature weight set includes:
determining the similarity between each second video feature and each first video feature to obtain a similarity set;
and carrying out normalization processing on the similarity in the similarity set, and determining a weight vector of the second target video relative to the first target video to obtain the characteristic weight set.
In an exemplary embodiment, the normalizing the similarity in the similarity set, determining a weight vector of the second target video relative to the first target video, to obtain the feature weight set, includes:
normalizing the similarity in the similarity set, and determining the generalization weight of the second target video relative to the first target video to obtain a generalization weight set;
And carrying out normalization processing on the generalized weights in the generalized weight set, determining a weight vector of the second target video relative to the first target video, and obtaining the characteristic weight set.
In an exemplary embodiment, the method for acquiring the first video feature or the second video feature includes:
inputting the first target video into a preset Embedding model to obtain the first video feature;
or, inputting the second target video into the Embedding model to obtain the second video feature.
In an exemplary embodiment, the method for obtaining the target video set includes:
acquiring a target search word;
and acquiring videos related to the target search word to obtain the target video set.
In an exemplary embodiment, the sorting the target videos in the target video set according to the first sorting feature and the second sorting feature to obtain a sorting result includes:
inputting the first ordering feature and the second ordering feature into a preset video ordering model, ordering the first target video corresponding to the first ordering feature and the second target video corresponding to the second ordering feature, and outputting the ordering result.
According to a second aspect of embodiments of the present disclosure, there is provided a video ordering apparatus in a search scene, including:
a video set acquisition unit configured to perform acquisition of a target video set; wherein the target videos in the target video set comprise at least one first target video and at least one second target video;
a first ranking feature acquiring unit configured to perform acquisition of a first ranking feature corresponding to the first target video;
the second ordering feature determining unit is configured to perform weighting on the first ordering feature according to a weight vector in a preset feature weight set to obtain a second ordering feature corresponding to the second target video;
a video ordering unit configured to perform ordering of the target videos in the target video set according to the first ordering feature and the second ordering feature, so as to obtain an ordering result;
and the video display unit is configured to display the target videos in the target video set according to the sorting result.
In an exemplary embodiment, each of the first target videos corresponds to a first video feature, and each of the second target videos corresponds to a second video feature;
The second ranking features determining unit is further configured to perform:
and determining a weight vector of the second target video relative to the first target video according to the association relation between the first video feature and the second video feature, so as to obtain the feature weight set.
In an exemplary embodiment, the second ranking features determining unit is further configured to perform:
determining the similarity between each second video feature and each first video feature to obtain a similarity set;
and carrying out normalization processing on the similarity in the similarity set, and determining a weight vector of the second target video relative to the first target video to obtain the characteristic weight set.
In an exemplary embodiment, the second ranking features determining unit is further configured to perform:
normalizing the similarity in the similarity set, and determining the generalization weight of the second target video relative to the first target video to obtain a generalization weight set;
and carrying out normalization processing on the generalized weights in the generalized weight set, determining a weight vector of the second target video relative to the first target video, and obtaining the characteristic weight set.
In an exemplary embodiment, the second ranking features determining unit is further configured to perform:
inputting the first target video into a preset Embedding model to obtain the first video feature;
or, inputting the second target video into the Embedding model to obtain the second video feature.
In an exemplary embodiment, the video set acquisition unit is further configured to perform:
acquiring a target search word;
and acquiring videos related to the target search word to obtain the target video set.
In an exemplary embodiment, the video ordering unit is further configured to perform:
inputting the first ordering feature and the second ordering feature into a preset video ordering model, ordering the first target video corresponding to the first ordering feature and the second target video corresponding to the second ordering feature, and outputting the ordering result.
According to a third aspect of embodiments of the present disclosure, there is provided an electronic device, comprising:
a processor;
a memory for storing the processor-executable instructions;
wherein the processor is configured to execute the instructions to implement the video ordering method in the search scenario of any one of the above first aspects.
According to a fourth aspect of embodiments of the present disclosure, there is provided a storage medium, which when executed by a processor of an electronic device, enables the electronic device to perform the video ordering method in the search scenario of any one of the above-described first aspects.
According to a fifth aspect of embodiments 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 a device reads and executes the computer program, causing the device to perform the video ordering method under the search scenario set forth in any one of the embodiments of the first aspect.
The technical scheme provided by the embodiment of the disclosure at least brings the following beneficial effects:
and weighting the first ordering feature corresponding to each first target video according to a weight vector in a preset feature weight set to obtain a second ordering feature corresponding to a second target video. Therefore, when the second target video does not have the corresponding ordering feature, the ordering feature is incomplete or the ordering feature is unavailable, the second ordering feature corresponding to the second target video can be obtained according to the first ordering feature corresponding to the first target video. According to the first ordering feature and the second ordering feature, ordering the target videos in the target video set to obtain an ordering result, and displaying the target videos in the target video set according to the ordering result. Therefore, when the corresponding ordering feature does not exist in part of videos in the target video set, the ordering feature is incomplete or the ordering feature is unavailable, the second ordering feature corresponding to the second target video can be obtained according to the first ordering feature corresponding to the first target video, and the purposes of ordering and displaying the target videos in the target video set are achieved according to the first ordering feature and the second ordering feature.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure and do not constitute an undue limitation on the disclosure.
Fig. 1 is a flowchart illustrating a video ordering method in a search scenario, according to an example embodiment.
FIG. 2 is a flow chart illustrating a manner of acquisition of a feature weight set according to an exemplary embodiment.
Fig. 3 is a flow chart illustrating one possible implementation of step S320 according to an exemplary embodiment.
Fig. 4 is a block diagram illustrating a video ordering apparatus in a search scenario according to an example embodiment.
FIG. 5 is a block diagram of an electronic device for video ordering in a search scene, according to an example embodiment.
Detailed Description
In order to enable those skilled in the art to better understand the technical solutions of the present disclosure, the technical solutions of the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.
It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the foregoing figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the disclosure described herein may be capable of operation in sequences other than those illustrated or described herein. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present disclosure as detailed in the accompanying claims.
Fig. 1 is a flowchart illustrating a video ranking method in a search scenario according to an exemplary embodiment, where the method is applied to an electronic device for illustration, it is to be understood that the method may also be applied to a server, and may also be applied to a system including a terminal and a server, and implemented through interaction between the terminal and the server. In this embodiment, the method includes the steps of:
in step S100, a target video set is acquired; wherein the target videos in the target video set comprise at least one first target video and at least one second target video.
In step S200, a first ranking feature corresponding to a first target video is obtained.
In step S300, the first ranking features are weighted according to the weight vectors in the preset feature weight set, so as to obtain second ranking features corresponding to the second target video.
In step S400, the target videos in the target video set are ranked according to the first ranking feature and the second ranking feature, so as to obtain a ranking result.
In step S500, according to the sorting result, the target videos in the target video set are displayed.
Wherein the target video set is the set of video formations that need to be ordered and presented. The feature weight set is a set formed by weight vectors of the second target video relative to the first target video, and the first ordering feature can be mapped to a second ordering feature corresponding to the second target video through the weight vectors in the feature weight set.
Specifically, a target video set formed by videos to be sequenced and displayed is obtained, wherein the target videos in the target video set comprise at least one first target video and at least one second target video. And then, acquiring a first ordering feature corresponding to the first target video, weighting the first ordering feature according to a weight vector in a preset feature weight set to obtain an ordering feature reconstructed based on the first ordering feature and the weight vector, determining the ordering feature as a second ordering feature corresponding to the second target video, and representing the ordering feature of the second target video by using the ordering feature of the first target video. Therefore, when the second target video does not have the corresponding ordering feature, the ordering feature is incomplete or the ordering feature is unavailable, the second ordering feature corresponding to the second target video can be obtained according to the first ordering feature corresponding to the first target video. And sorting the target videos in the target video set according to the first sorting feature and the second sorting feature to obtain a sorting result. And displaying the target videos in the target video set according to the sequencing result.
For example, when there are 10 target videos in one target video set to be sorted and presented, 8 target videos (first target video) in the 10 target videos have corresponding play amounts, 2 target videos (second target video) in the 10 target videos do not have corresponding play amounts, or play amount data is not available. At this time, if the 10 target videos need to be ranked according to the play amount (ranking feature) of the videos, since the corresponding play amount data does not exist in part of the target videos, the 10 target videos in the target video set cannot be ranked and displayed according to the play amount. At this time, two weight vectors may be used to weight the play amounts of 8 target videos having play amounts, so as to obtain two reconstructed play amount data, and the play amounts of 2 target videos having no play amounts are represented by the two reconstructed play amount data. At this time, the 10 target videos in the target video set all have corresponding play amount data, and at this time, the 10 target videos in the target video set can be ordered and displayed according to the play amount. The method solves the problem that the target videos cannot be sequenced and displayed.
According to the video ordering method under the search scene, the first ordering feature corresponding to each first target video is weighted according to the weight vector in the preset feature weight set, so that the second ordering feature corresponding to the second target video is obtained. Therefore, when the second target video does not have the corresponding ordering feature, the ordering feature is incomplete or the ordering feature is unavailable, the second ordering feature corresponding to the second target video can be obtained according to the first ordering feature corresponding to the first target video. According to the first ordering feature and the second ordering feature, ordering the target videos in the target video set to obtain an ordering result, and displaying the target videos in the target video set according to the ordering result. Therefore, when the corresponding ordering feature does not exist in part of videos in the target video set, the ordering feature is incomplete or the ordering feature is unavailable, the second ordering feature corresponding to the second target video can be obtained according to the first ordering feature corresponding to the first target video, and the purposes of ordering and displaying the target videos in the target video set are achieved according to the first ordering feature and the second ordering feature.
In an exemplary embodiment, one way to obtain the feature weight set is:
And determining a weight vector of the second target video relative to the first target video according to the association relation between the first video feature and the second video feature to obtain a feature weight set.
Specifically, the weight vector in the feature weight set is used for determining the second ordering feature according to the first ordering feature, so that the weight vector is a representation of the mapping relationship from the first ordering feature to the second ordering feature, and the weight vector is determined according to the association relationship between the first video feature and the second video feature.
Optionally, as shown in fig. 2, a flowchart of a method for obtaining a feature weight set according to an exemplary embodiment specifically includes the following steps:
in step S310, the similarity between each second video feature and each first video feature is determined, so as to obtain a similarity set.
In step S320, the similarity in the similarity set is normalized, and a weight vector of the second target video relative to the first target video is determined, so as to obtain a feature weight set.
Specifically, according to the second video features and the first video features, determining the similarity between each second video feature and each first video feature, normalizing the similarity in the similarity set, determining the normalized similarity as a weight vector of the second target video relative to the first target video, and obtaining a feature weight set.
For example, when the first video feature and the second video feature are represented by an embedded corresponding to the target video, the similarity between each second video feature and each first video feature is obtained as shown in formula (1):
simliarity i ＝cosine(embedding i ,embedding p ) (1)
wherein, simliarity i Representing the similarity between each second video feature and each first video feature i Embedding representation for a first video feature p An embedded representation of the second video feature.
Specifically, the target video set is P, the second target video set is P, at least one second target video set is P ', the first target video set is i, and at least one second target video set is { i e (P-P') }. simliarity set For by simliarity i And forming a similarity set.
And carrying out normalization processing on the similarity in the similarity set, and determining the normalized similarity as a weight vector of the second target video relative to the first target video to obtain a characteristic weight set.
In the above exemplary embodiment, the similarity between each second video feature and each first video feature is determined, a similarity set is obtained, the similarity in the similarity set is normalized, and a weight vector of the second target video relative to the first target video is determined, so as to obtain a feature weight set. Therefore, the weight vector capable of establishing the mapping relation between the first video feature and the second video feature can be determined on the basis of the first video feature and the second video feature, so that the second ordering feature corresponding to the second target video can be obtained according to the first ordering feature on the premise of obtaining the first ordering feature of the first target video, and the problem that the second target video does not have the corresponding ordering feature, the ordering feature is incomplete or the ordering feature is not complete can be solved.
In an exemplary embodiment, as shown in fig. 3, a flowchart of an implementation manner of step S320 according to an exemplary embodiment is shown, and specifically includes:
in step S321, the similarity in the similarity set is normalized, and the generalization weight of the second target video relative to the first target video is determined, so as to obtain a generalization weight set.
In step S322, normalization processing is performed on the generalized weights in the generalized weight set, and a weight vector of the second target video relative to the first target video is determined, so as to obtain a feature weight set.
Specifically, the similarity in the similarity set is normalized to obtain a normalized similarity, and the normalized similarity can reflect the weight ratio of the second target video relative to the first target video, so that the normalized similarity is determined as the generalization weight of the second target video relative to the first target video, and a generalization weight set is obtained.
Illustratively, the similarity is subjected to min-max normalization to obtain the weighting of the second target video p relative to the first target video i, and the weighting weight is generalized i The acquisition mode of (2) is as shown in the formula:
then, in order to ensure that the characteristics of the second target video p and the first target video i are in an order of magnitude, the generalized weights need to be subjected to weight normalization, and the generalized weights after the weight normalization are determined to be weight vectors of the second target video relative to the first target video, so that a characteristic weight set is obtained. The weight vector is obtained as shown in formula (3):
Optionally, inputting the first target video into a preset Embedding model to obtain a first video feature; or inputting the second target video into the editing model to obtain the second video feature.
Specifically, when the first video feature and the second video feature are the corresponding Embedding representations of the target video, an Embedding system with one video is needed to acquire the Embedding representations of the first target video and the second target video, and the Embedding system can be an intermediate feature of a visual model or a width trained based on behavior data&And (5) a deep model. Unification can be expressed as having one ebedding for one video i i Corresponding to this.
In the above exemplary embodiment, the similarity in the similarity set is normalized, a generalized weight of the second target video relative to the first target video is determined, a generalized weight set is obtained, the generalized weight in the generalized weight set is normalized, and a weight vector of the second target video relative to the first target video is determined, so as to obtain a feature weight set. Therefore, the weight vector which can establish the mapping relation between the first video feature and the second video feature can be determined on the basis of the first video feature and the second video feature, and the first ordering feature and the second ordering feature can be ensured to be on one order of magnitude by normalizing the generalized weight, so that the second ordering feature corresponding to the second target video can be obtained according to the first ordering feature on the premise of obtaining the first ordering feature of the first target video, and the problem that the second target video does not have the corresponding ordering feature, the incomplete ordering feature or the ordering feature can be solved.
In an exemplary embodiment, one way of obtaining the target video set is:
acquiring a target search word; and acquiring videos related to the target search words to obtain a target video set.
Specifically, in a video search scenario, according to the target search word, videos related to the target search word can be recalled, and the videos are videos required to be ranked and displayed to form a target video set.
In the above exemplary embodiments, a method for obtaining a target video set is provided, which provides boundaries for subsequent video ordering and displaying. It should be understood that the above is only one way to obtain the target video set, and is not limited to the target video set. By way of example, a target video set may also be determined by a user ID, video distribution area, video distribution time, etc.
In an exemplary embodiment, as an implementation manner of step S400, the method includes:
inputting the first ordering feature and the second ordering feature into a preset video ordering model, and performing an ordering feature on a first target video corresponding to the first ordering feature and a second target video corresponding to the second ordering feature to obtain a second ordering feature corresponding to the second target video, wherein the specific formula (4) is as follows:
Wherein,a second ordering attribute representing a second target video correspondence +.>Identifying a first ranking feature, softmax, corresponding to a first target video i Representing the weight vector.
After the second ordering feature corresponding to the second target video is obtained, the first ordering feature and the second ordering feature are input into a preset video ordering model, the first target video corresponding to the first ordering feature and the second target video corresponding to the second ordering feature are ordered, and an ordering result is output.
Wherein the predetermined video ranking model may be a scoring model, for example, byAnd scoring and sorting the crust sorting characteristics and the second sorting characteristics to obtain a sorting result of the target video.
In the above exemplary embodiment, the first ranking features and the second ranking features are input into a preset video ranking model, the first target video corresponding to the first ranking features and the second target video corresponding to the second ranking features are ranked, and the ranking result is output. And then according to the sequencing result, the target videos in the target video set are sequenced and displayed, so that the problem that the target videos cannot be sequenced and displayed is solved.
It should be understood that, although the steps in the flowcharts of fig. 1-3 are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in fig. 1-3 may include multiple steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor do the order in which the steps or stages are performed necessarily performed in sequence, but may be performed alternately or alternately with at least a portion of the steps or stages in other steps or other steps.
Fig. 4 is a block diagram illustrating a video ordering apparatus in a search scenario according to an example embodiment. Referring to fig. 4, the apparatus includes a video set acquisition unit 401, a first ranking feature acquisition unit 402, a second ranking feature determination unit 403, a video ranking unit 404, and a video presentation unit 405:
a video set acquisition unit 401 configured to perform acquisition of a target video set; wherein the target videos in the target video set comprise at least one first target video and at least one second target video;
a first ranking feature acquiring unit 402 configured to perform acquisition of a first ranking feature corresponding to a first target video;
a second ranking feature determining unit 403 configured to perform weighting on the first ranking feature according to the weight vector in the preset feature weight set to obtain a second ranking feature corresponding to the second target video;
a video ranking unit 404 configured to perform ranking of the target videos in the target video set according to the first ranking feature and the second ranking feature, resulting in a ranking result;
and the video display unit 405 is configured to perform displaying of the target videos in the target video set according to the sorting result.
In an exemplary embodiment, each first target video corresponds to a first video feature and each second target video corresponds to a second video feature; the second ordering attribute determination unit 403 is further configured to perform: and determining a weight vector of the second target video relative to the first target video according to the association relation between the first video feature and the second video feature to obtain a feature weight set.
In an exemplary embodiment, the second ordering attribute determining unit 403 is further configured to perform: determining the similarity between each second video feature and each first video feature to obtain a similarity set; and carrying out normalization processing on the similarity in the similarity set, determining a weight vector of the second target video relative to the first target video, and obtaining a characteristic weight set.
In an exemplary embodiment, the second ordering attribute determining unit 403 is further configured to perform: normalizing the similarity in the similarity set to determine the generalization weight of the second target video relative to the first target video, and obtaining a generalization weight set; and carrying out normalization processing on the generalized weights in the generalized weight set, determining a weight vector of the second target video relative to the first target video, and obtaining a characteristic weight set.
In an exemplary embodiment, the second ordering attribute determining unit 403 is further configured to perform: inputting a first target video into a preset Embedding model to obtain a first video feature; or inputting the second target video into the editing model to obtain the second video feature.
In an exemplary embodiment, the video set acquisition unit 401 is further configured to perform: acquiring a target search word; and acquiring videos related to the target search words to obtain a target video set.
In an exemplary embodiment, the video ordering unit 404 is further configured to perform: inputting the first ordering feature and the second ordering feature into a preset video ordering model, ordering the first target video corresponding to the first ordering feature and the second target video corresponding to the second ordering feature, and outputting an ordering result.
The specific manner in which the various modules perform the operations in the apparatus of the above embodiments have been described in detail in connection with the embodiments of the method, and will not be described in detail herein.
Fig. 5 is a block diagram illustrating an electronic device 500 for video ordering in a search scene, according to an example embodiment. For example, device 500 may be a mobile phone, computer, digital broadcast terminal, messaging device, game console, tablet device, medical device, exercise device, personal digital assistant, or the like.
Referring to fig. 5, device 500 may include one or more of the following components: a processing component 502, a memory 504, a power supply component 506, a multimedia component 508, an audio component 510, an input/output (I/O) interface 512, a sensor component 514, and a communication component 516.
The processing component 502 generally controls overall operation of the device 500, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing component 502 may include one or more processors 520 to execute instructions to perform all or part of the steps of the methods described above. Further, the processing component 502 can include one or more modules that facilitate interactions between the processing component 502 and other components. For example, the processing component 502 can include a multimedia module to facilitate interaction between the multimedia component 508 and the processing component 502.
Memory 504 is configured to store various types of data to support operations at device 500. Examples of such data include instructions for any application or method operating on device 500, contact data, phonebook data, messages, pictures, video, and the like. The memory 504 may be implemented by any type or combination of volatile or nonvolatile memory devices such as Static Random Access Memory (SRAM), electrically Erasable Programmable Read Only Memory (EEPROM), erasable Programmable Read Only Memory (EPROM), programmable Read Only Memory (PROM), read Only Memory (ROM), magnetic memory, flash memory, magnetic or optical disk.
The power supply component 506 provides power to the various components of the device 500. Power supply components 506 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for device 500.
The multimedia component 508 includes a screen between the device 500 and the user that provides an output interface. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensor may sense not only the boundary of a touch or slide action, but also the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 508 includes a front-facing camera and/or a rear-facing camera. The front-facing camera and/or the rear-facing camera may receive external multimedia data when the device 500 is in an operational mode, such as a shooting mode or a video mode. Each front camera and rear camera may be a fixed optical lens system or have focal length and optical zoom capabilities.
The audio component 510 is configured to output and/or input audio signals. For example, the audio component 510 includes a Microphone (MIC) configured to receive external audio signals when the device 500 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may be further stored in the memory 504 or transmitted via the communication component 516. In some embodiments, the audio component 510 further comprises a speaker for outputting audio signals.
The I/O interface 512 provides an interface between the processing component 502 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to: homepage button, volume button, start button, and lock button.
The sensor assembly 514 includes one or more sensors for providing status assessment of various aspects of the device 500. For example, the sensor assembly 514 may detect the on/off state of the device 500, the relative positioning of the components, such as the display and keypad of the device 500, the sensor assembly 514 may also detect a change in position of the device 500 or a component of the device 500, the presence or absence of user contact with the device 500, the orientation or acceleration/deceleration of the device 500, and a change in temperature of the device 500. The sensor assembly 514 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 514 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 514 may also include an acceleration sensor, a gyroscopic sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.
The communication component 516 is configured to facilitate communication between the device 500 and other devices, either wired or wireless. The device 500 may access a wireless network based on a communication standard, such as WiFi, an operator network (e.g., 2G, 3G, 4G, or 5G), or a combination thereof. In one exemplary embodiment, the communication component 516 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 516 further includes a Near Field Communication (NFC) module to facilitate short range communications.
In an exemplary embodiment, the apparatus 500 may be implemented by one or more Application Specific Integrated Circuits (ASICs), digital Signal Processors (DSPs), digital Signal Processing Devices (DSPDs), programmable Logic Devices (PLDs), field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic elements for executing the methods described above.
In an exemplary embodiment, a non-transitory computer readable storage medium is also provided, such as memory 504, including instructions executable by processor 520 of device 500 to perform the above-described method. For example, the non-transitory computer readable storage medium may be ROM, random Access Memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.
In an exemplary embodiment, a computer program product is also provided, the program product comprising a computer program stored in a readable storage medium, from which the at least one processor 520 of the device reads and executes the computer program, causing the device to perform the above-described method.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any adaptations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It is to be understood that the present disclosure is not limited to the precise arrangements and instrumentalities shown in the drawings, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (14)
1. A method for video ordering in a search scene, comprising:
Acquiring a target video set; the target videos in the target video set comprise at least one first target video and at least one second target video, and the second target video is a video with no corresponding ordering feature, incomplete ordering feature or unavailable ordering feature;
acquiring a first ordering characteristic corresponding to the first target video, wherein the first ordering characteristic is play quantity, exposure quantity, click number, click rate, praise number, praise rate, attention rate or play completion rate;
weighting the first ordering feature according to a weight vector in a preset feature weight set to obtain a second ordering feature corresponding to the second target video;
sorting the target videos in the target video set according to the first sorting feature and the second sorting feature to obtain a sorting result;
and displaying the target videos in the target video set according to the sequencing result.
2. The method for video ranking in a search scene according to claim 1 wherein each of the first target videos corresponds to a first video feature and each of the second target videos corresponds to a second video feature;
The obtaining mode of the characteristic weight set comprises the following steps:
and determining a weight vector of the second target video relative to the first target video according to the association relation between the first video feature and the second video feature, so as to obtain the feature weight set.
3. The method for video ranking in a search scene according to claim 2, wherein determining a weight vector of the second target video relative to the first target video according to the association relationship between the first video feature and the second video feature, to obtain the feature weight set, includes:
determining the similarity between each second video feature and each first video feature to obtain a similarity set;
and carrying out normalization processing on the similarity in the similarity set, and determining a weight vector of the second target video relative to the first target video to obtain the characteristic weight set.
4. The method for video ranking in a search scene according to claim 3, wherein the normalizing the similarity in the similarity set to determine a weight vector of the second target video relative to the first target video, and obtaining the feature weight set includes:
Normalizing the similarity in the similarity set, and determining the generalization weight of the second target video relative to the first target video to obtain a generalization weight set;
and carrying out normalization processing on the generalized weights in the generalized weight set, determining a weight vector of the second target video relative to the first target video, and obtaining the characteristic weight set.
5. The method for ordering videos in a search scene according to claim 1, wherein the obtaining manner of the target video set includes:
acquiring a target search word;
and acquiring videos related to the target search word to obtain the target video set.
6. The method for ranking videos in a search scene according to claim 1, wherein ranking the target videos in the target video set according to the first ranking feature and the second ranking feature to obtain a ranking result comprises:
inputting the first ordering feature and the second ordering feature into a preset video ordering model, ordering the first target video corresponding to the first ordering feature and the second target video corresponding to the second ordering feature, and outputting the ordering result.
7. A video ordering apparatus in a search scene, comprising:
a video set acquisition unit configured to perform acquisition of a target video set; the target videos in the target video set comprise at least one first target video and at least one second target video, and the second target video is a video with no corresponding ordering feature, incomplete ordering feature or unavailable ordering feature;
a first ranking feature acquiring unit configured to perform acquiring a first ranking feature corresponding to the first target video, the first ranking feature being a play amount, an exposure amount, a click count, a click rate, a praise count, a praise rate, a focus rate, or a play completion rate;
the second ordering feature determining unit is configured to perform weighting on the first ordering feature according to a weight vector in a preset feature weight set to obtain a second ordering feature corresponding to the second target video;
a video ordering unit configured to perform ordering of the target videos in the target video set according to the first ordering feature and the second ordering feature, so as to obtain an ordering result;
and the video display unit is configured to display the target videos in the target video set according to the sorting result.
8. The video ordering apparatus in a search scene according to claim 7, wherein each of the first target videos corresponds to a first video feature, and each of the second target videos corresponds to a second video feature;
the second ranking features determining unit is further configured to perform:
and determining a weight vector of the second target video relative to the first target video according to the association relation between the first video feature and the second video feature, so as to obtain the feature weight set.
9. The video ordering apparatus in a search scene of claim 8, wherein the second ordering feature determination unit is further configured to perform:
determining the similarity between each second video feature and each first video feature to obtain a similarity set;
and carrying out normalization processing on the similarity in the similarity set, and determining a weight vector of the second target video relative to the first target video to obtain the characteristic weight set.
10. The video ordering apparatus in a search scene of claim 9, wherein the second ordering feature determination unit is further configured to perform:
Normalizing the similarity in the similarity set, and determining the generalization weight of the second target video relative to the first target video to obtain a generalization weight set;
and carrying out normalization processing on the generalized weights in the generalized weight set, determining a weight vector of the second target video relative to the first target video, and obtaining the characteristic weight set.
11. The video ordering apparatus in a search scene according to claim 7, wherein the video set acquisition unit is further configured to perform:
acquiring a target search word;
and acquiring videos related to the target search word to obtain the target video set.
12. The video ordering apparatus in a search scene according to claim 7, wherein the video ordering unit is further configured to perform:
inputting the first ordering feature and the second ordering feature into a preset video ordering model, ordering the first target video corresponding to the first ordering feature and the second target video corresponding to the second ordering feature, and outputting the ordering result.
13. An electronic device, comprising:
a processor;
A memory for storing the processor-executable instructions;
wherein the processor is configured to execute the instructions to implement the video ordering method in a search scenario of any one of claims 1 to 6.
14. A storage medium, which when executed by a processor of an electronic device, causes the electronic device to perform the video ordering method in a search scenario of any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011261872.5A CN112380388B (en) | 2020-11-12 | 2020-11-12 | Video ordering method and device under search scene, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011261872.5A CN112380388B (en) | 2020-11-12 | 2020-11-12 | Video ordering method and device under search scene, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112380388A CN112380388A (en) | 2021-02-19 |
| CN112380388B true CN112380388B (en) | 2024-03-12 |
Family
ID=74583319
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011261872.5A Active CN112380388B (en) | 2020-11-12 | 2020-11-12 | Video ordering method and device under search scene, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112380388B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108304512A (en) * | 2018-01-19 | 2018-07-20 | 北京奇艺世纪科技有限公司 | A kind of thick sort method of video search engine, device and electronic equipment |
| CN109189987A (en) * | 2017-09-04 | 2019-01-11 | 优酷网络技术（北京）有限公司 | Video searching method and device |
| CN109657097A (en) * | 2018-11-07 | 2019-04-19 | 北京达佳互联信息技术有限公司 | Video screening technique, device, electronic equipment and storage medium |
| CN111428771A (en) * | 2019-11-08 | 2020-07-17 | 腾讯科技（深圳）有限公司 | Video scene classification method and device and computer-readable storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140372424A1 (en) * | 2013-06-18 | 2014-12-18 | Thomson Licensing | Method and system for searching video scenes |
-
2020
- 2020-11-12 CN CN202011261872.5A patent/CN112380388B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109189987A (en) * | 2017-09-04 | 2019-01-11 | 优酷网络技术（北京）有限公司 | Video searching method and device |
| CN108304512A (en) * | 2018-01-19 | 2018-07-20 | 北京奇艺世纪科技有限公司 | A kind of thick sort method of video search engine, device and electronic equipment |
| CN109657097A (en) * | 2018-11-07 | 2019-04-19 | 北京达佳互联信息技术有限公司 | Video screening technique, device, electronic equipment and storage medium |
| CN111428771A (en) * | 2019-11-08 | 2020-07-17 | 腾讯科技（深圳）有限公司 | Video scene classification method and device and computer-readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112380388A (en) | 2021-02-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111859020B (en) | Recommendation method, recommendation device, electronic equipment and computer readable storage medium | |
| CN107463643B (en) | Barrage data display method and device and storage medium | |
| CN106485567B (en) | Article recommendation method and device | |
| CN112148980B (en) | Article recommending method, device, equipment and storage medium based on user click | |
| CN110781323A (en) | Method and device for determining label of multimedia resource, electronic equipment and storage medium | |
| CN112148923B (en) | Method for ordering search results, method, device and equipment for generating ordering model | |
| CN110941727B (en) | Resource recommendation method and device, electronic equipment and storage medium | |
| CN112380388B (en) | Video ordering method and device under search scene, electronic equipment and storage medium | |
| CN116233554A (en) | Video playing method, device, electronic equipment and storage medium | |
| CN107122801B (en) | Image classification method and device | |
| CN112000840B (en) | Business object display method and device | |
| CN113159206A (en) | Image comparison method and device, electronic equipment and computer readable storage medium | |
| CN114117058A (en) | Account information determination method and device, electronic equipment and storage medium | |
| CN117350824B (en) | Electronic element information uploading and displaying method, device, medium and equipment | |
| CN113255473B (en) | Video identification method and device and video cover identification model generation method and device | |
| CN113190725B (en) | Object recommendation and model training method and device, equipment, medium and product | |
| CN112307353B (en) | Data processing method and device, electronic equipment and storage medium | |
| CN114722238B (en) | Video recommendation method and device, electronic equipment, storage medium and program product | |
| CN115484471B (en) | Method and device for recommending anchor | |
| CN113157703B (en) | Data query method and device, electronic equipment and storage medium | |
| CN113407754B (en) | Album generating method, apparatus, electronic device and storage medium | |
| CN107239280B (en) | Method and device for determining notification importance and mobile terminal | |
| CN112989172B (en) | Content recommendation method, device, computer equipment and storage medium | |
| CN113191792B (en) | Task processing method, device, electronic equipment, storage medium and program product | |
| CN109063001B (en) | Page display method and device |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |