CN113515670A

CN113515670A - Method, device and storage medium for identifying state of movie and television resource

Info

Publication number: CN113515670A
Application number: CN202110921963.5A
Authority: CN
Inventors: 帅丹; 王鑫
Original assignee: Chengdu Jimi Technology Co Ltd
Current assignee: Chengdu Jimi Technology Co Ltd
Priority date: 2021-08-12
Filing date: 2021-08-12
Publication date: 2021-10-19
Anticipated expiration: 2041-08-12
Also published as: CN113515670B

Abstract

The invention discloses a method, equipment and a storage medium for identifying the state of a film and television resource. The method comprises the following steps: identifying a movie resource to be inspected, the movie resource to be inspected including at least one of: suspected offline movie and television resources, active movie and television resources, movie and television resources configured by an operation platform, movie and television resources added by a partner of a client, and residual full movie and television resources in a movie and television resource library sequentially traversed according to a first preset period; and checking whether the video resource to be checked is offline or not according to the playing screenshot or the playing log of the video resource to be checked. By implementing the scheme of the invention, the offline movie and television resources can be quickly identified and off-shelf from the business system, so that the abnormal movie and television resources are not pushed to users, and the user experience is improved.

Description

Method, device and storage medium for identifying state of movie and television resource

Technical Field

The present invention relates to the field of multimedia technologies, and in particular, to a method, an apparatus, and a storage medium for identifying a state of a video resource.

Background

The film and television resources are mainly concentrated on the head manufacturers who do the content, and the manufacturers who do the television or the projection generally cooperate with the related manufacturers. When the movie and television resources are sourced from three-party manufacturers, if the movie and television is off shelf for various reasons, the movie and television cannot be synchronized at the first time, so that the offline movie and television resources need to be found and relevant processing needs to be carried out as soon as possible in order to guarantee user experience.

Disclosure of Invention

In view of this, embodiments of the present invention provide a method, an apparatus, and a storage medium for identifying a state of a video resource, which can quickly identify the state of the video resource, so as to perform related processing on the video resource whose state is offline.

In a first aspect, an embodiment of the present invention provides a method for identifying a state of a movie resource, where the method includes:

identifying a movie resource to be inspected, the movie resource to be inspected including at least one of: suspected offline movie and television resources, active movie and television resources, movie and television resources configured by an operation platform, movie and television resources added by a partner of a client, and residual full movie and television resources in a movie and television resource library sequentially traversed according to a first preset period;

and checking whether the video resource to be checked is offline or not according to the playing screenshot or the playing log of the video resource to be checked.

In one possible implementation, the movie resource to be inspected includes a suspected offline movie resource, and the identifying the movie resource to be inspected includes:

collecting the film watching behaviors of the user from the client;

and identifying suspected offline movie and television resources according to the viewing behavior of the user.

In one possible implementation, the viewing behavior of the user includes event generation time, device identification, event type, and event content.

In a possible implementation manner, the identifying the suspected offline movie resource according to the viewing behavior of the user includes:

generating a movie and television resource related event table according to the watching behavior of a user, wherein the movie and television resource related event table comprises an initial playing movie and television resource identifier and data corresponding to the initial playing movie and television resource identifier, and the data corresponding to the initial playing movie and television resource identifier comprises any one or more of the following data: the number of playing next movie and television resources, the number of playing next movie and television resources at a first time interval, the number of playing quitting events and the number of playing quitting at a second time interval;

and identifying suspected offline movie resources according to the movie resource related event table.

In a possible implementation manner, the generating a movie resource related event table according to the viewing behavior of the user includes:

processing the user viewing behaviors of preset interval time, and processing the user viewing behaviors into a first user behavior table, wherein the first user behavior table comprises field equipment identifiers and any one or more of the following fields: the method comprises the steps of starting to play a movie resource identifier, a next operation event type, a next movie resource playing time interval and a next operation event time interval;

performing event type classification and interval time classification processing on the first user behavior table to generate a second user behavior table, wherein the second user behavior table comprises field equipment identifiers and any one or more of the following fields: the method comprises the steps of starting to play a movie resource identifier, judging whether a next movie resource is played or not, classifying the type of a next operation event, and judging the time interval for playing the next movie resource and the time interval for playing the next operation event;

and counting data corresponding to the identifier of the video resource which is played at the beginning by using the identifier of the video resource which is played at the beginning as an index by using the second user behavior table to generate a related event table of the video resource.

In a possible implementation manner, the identifying, according to the movie resource related event table, a suspected offline movie resource includes:

normalizing data corresponding to the identifier of the starting playing movie resource in the movie and television resource related event table, inputting the processed data into a trained suspected offline model of the movie and television resource, and if the value output by the suspected offline model of the movie and television resource is greater than or equal to a first threshold value, judging that the movie and television resource indicated by the identifier of the starting playing movie and television resource in the movie and television resource related event table is suspected offline movie and television resource, wherein the suspected offline model of the movie and television resource is used for predicting whether the movie and television resource is suspected offline movie and television resource; alternatively, the first and second electrodes may be,

and if the data corresponding to the identifier of the starting playing movie resource in the movie and television resource related event table accords with the rule of suspected offline movie and television resources, judging that the movie and television resources indicated by the identifier of the starting playing movie and television resources in the movie and television resource related event table are suspected offline movie and television resources.

In one possible implementation, the suspected offline movie resource rule includes one of the following:

playing the next movie resource by the first time quantity/playing the next movie resource > = the second threshold;

when the number of play-out events is greater than or equal to the preset value, the number of play-out intervals of the second time/the number of play-out events > = a third threshold;

the number of playing next movie resource interval first time/the number of playing next movie resource > = fourth threshold, and the number of playing back interval second time/the number of playing back event > = fifth threshold.

In one possible implementation, the event types include play, fast forward, fast reverse, return, home page, and full screen; the event type classification comprises continuous playing, quitting playing and no event, wherein the continuous playing comprises fast forward, fast backward and full screen, and the quitting playing comprises return and homepage.

In a possible implementation manner, the data corresponding to the identifier of the starting playing movie resource further includes any one or more of the following: the number of the next film and television resources which are not played, the number of the third time interval between the playing of the next film and television resources, the number of the events which are continuously played, the number of no events, the number of the fourth time interval between the quitting of playing, the number of the fifth time interval between the continuous playing and the number of the sixth time interval between the continuous playing.

In a possible implementation manner, the checking whether the movie resource to be checked is offline according to the play screenshot or the play log of the movie resource to be checked includes at least one of the following items:

if the video resource to be detected has a playing log which is not played successfully in the playing process, judging that the video resource to be detected is in an off-line state;

if N continuous playing screenshots containing abnormally-popped pictures exist in the playing screenshots of the video resource to be detected, judging that the video resource to be detected is in an off-line state, wherein N is a preset positive integer;

and if the video resource to be detected has pictures which are not changed within a continuous period of time in the playing process, judging that the video resource to be detected is in the offline state.

In a possible implementation manner, the checking whether the movie resource to be checked is offline according to the play screenshot or the play log of the movie resource to be checked includes:

judging whether the video resource to be detected has a playing log which is not played successfully in the playing process, and if the video resource to be detected has the playing log which is not played successfully in the playing process, judging that the video resource to be detected is in an off-line state; otherwise, acquiring a playing screenshot of the video resource to be detected according to a preset frequency;

judging whether N continuous playing screenshots containing pictures popped up abnormally during playing exist in the obtained playing screenshots, wherein N is a preset positive integer, and if N continuous playing screenshots containing the pictures popped up abnormally during playing exist in the obtained playing screenshots, judging that the video resource to be detected is in an off-line state;

judging whether the video resource to be detected has pictures which are unchanged within a continuous period of time in the playing process according to the acquired playing screenshot; if the video resource to be detected has pictures which are unchanged within a continuous period of time in the playing process, judging that the video resource to be detected is in an off-line state; otherwise, judging the video resource to be detected to be in a normal state.

In a possible implementation manner, the determining whether there are N consecutive screenshots including a picture popped up abnormally during playing in the acquired screenshots includes:

and carrying out character recognition on the non-caption and non-bullet-caption areas in the played screenshot, and judging whether the recognized characters contain related logs of abnormal playing or not.

In a possible implementation manner, the determining, according to the acquired screenshot, whether there is a frame that does not change for a continuous period of time in the playing process of the movie resource to be checked includes:

if the continuous M playing screenshots are highly similar, judging that the to-be-detected movie resource has pictures which are unchanged within a continuous period of time in the playing process, wherein M is a preset positive integer.

In a possible implementation manner, the method for judging the high similarity of the played screenshot includes:

acquiring two continuous screenshots A and B from a played screenshot;

removing pixel areas containing status bar parts at the tops of the screenshot A and the screenshot B; acquiring RGB values of a screenshot A and a screenshot B of a pixel area with the top containing a status bar part removed, and converting the RGB values into a gray image; processing the gray level image by adopting a maximum pooling method; and judging the ratio of the cross correlation between the processed screenshot A and the screenshot B to the autocorrelation between the screenshot A, and if the cross correlation is greater than or equal to a sixth threshold, judging that the screenshot A and the screenshot B are highly similar.

In a possible implementation manner, after the identifying the movie resource to be checked, and before the checking whether the movie resource to be checked is offline according to the play screenshot or the play log of the movie resource to be checked, the method further includes:

sending the data of the video resources to be inspected to inspection equipment;

and acquiring a playing screenshot or a playing log of the video resource to be detected played by the detection equipment.

In a possible implementation manner, the issuing, to the inspection device, data of the movie resource to be inspected includes:

if the movie and television resources to be detected need to be offline, sending the movie and television resource information to be detected to a message queue;

acquiring data of the target inspection movie resources from the message queue according to the priority of the movie resources;

and translating the data of the target inspection video resource into a protocol instruction which can be executed by the inspection equipment, and issuing the protocol instruction to the inspection equipment.

In one possible implementation, the priority of the movie resource includes: suspected offline movie and television resources > active movie and television resources > movie and television resources configured by an operation platform > movie and television resources added by a partner of a client > residual full amount of movie and television resources in a movie and television resource library sequentially traversed according to a first preset period.

In a possible implementation manner, after checking whether the movie resource to be checked is offline according to the play screenshot or the play log of the movie resource to be checked, the method further includes:

if the video resources to be detected are detected to be in the offline state and are in the normal state in the original library, changing the video resources to be detected to be in the offline state and informing operators;

and if the video resources to be detected are detected to be in an online state and are in an offline state in the original library, informing the operator of processing.

In a second aspect, an embodiment of the present invention provides a device for identifying a state of a movie resource, including:

the movie and television resource identification module to be detected is used for identifying the movie and television resource to be detected, and the movie and television resource to be detected comprises at least one item in the following items: suspected offline movie and television resources, active movie and television resources, movie and television resources configured by an operation platform, movie and television resources added by a partner of a client, and residual full movie and television resources in a movie and television resource library sequentially traversed according to a first preset period;

and the offline inspection module of the movie and television resources is used for inspecting whether the movie and television resources to be inspected are offline or not according to the playing screenshot or the playing log of the movie and television resources to be inspected.

In one possible implementation, the movie and television resource to be checked includes a suspected offline movie and television resource, and the movie and television resource to be checked identification module includes:

the user viewing behavior collection module is used for collecting the viewing behaviors of the user from the client;

and the suspected offline movie resource analysis module is used for identifying the suspected offline movie resource according to the viewing behavior of the user.

In a possible implementation manner, the movie resource identification module to be checked includes:

the active video resource analysis module is used for identifying active video resources with the number of P-th place before the ranking viewed by the user within a second preset period time;

the configuration video resource processing module is used for identifying video resources configured by the operation platform;

the newly-added video resource processing module is used for identifying the video resources added by the partner of the client;

and the full-amount video resource processing module is used for sequentially traversing the residual full-amount video resources in the video resource library according to a first preset period.

In one possible implementation manner, the method further includes:

the film and television resource inspection and distribution module is used for sending the film and television resource information to be inspected to the message queue if the film and television resource to be inspected needs to be offline judged; acquiring data of the target inspection movie resources from the message queue according to the priority of the movie resources; and translating the data of the target inspection video resource into a protocol instruction which can be executed by the inspection equipment, and issuing the protocol instruction to the inspection equipment.

In one possible implementation manner, the method further includes:

the movie and television resource state processing module is used for changing the movie and television resources to be detected into the offline state and informing operators if the movie and television resources to be detected are detected to be the offline state and are in the normal state in the original library; and if the video resources to be detected are detected to be in an online state and are in an offline state in the original library, informing the operator of processing.

In a third aspect, an embodiment of the present invention provides a state identification device for video resources, where the device includes a processor and a memory, where the memory stores instructions executable by the processor, and the instructions are loaded and executed by the processor to implement the state identification method for video resources according to the first aspect.

In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the method for identifying a state of a movie resource according to the first aspect is implemented.

In a fifth aspect, an embodiment of the present invention provides a computer program product, which includes instructions that, when executed by at least one processor, cause the at least one processor to execute the movie resource state identification method according to the first aspect.

It should be noted that the apparatus of the second aspect, the device of the third aspect, the storage medium of the fourth aspect, and the computer program product of the fifth aspect are used to execute the method provided by the first aspect, so that the same beneficial effects as those of the method of the first aspect can be achieved, and the embodiments of the present invention are not described again.

By implementing the scheme of the invention, the offline movie and television resources can be quickly identified and off-shelf from the business system, so that the abnormal movie and television resources are not pushed to users, and the user experience is improved.

Drawings

Fig. 1 is a flowchart of a movie resource state identification method according to an embodiment of the present invention;

FIG. 2 is a schematic diagram of a method for identifying a suspected offline movie resource according to a viewing behavior of a user according to an embodiment of the present invention;

fig. 3 is a schematic diagram of a method for issuing data of a video resource to be inspected to an inspection device according to an embodiment of the present invention;

fig. 4 is a schematic structural diagram of a movie resource status identification apparatus according to an embodiment of the present invention.

Detailed Description

In order to make those skilled in the art better understand the technical solutions in the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention. Moreover, while the present disclosure has been described in terms of one or more exemplary embodiments, it is to be understood that each aspect of the disclosure can be implemented as a separate entity, whether or not such embodiment is described in connection with its specific embodiments. The embodiments described below and the features of the embodiments can be combined with each other without conflict.

In the embodiments of the present invention, words such as "exemplary", "for example", etc. are used to mean serving as an example, instance, or illustration. Any embodiment or design described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments or designs. Rather, the term using examples is intended to present concepts in a concrete fashion.

Unless defined otherwise, technical or scientific terms used herein shall have the ordinary meaning as understood by one of ordinary skill in the art to which this invention belongs. The terminology used in the embodiments of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The use of "first," "second," and similar terms in the present application do not denote any order, quantity, or importance, but rather the terms are used to distinguish one element from another, and may or may not be identical in meaning. The word "comprising" or "comprises", and the like, means that the element or item listed before the word covers the element or item listed after the word and its equivalents, but does not exclude other elements or items. The term "and/or" is meant to encompass any and all possible combinations of one or more of the associated listed items. The character "/" generally indicates that the preceding and following associated objects are in an "or" relationship.

In the embodiment of the present invention, the client may be a television, a projector, or the like, or may also refer to a video playing application, and a user may use the client to perform a movie viewing behavior. As shown in fig. 1, the method for identifying the state of the movie resource includes the following steps:

step S101, identifying a movie and television resource to be detected, wherein the movie and television resource to be detected comprises at least one item of the following items: the method comprises the steps of suspected offline movie and television resources, active movie and television resources, movie and television resources configured by an operation platform, movie and television resources added by a partner of a client, and residual full movie and television resources in a movie and television resource library sequentially traversed according to a first preset period.

When finding the movie and television resources which are possibly required to be checked whether to be off-line, the movie and television resources to be checked can be found from multiple aspects such as user watching behaviors, operation platforms, movie and television resource libraries and the like, and the priority is as follows:

(1) suspected offline movie resources. And analyzing and identifying suspected offline movie resources from the watching behaviors of the user.

(2) Active movie resources. Counting the number of video resources watched by the user in real time within a period time (one period time can be selected within 1-100 minutes, such as 5 minutes), and removing duplication from the active video resources within the previous period time, and taking a top P (the value range of P can be 100-500, such as top 300).

(3) And operating the movie and television resources configured by the platform.

(4) And the effective movie and television resources are increased in real time from the cooperation party of the client.

(5) And traversing the residual total amount of video resources in the video resource library in sequence according to a certain period (relatively long time, such as 1 hour to 10 days, such as 1 day).

In some embodiments, the movie resource to be inspected includes a suspected offline movie resource, and identifying the movie resource to be inspected includes: collecting the film watching behaviors of the user from the client; and identifying suspected offline movie and television resources according to the viewing behavior of the user.

Optionally, the viewing behavior of the user includes event generation time, device identifier, event type and event content, where the event type includes: play, fast forward, fast backward, return, home page, full screen, etc., the event content is the object of the event, for example, if playing movie V1, the event content is movie V1. Illustratively, the collected viewing behavior of the user is shown in table 1.

TABLE 1

Event generation time	Device identification	Event type	Event content
				20210101 9:02:00	Device D1	Play back	Film V1
20210101 9:02:01	Device D1	Return to
				20210101 9:02:05	Device D1	Play back	Film V2
20210101 9:01:30	Device D2	Play back	Film V2

In some embodiments, identifying a suspected offline movie resource based on the viewing behavior of the user comprises: generating a movie and television resource related event table according to the watching behavior of a user, wherein the movie and television resource related event table comprises an initial playing movie and television resource identifier and data corresponding to the initial playing movie and television resource identifier, and the data corresponding to the initial playing movie and television resource identifier comprises the number of playing next movie and television resources, the number of playing next movie and television resource intervals with first time, the number of playing quitting events and the number of playing quitting intervals with second time; and identifying suspected offline movie resources according to the movie resource related event table.

Optionally, the generating the movie resource related event table according to the viewing behavior of the user includes:

(1) and processing the user viewing behaviors of the preset interval time, and processing the user viewing behaviors into a first user behavior table, wherein the first user behavior table comprises a field device identifier, an identifier of a starting playing movie and television resource, an identifier of a next playing movie and television resource, a type of a next operation event, a time interval for playing the next movie and television resource and a time interval for the next operation event. For example, a user viewing behavior log of a certain interval time (the interval time can be selected within 1-10 minutes, such as 3 minutes) is processed in real time, each movie resource "play" is taken as a starting time point, a next "play" event and a next operation event are found, if there is no next movie resource "play", the identifier of the next play movie resource is recorded as empty, if there is no next operation event, the type of the next operation event is recorded as no event, and the ending time point of the interval time interval is taken as an operation time, the behavior log of each user is processed as a first user behavior table, wherein the first user behavior represents, for example, table 2.

TABLE 2

Device identification	Initial playing movie resource identification	Next playing movie resource identification	Next operation event type	Playing next movie resource time interval	Next operational event time interval
						Device D1	Film V1	Film V2	Return to	5	1
Device D1	Film V2		Without events		55
						Device D2	Film V2		Without events		90

Wherein, the identifier of the starting playing movie and television resource refers to the identifier of the movie and television resource played at the starting time point; the identification of the next playing movie and television resource is the identification of the next playing movie and television resource in the interval time; the next operation event type is the next operation event type after the video resources are played at the starting time within the interval time; the time interval for playing the next film and television resource is the interval time between the time point for playing the next film and television resource in the interval time and the starting time point; the next operation event time interval is an interval time between a time point of the next operation and a start time point within the interval time.

(2) And carrying out event type classification and interval time classification processing on the first user behavior table to generate a second user behavior table, wherein the second user behavior table comprises field equipment identification, identification of starting playing movie and television resources, whether playing of next movie and television resources exists, classification of the type of the next operation event, time interval of playing of the next movie and television resources and time interval of the next operation event.

Wherein the event type classification includes: continuing playing, quitting playing and having no event. The continuous playing comprises the following steps: fast forward, fast rewind and full screen; the quitting of playing comprises the following steps: return and home pages. And the next operation event type classification is the event type classification corresponding to the next operation.

The time interval for playing the next movie resource is as follows: the distinguishing interval time is a certain threshold (the threshold can be selected from 10-360 seconds, such as 30 seconds), the time is longer when the threshold is larger than the distinguishing interval time, and the time is shorter when the threshold is smaller than or equal to the distinguishing interval time.

The next operational event time interval is long or short: the distinguishing interval time is a certain threshold (the threshold can be selected from 1-120 seconds, such as 3 seconds), the time is longer when the threshold is larger than the distinguishing interval time, and the time is shorter when the threshold is smaller than or equal to the distinguishing interval time. When the next operation event type is classified as no event, only data with the time interval of the next operation event being longer than a certain threshold (for example, more than 1 minute) is retained, and the time interval of the next operation event is defined as long. Illustratively, the second user behavior table is shown in table 3.

TABLE 3

Equipment label Sign board	Initial playing movie and television data Source identification	Whether there is a next movie to be played Visual resource	Class of next operation event Type classification	Playing time of next film and television resource The length of the interval	Next operational event time The length of the interval
						Device D1	Film V1	Is provided with	Quit playing	Short length	Short length
Device D1	Film V2	Is free of	Without events
						Device D2	Film V2	Is free of	Without events	Short length	Long and long

When the device D1 starts playing the movie resource identified as the movie V2, the line of data is deleted because the next operation event type is classified as no event and the time interval of the next operation event is shorter than 1 minute. The modified second user behavior table is shown in table 4.

TABLE 4

Equipment label Sign board	Initial playing movie and television data Source identification	Whether there is a next movie to be played Visual resource	Class of next operation event Type classification	Playing time of next film and television resource The length of the interval	Next operational event time The length of the interval
						Device D1	Film V1	Is provided with	Quit playing	Short length	Short length
Device D2	Film V2	Is free of	Without events	Short length	Long and long

(3) And counting data corresponding to the identifier of the video resource which is played at the beginning by using the identifier of the video resource which is played at the beginning as an index by using the second user behavior table to generate a related event table of the video resource. Illustratively, the movie resource related event table is shown in table 5 or table 6.

TABLE 5

Initial playing movie resource identification	Number of playing down a movie resource	Number of first time interval for playing next film and television resource	Number of play-out events	The amount of the second time of the play-out interval
					Film V1	1000	950	100	95

TABLE 6

Initial playing of video resources Identification	For playing the next film and television resource Number of	Without playing the next movie resource Number of	Number of events of quitting playing Measurement of	Continue playing event number Measurement of	Number of no events Measurement of
						Film V1	1000	100	100	5	100

Play down a movie The source being spaced by a third time Number of	Between playing next film and television resource Number of intervals of first time	Exiting play interval fourth time Number of	Quit the play interval Number of two times	Interval of continuous play Number of five hours	Continue playing Interval sixth Number of times Measurement of
						50	950	5	95	4	1

Taking the initial playing movie resource identifier as movie V1 as an example, the number of playing the next movie resource is the data amount of playing the next movie resource in the interval time after playing the movie V1; the quantity of the next film and television resources which are not played is the data quantity of the next film and television resources which are not played in the interval time after the film and television V1 is played; after the number of the play quitting events is V1, classifying the next operation event type into the data volume of the play quitting in the interval time; after the number of the continuous playing events is that of the videos V1, classifying the next operation event type into the data volume of continuous playing in the interval time; the non-event number is the data volume of the next operation event type classified as no event in the interval time after the movie V1 is played; after the first time interval of playing the next movie resource is the amount of data which is the short time interval of playing the next movie resource in the interval time after playing the movie V1; after the next movie resource is played for the third time interval, the data volume of the next movie resource is played for the long time interval in the interval time after the movie V1 is played; after the amount of the second time of the play exiting interval is the play movie V1, classifying the next operation event type as play exiting within the interval time, and setting the time interval of the next operation event as short data volume; after the fourth time of the play exiting interval is the play movie V1, classifying the next operation event type as play exiting within the interval time, and the time interval of the next operation event is the data volume with the length being long; after the quantity of the continuous playing interval fifth time is the playing movie V1, classifying the next operation event type into continuous playing within the interval time, and the length of the next operation event time interval is the long data volume; after the play continuation interval has the sixth time as the play movie V1, the next operation event type is classified as play continuation within the interval time, and the next operation event interval is short and long. The time interval between the first time and the second time may be the same as or different from the time interval between the third time and the sixth time, and the embodiment of the present invention is not limited thereto.

Optionally, identifying the suspected offline movie resource according to the movie resource related event table includes:

the method comprises the following steps: and normalizing the data corresponding to the identifier of the video resource which is played at the beginning in the event table related to the video resource, for example, normalizing the data to be between 0 and 1 by using a maximum and minimum value method. And inputting the processed data into a trained suspected offline movie resource model, and if the value output by the suspected offline movie resource model is greater than or equal to a first threshold value, determining that the movie resource indicated by the identifier of the initially played movie resource in the related event table of the movie resource is suspected offline movie resource, wherein the suspected offline movie resource model is used for predicting whether the movie resource is suspected offline movie resource. The first threshold is preset according to experimental data, and may be subsequently adjusted according to an actual situation, where the first threshold may be a number greater than 0 and less than 1, for example, 0.5.

In some embodiments, the suspected offline movie resource model is an FM model, and if the probability of being the suspected offline movie resource predicted by using the trained FM model is greater than or equal to 0.5 (i.e., the first threshold), it is determined as the suspected offline movie resource, otherwise, it is determined as not being the suspected offline movie resource. The FM model can synthesize binomial features, and the model training method comprises the following steps: and generating basic data of the event table related to the trained film and television resources, and performing model iteration and training by marking whether the film and television resources are offline or not manually.

The second method comprises the following steps: and if the data corresponding to the identifier of the starting playing movie resource in the movie and television resource related event table accords with the rule of suspected offline movie and television resources, judging that the movie and television resources indicated by the identifier of the starting playing movie and television resources in the movie and television resource related event table are suspected offline movie and television resources. Optionally, the suspected offline movie resource rule comprises one of:

(1) the number of playing next movie resource interval first time/the number of playing next movie resource > = the second threshold (the second threshold may be a number greater than or equal to 0.5 and less than 1, such as 0.7);

(2) when the number of play-out events is greater than or equal to a predetermined value (the predetermined value can be a number between 100 and 10000, such as 1000, which can be estimated according to different user amounts), the number of play-out intervals of the second time/the number of play-out events > = a third threshold (the third threshold can be a number greater than or equal to 0.5 and less than 1, such as 0.7);

(3) the number of playing next movie resource interval first time/the number of playing next movie resource > = the fourth threshold (the fourth threshold may be a number greater than or equal to 0.3 and less than 1, such as 0.4), and the number of playing back interval second time/the number of playing back event > = the fifth threshold (the fifth threshold may be a number greater than or equal to 0.3 and less than 1, such as 0.4).

And S102, checking whether the video resource to be checked is offline or not according to the playing screenshot or the playing log of the video resource to be checked.

In some embodiments, the checking whether the movie resource to be checked is offline according to the play screenshot or the play log of the movie resource to be checked comprises at least one of the following items: if the video resource to be detected has a playing log which is not played successfully in the playing process, judging that the video resource to be detected is in an off-line state; if N continuous screenshots (N is a preset positive integer and can be selected from 2-10, for example, 5) containing images which pop up abnormally play exist in the screenshots of the video resources to be detected, judging that the video resources to be detected are in an off-line state; if the video resource to be detected has unchanged pictures within a continuous period of time (the range of the period of time can be 5 milliseconds to 30 seconds, such as 10 milliseconds) in the playing process, the video resource to be detected is judged to be in the offline state. For example, as shown in fig. 2, playing the to-be-checked movie resource for a certain time (the playing time can be set according to actual conditions, and can be a time between 1 second and 3 minutes, such as 1 minute), and checking whether the to-be-checked movie resource is offline according to the play screenshot or the play log of the to-be-checked movie resource includes:

judging whether the video resource to be detected has a playing log which is not played successfully in the playing process (such as the playing log of a three-party player, the three-party player can be love art, Tencent, Youke and the like), and if the video resource to be detected has the playing log which is not played successfully in the playing process, judging that the video resource to be detected is in an off-line state; otherwise, the playing screenshot of the movie resource to be checked is obtained according to a certain frequency (the range of the playing screenshot can be 1 time/1000 milliseconds to 1 time/100 milliseconds, such as 1 time/500 milliseconds, which can be set according to the actual situation).

Judging whether continuous several (for example, 5) playing screenshots containing images popped up abnormally are present in the obtained playing screenshots, optionally, performing character recognition on non-subtitle and non-bullet screen areas in the playing screenshots by using an image OCR recognition technology, and judging whether related logs of playing abnormity such as offline, crash, abnormal and the like are contained in the recognized characters. If 5 continuous playing screenshots containing abnormally played and popped pictures exist in the acquired playing screenshots, judging that the video resource to be detected is in an off-line state; otherwise, judging whether the video resource to be detected has pictures which are not changed within a continuous period of time in the playing process according to the acquired playing screenshot.

If the video resource to be detected has pictures which are unchanged within a continuous period of time in the playing process, for example, several (2-50, for example, 20) continuous screenshots are highly similar, the video resource to be detected is judged to be in a offline state; otherwise, judging the video resource to be detected to be in a normal state. The method for judging the high similarity of the played screenshots comprises the following steps: acquiring two continuous screenshots A and B from a played screenshot; removing the pixel area containing the status bar portion at the top of screenshot A and screenshot B (e.g., the projection or television top may contain the system status bar); acquiring RGB values of a screenshot A and a screenshot B of a pixel area with the top containing a status bar part removed, and converting the RGB values into a gray image; processing the gray-scale image by a maximum pooling method (such as 16-16 maximum pooling); and judging the ratio of the cross correlation between the screenshot A and the screenshot B after the processing and the auto correlation between the screenshot A, and if the ratio is greater than or equal to a sixth threshold (the sixth threshold can be a number between 0.5 and 1, such as 0.95), judging that the screenshot A is highly similar to the screenshot B.

It should be noted that, in the flow shown in fig. 2, the sequence of each judgment may be adjusted according to actual needs, and the method for judging high similarity of played screenshots is not limited in the embodiment of the present invention.

Optionally, before step S102, the relevant data of the movie resource to be checked may be sent to the checking device, and the checking device may be a device capable of playing movies, such as a television, a projector, and the like, so that the checking device plays the movie resource to be checked, and returns the play screenshot or play log of the movie resource to be checked. In some embodiments, as shown in fig. 3, the issuing the data of the movie resource to be inspected to the inspection apparatus includes:

firstly, judging whether the video resources to be detected need to be offline. If the identified or distributed video resources have been processed within a certain time (for example, 10 minutes) recently, the distribution/processing is not performed, and the process ends; otherwise, the next step is carried out.

Secondly, the information of the movie and television resources to be checked is sent to a message queue (such as kafka/robtmq), and the data of the target movie and television resources to be checked are obtained from the message queue according to the priority of the movie and television resources. Illustratively, the priority of the movie resources includes, but is not limited to: suspected offline movie and television resources > active movie and television resources > movie and television resources configured by an operation platform > movie and television resources added by a partner of a client > residual full amount of movie and television resources in a movie and television resource library sequentially traversed according to a preset period.

And thirdly, the related data (including the identification of the video resources, the playing opening mode of the video resources and the like) of the target inspection video resources are translated into a protocol instruction which can be played by the inspection equipment, and the protocol instruction is issued to the inspection equipment through a long connecting channel of the machine. It should be noted that there is an associated long connection handler in the verification device.

Optionally, after the verification result is obtained in step S102, corresponding processing may also be performed according to the verification result, such as: if the video resource to be detected is detected to be in the offline state and is in the normal state in the original library, changing the video resource to be detected to be in the offline state, and notifying operators (such as through mail notification); if the video resource to be detected is detected to be in an online state and is in an offline state in the original library, notifying operators to process; if the checking result is not changed with the state in the original library, the processing is not carried out.

Based on the same inventive concept as the method for improving the data transmission rate, the embodiment of the present invention further provides a movie resource state identification device, including: the movie and television resource identification module to be detected is used for identifying the movie and television resource to be detected, and the movie and television resource to be detected comprises at least one item in the following items: suspected offline movie and television resources, active movie and television resources, movie and television resources configured by an operation platform, movie and television resources added by a partner of a client, and residual full movie and television resources in a movie and television resource library sequentially traversed according to a first preset period; and the offline inspection module of the movie and television resources is used for inspecting whether the movie and television resources to be inspected are offline or not according to the playing screenshot or the playing log of the movie and television resources to be inspected.

Optionally, the movie and television resources to be inspected include suspected offline movie and television resources, the movie and television resources to be inspected identification module includes: the user viewing behavior collection module is used for collecting the viewing behaviors of the user from the client; and the suspected offline movie resource analysis module is used for identifying the suspected offline movie resource according to the viewing behavior of the user.

Optionally, the movie and television resource identification module to be checked includes: the active video resource analysis module is used for identifying active video resources with the number of P-th place before the ranking viewed by the user within a second preset period time; the configuration video resource processing module is used for identifying video resources configured by the operation platform; the newly-added video resource processing module is used for identifying the video resources added by the partner of the client; and the full-amount video resource processing module is used for sequentially traversing the residual full-amount video resources in the video resource library according to a first preset period. The newly added movie resource processing module and the full movie resource processing module can identify corresponding movie resources from the movie resource library synchronization module.

Optionally, the movie resource status recognition apparatus further includes: the film and television resource inspection and distribution module is used for sending the film and television resource information to be inspected to the message queue if the film and television resource to be inspected needs to be offline judged; acquiring data of the target inspection movie resources from the message queue according to the priority of the movie resources; and translating the data of the target inspection video resource into a protocol instruction which can be executed by the inspection equipment, and issuing the protocol instruction to the inspection equipment.

Optionally, the movie resource status recognition apparatus further includes: the movie and television resource state processing module is used for changing the movie and television resources to be detected into the offline state and informing operators if the movie and television resources to be detected are detected to be the offline state and are in the normal state in the original library; and if the video resources to be detected are detected to be in an online state and are in an offline state in the original library, informing the operator of processing. Fig. 4 is a schematic structural diagram of the movie resource status recognition apparatus.

Based on the same inventive concept as the method for improving the data transmission rate, an embodiment of the present invention further provides a device for identifying a state of a video resource, where the device includes a processor and a memory, where the memory stores instructions executable by the processor, and the instructions are loaded and executed by the processor, so as to implement the method for identifying a state of a video resource according to the embodiment.

In addition, an embodiment of the present invention further provides a computer-readable storage medium, in which a computer program is stored, and when the computer program is executed by a processor, the method for identifying a state of a movie resource according to the above-mentioned embodiment is implemented.

It should be understood that, in various embodiments of the present invention, the sequence numbers of the above-mentioned processes do not mean the execution sequence, some or all of the steps may be executed in parallel or executed sequentially, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

Those of ordinary skill in the art will appreciate that the various illustrative modules and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.

It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described apparatuses, devices and modules may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again. In the embodiments provided by the present invention, it should be understood that the disclosed apparatus, device and method can be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a logical division, and in actual implementation, there may be other divisions, for example, multiple modules or components may be combined or integrated into another system, or some features may be omitted, or not implemented. The modules described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. In addition, functional modules in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more modules are integrated into one unit.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention or a part thereof, which essentially contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, a network device or a terminal, etc.) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: u disk, removable hard disk, ROM, RAM) magnetic or optical disk, or the like.

The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.

Claims

1. A method for identifying the state of a film and television resource is characterized by comprising the following steps:

2. The method as claimed in claim 1, wherein the movie resource to be inspected includes a suspected offline movie resource, and the identifying the movie resource to be inspected includes:

collecting the film watching behaviors of the user from the client;

3. The method as claimed in claim 2, wherein the viewing behavior of the user includes event generation time, device identification, event type and event content.

4. The method as claimed in claim 3, wherein said identifying the suspected offline movie resource according to the viewing behavior of the user comprises:

5. The method for identifying the state of the film resource as claimed in claim 4, wherein the generating the film resource-related event table according to the viewing behavior of the user comprises:

6. The method of claim 4, wherein the identifying the suspected offline movie resource according to the movie resource related event table comprises:

7. The method of claim 6, wherein the suspected offline movie resource rule comprises one of:

8. A movie resource state recognition method according to claim 5, wherein the event types include play, fast forward, fast backward, return, home page, and full screen; the event type classification comprises continuous playing, quitting playing and no event, wherein the continuous playing comprises fast forward, fast backward and full screen, and the quitting playing comprises return and homepage.

9. The method for identifying the status of a movie resource as claimed in claim 4, wherein the data corresponding to the identifier of the movie resource to be played at the beginning further comprises any one or more of the following: the number of the next film and television resources which are not played, the number of the third time interval between the playing of the next film and television resources, the number of the events which are continuously played, the number of no events, the number of the fourth time interval between the quitting of playing, the number of the fifth time interval between the continuous playing and the number of the sixth time interval between the continuous playing.

10. The method for identifying the state of the movie resource as claimed in claim 1, wherein the step of checking whether the movie resource to be checked is offline according to the screenshot or the log of the movie resource to be checked comprises at least one of the following steps:

11. The method for identifying the state of the movie resource as claimed in claim 1, wherein the step of checking whether the movie resource to be checked is offline according to the play screenshot or the play log of the movie resource to be checked comprises the steps of:

12. The method for identifying the state of the video resource according to claim 11, wherein the step of judging whether there are N consecutive screenshots including a picture popped up abnormally during playing comprises:

13. The method for identifying the state of the video resource according to claim 11, wherein said determining whether the video resource to be detected has an unchanged picture within a continuous period of time during the playing process according to the acquired screenshot comprises:

14. The method for identifying the state of the film and television resource as claimed in claim 13, wherein the method for judging the high similarity of the played screenshots comprises the following steps:

acquiring two continuous screenshots A and B from a played screenshot;

15. The method for identifying the status of the movie resource as claimed in claim 1, further comprising, after the identifying the movie resource to be detected and before the detecting whether the movie resource to be detected is offline according to the screenshot or the play log of the movie resource to be detected, the steps of:

16. The method as claimed in claim 15, wherein said issuing the data of the movie resource to be inspected to the inspection device comprises:

17. The method for identifying the status of a movie resource as claimed in claim 16, wherein the priority of the movie resource comprises: suspected offline movie and television resources > active movie and television resources > movie and television resources configured by an operation platform > movie and television resources added by a partner of a client > residual full amount of movie and television resources in a movie and television resource library sequentially traversed according to a first preset period.

18. The method for identifying the state of the movie resource as claimed in claim 1, further comprising, after the checking whether the movie resource to be checked is offline according to the screenshot or the log of the movie resource to be checked, the following steps:

19. A movie resource status recognition device, which comprises a processor and a memory, wherein the memory stores instructions executable by the processor, and the instructions are loaded and executed by the processor to implement the movie resource status recognition method according to any one of claims 1 to 18.

20. A computer-readable storage medium storing a computer program, wherein the computer program is executed by a processor to implement the movie resource status identification method according to any one of claims 1 to 18.