CN114092732A - Image work classification method, storage medium and device - Google Patents

Abstract

The disclosure relates to an image work classification method, a storage medium and a device, which relate to the technical field of computer application and improve the accuracy of image work classification. The specific scheme comprises the following steps: acquiring a first time length and the playing time length of the image works, wherein the first time length is a classification time length range corresponding to the total time length of the image works; acquiring an effective duration threshold corresponding to the first duration, wherein the effective duration threshold is used for representing the shortest duration for effectively playing the image works; and if the effective duration threshold is smaller than the playing duration of the image works, determining that the image works belong to the target type of image works.

Description

Image work classification method, storage medium and device

Technical Field

The present disclosure relates to the field of computer application technologies, and in particular, to a method, a storage medium, and an apparatus for classifying image works.

Background

The image works (such as video and other image works) are displayed on one screen of the user equipment in an immersive experience form (such as a slide-up and slide-down product form). In the experience form, the user equipment cannot detect the click operation, and cannot determine the classification of the image works according to the click operation, for example: it is determined whether the type of the image work is the type of the image work of interest to the viewing user. Generally, the user equipment determines the classification of the image works according to the playing time length of the acquired image works.

However, the above-mentioned method of determining the classification of the image works according to the playing duration of the image works often causes a problem of inaccurate classification of the image works.

Disclosure of Invention

The present disclosure provides an image work classification method, a storage medium, and an apparatus, which solve the problem of inaccurate classification of image works. The technical scheme of the disclosure is as follows:

according to a first aspect of the present disclosure, there is provided a method of classifying a work of images, the method comprising: acquiring a first time length and the playing time length of the image works, wherein the first time length is a classification time length range corresponding to the total time length of the image works; acquiring an effective duration threshold corresponding to the first duration, wherein the effective duration threshold is used for representing the shortest duration for effectively playing the image works; and if the effective duration threshold is smaller than the playing duration of the image works, determining that the image works belong to the target type of image works.

In an embodiment of the present disclosure: and the effective playing time length of the image works in the classification time length range is more accurately reflected according to the effective time length threshold value obtained by the first time length. And determining whether the image works belong to the image works of the target type (such as the image works of the type interested by the watching user) according to the effective duration threshold and the playing duration of the image works, wherein the determination result is more accurate.

Optionally, the obtaining the valid duration threshold corresponding to the first duration includes: acquiring the playing time of the target image work in a historical time period; the classification duration range corresponding to the total duration of the target image works is the same as the first duration, and the image works in the same classification duration range correspond to the same effective duration threshold; and counting the playing time of the target image work to obtain an effective time threshold corresponding to the first time.

Optionally, the "counting the playing time of the target image work to obtain the effective time threshold corresponding to the first time" includes: counting the invalid playing time of the target image work; the ratio of the number of the invalid playing time lengths to the total number of the playing time lengths is larger than a first preset threshold value; the total number of the playing time lengths is the total number of the playing time lengths of the target image works in the historical time period; and based on the invalid playing time length, obtaining an effective time length threshold value corresponding to the first time length by using a preset calculation method. The preset calculation method may be: and acquiring the invalid playing time length with the longest time length from the plurality of invalid playing time lengths as an effective time length threshold value corresponding to the first time length. Or, the invalid playing time length with the longest time length and the preset threshold are calculated and then taken as the valid time length threshold corresponding to the first time length, and illustratively, the sum of the invalid playing time length with the longest time length and the preset threshold is taken as the valid time length threshold corresponding to the first time length.

Optionally, the obtaining the valid duration threshold corresponding to the first duration includes: and inquiring to obtain the effective duration threshold corresponding to the first duration from a pre-stored corresponding relation table between the classification duration range and the effective duration threshold.

Optionally, the "acquiring the first time length" includes: acquiring the total duration of the image works; if the total duration of the image works is greater than or equal to the preset total duration threshold, taking the preset total duration threshold as a first duration; and if the total duration of the image works is smaller than the preset total duration threshold, taking the total duration of the image works as a first duration.

Optionally, the method further includes: counting a preselected total time length in the total time lengths of the plurality of image works; the ratio of the number of the image works in the total number of the plurality of image works in the total pre-selected duration is larger than a second preset threshold; and acquiring the preselected total time length meeting the preset condition from the preselected total time length as a preset total time length threshold value.

According to a second aspect of the present disclosure, there is provided an image work recommendation method including: responding to an image work recommendation request, wherein the image work recommendation request is used for requesting to acquire an image work, and the image work request comprises an account identifier; acquiring a recommendation feature corresponding to the account identifier, wherein the recommendation feature is obtained based on the image work of the target type determined by any one of the possible image work classification methods of the first aspect, and the recommendation feature includes at least one of a subject of the image work of the target type, a style of the image work of the target type, or a publisher of the image work of the target type; acquiring an image work including recommended features from an image work library; and recommending the acquired image works comprising the recommended features to the account indicated by the account identification.

In this way, the image works of the target type determined by the image work classification method provided by the first aspect can be more accurately determined as the image works of the type preferred by the account, so that the recommendation of the image works to the account based on the image works can be more accurate.

According to a third aspect of the present disclosure, there is provided an image work classification apparatus including: the first obtaining module is configured to obtain a first time length and the playing time length of the image works, wherein the first time length is a classification time length range corresponding to the total time length of the image works; the second acquisition module is configured to acquire an effective duration threshold corresponding to the first duration, and the effective duration threshold is used for representing the shortest duration for effectively playing the image works; and the determining module is configured to determine that the image work belongs to the target type of image work if the effective duration threshold is smaller than the playing duration of the image work.

Optionally, the second obtaining module is specifically configured to: acquiring the playing time of the target image work in a historical time period; the classification duration range corresponding to the total duration of the target image works is the same as the first duration, and the image works in the same classification duration range correspond to the same effective duration threshold; the image work classification device further comprises a counting module configured to count the playing time of the target image work to obtain an effective time threshold corresponding to the first time.

Optionally, the statistical module is specifically configured to: counting the invalid playing time of the target image work; the ratio of the number of the invalid playing time lengths to the total number of the playing time lengths is larger than a first preset threshold value; the total number of the playing time lengths is the total number of the playing time lengths of the target image works in the historical time period; and based on the invalid playing time length, obtaining an effective time length threshold value corresponding to the first time length by using a preset calculation method.

Optionally, the second obtaining module is specifically configured to: and inquiring to obtain the effective duration threshold corresponding to the first duration from a pre-stored corresponding relation table between the classification duration range and the effective duration threshold.

Optionally, the first obtaining module is specifically configured to: acquiring the total duration of the image works; if the total duration of the image works is greater than or equal to the preset total duration threshold, taking the preset total duration threshold as a first duration; and if the total duration of the image works is smaller than the preset total duration threshold, taking the total duration of the image works as a first duration.

Optionally, the statistical module is further configured to: counting a preselected total time length in the total time lengths of the plurality of image works; the ratio of the number of the image works in the total number of the plurality of image works in the total pre-selected duration is larger than a second preset threshold; and acquiring the preselected total time length meeting the preset condition from the preselected total time length as a preset total time length threshold value.

According to a fourth aspect of the present disclosure, there is provided an image work recommendation apparatus including: the response module is configured to respond to an image work recommendation request, wherein the image work recommendation request is used for requesting to acquire an image work, and the image work request comprises an account identifier; an obtaining module configured to obtain a recommendation feature corresponding to the account identifier, where the recommendation feature is obtained based on the image work of the target type determined by any one of the possible image work classification methods provided by the first aspect, and the recommendation feature includes at least one of a subject of the image work of the target type, a style of the image work of the target type, or a publisher of the image work of the target type; acquiring an image work including recommended features from an image work library; and the recommending module is configured to recommend the acquired image works comprising the recommending characteristics to the account indicated by the account identification.

According to a fifth aspect of the present disclosure, there is provided an electronic apparatus comprising: a processor; a memory for storing processor-executable instructions. Wherein the processor is configured to execute the instructions to implement the image work classification method shown in the first aspect and any one of the possible implementation manners of the first aspect, or to implement the image work recommendation method shown in the second aspect.

According to a sixth aspect of the present disclosure, there is provided a computer-readable storage medium, wherein instructions, when executed by a processor of an electronic device, enable the electronic device to perform the image work classification method as shown in the first aspect and any one of the possible implementations of the first aspect, or enable the electronic device to perform the image work recommendation method as shown in the second aspect.

According to a seventh aspect of the present disclosure, there is provided a computer program product directly loadable into an internal memory of an electronic device and containing software code, the computer program being capable of implementing the image work classification method according to the first aspect and any one of the possible implementations of the first aspect, or the image work recommendation method according to the second aspect, when loaded and executed by the electronic device.

Any one of the image work classification device, the image work recommendation device, the electronic device, the computer readable storage medium or the computer program product provided above is used for executing the corresponding method provided above, and therefore, the beneficial effects that can be achieved by the method can refer to the beneficial effects of the corresponding scheme in the corresponding method provided above, and are not repeated herein.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the disclosure and are not to be construed as limiting the disclosure.

Fig. 1 is a schematic view of a scene to which the image work classification method provided by the present disclosure is applied.

Fig. 2 is a flowchart illustrating a method of classifying a work of an image according to an exemplary embodiment.

FIG. 3 is a flow diagram illustrating another image work classification method according to an example embodiment.

FIG. 4 is a flowchart illustrating a method of image work recommendation, according to an example embodiment.

Fig. 5 is a block diagram illustrating a logical structure of an image work classification apparatus according to an exemplary embodiment.

Fig. 6 is a block diagram illustrating a logical structure of an image work recommendation apparatus according to an exemplary embodiment.

Fig. 7 is a block diagram illustrating a structure of an electronic device according to an example embodiment.

Detailed Description

In order to make the technical solutions of the present disclosure better understood by those of ordinary skill in the art, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.

The image work classification method provided by the embodiment of the disclosure can be applied to user equipment, and when the user equipment plays the image work, whether the image work is the type which is interested by a user watching the image work is determined according to the playing time length of the image work and the total time length of the image work.

The disclosed embodiments may be applied to a system architecture as shown in fig. 1, which includes an electronic device 10-1 for playing an image work. Optionally, the system further includes a server 10-2 for managing the display of the image work in the electronic device 10-1. The electronic device 10-1 and the server 10-2 are connected via a network.

The technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the drawings in the embodiments of the present disclosure, and it is obvious that the described embodiments are only a part of the embodiments of the present disclosure, and not all of the embodiments. All other embodiments, which can be derived by one of ordinary skill in the art from the embodiments disclosed herein without making any creative effort, shall fall within the scope of protection of the present disclosure.

It should be noted that the image work classification method and the image work recommendation method provided by the embodiment of the present disclosure may be applied to the electronic device 10-1 or the server 10-2 shown in fig. 1. The electronic device includes, but is not limited to, a mobile phone, a tablet computer, a notebook computer, a palm computer, a vehicle-mounted terminal, and the like. The server may be one server, or may be a server cluster composed of a plurality of servers, which is not limited in this disclosure.

As shown in fig. 2, fig. 2 is a flowchart illustrating a method of classifying a work of an image according to an exemplary embodiment. Applied to the electronic device 10-1, the method illustrated in FIG. 2 may include the steps of:

s100: the electronic device 10-1 acquires the first time length and the play time length of the image work. The first duration is a classification duration range corresponding to the total duration of the image works.

Specifically, the electronic device 10-1 obtains the start playing time and the end playing time of the image work, and obtains the playing duration of the image work according to the start playing time and the end playing time. The electronic equipment 10-1 acquires the total duration of the image works, and if the total duration of the image works is greater than or equal to a preset total duration threshold, the preset total duration threshold is used as a first duration; and if the total duration of the image works is smaller than the preset total duration threshold, taking the total duration of the image works as a first duration.

The electronic device 10-1 may determine the preset total duration threshold according to the following method: counting a preselected total time length in the total time lengths of the plurality of image works; the ratio of the number of the image works in the total number of the plurality of image works in the pre-selected total time length is larger than a second preset threshold value, and the pre-selected total time length meeting the preset condition is obtained from the pre-selected total time length and serves as the preset total time length threshold value.

In one example, the preselected total duration is a total duration of the image works that accounts for 90% of the total duration of all the image works in descending order. Assuming that the total time length of the plurality of image works includes 10 seconds, 15 seconds, 20 seconds, 30 seconds, 40 seconds, 50 seconds, 60 seconds and 65 seconds, 10 seconds, 15 seconds, 20 seconds, 30 seconds, 40 seconds, 50 seconds and 60 seconds are selected as the preselected total time length. And when the preset condition is the maximum total image work duration in the pre-selected total duration, acquiring 60 seconds as a preset total duration threshold.

In one possible implementation, the electronic device 10-1 obtains the first duration by:

the method comprises the following steps: the electronic device 10-1 acquires an index file corresponding to the image work. The index file may be an index file (e.g., m3u8) included in streaming media of dynamic bitrate adaptive technology (HTTP live streaming, HLS). The index file contains all the playing time information corresponding to the image works. For example, when a user views an image work at the electronic device 10-1, the electronic device 10-1 downloads the m3u8 index file corresponding to the image work.

Step two: the electronic device 10-1 parses the obtained index file to obtain the playing time lengths respectively corresponding to the slice files corresponding to the image work. The slice file specifically refers to a media slice file included in the streaming media. The playing time may be several seconds or several minutes, etc., and the embodiment of the disclosure does not limit this.

Step three: the electronic device 10-1 obtains the total duration of the image work according to the playing duration corresponding to each slice file.

Specifically, the electronic device 10-1 adds the playing time lengths corresponding to the acquired slice files, so as to obtain the total time length corresponding to the image work.

For example, the image work corresponds to 3 slice files, the playing time lengths corresponding to the 3 slice files obtained through analysis are respectively 4 seconds, 5 seconds and 6 seconds, and the playing time lengths corresponding to the 3 slice files are added, so that the total time length corresponding to the image work is 15 seconds.

Step four: the electronic device 10-1 obtains a first duration corresponding to the total duration according to the total duration of the image work.

For example, assume that the preset total duration threshold obtained by the electronic device 10-1 is 60 seconds. Based on the example in step three, the total duration of the image work is 15 seconds, 15 seconds is less than 60 seconds, and then the first duration of the image work is 15 seconds.

S101: the electronic device 10-1 obtains an effective duration threshold corresponding to the first duration, where the effective duration threshold is used to represent a shortest duration for effectively playing the image work.

In a possible implementation manner, the electronic device 10-1 queries and obtains the valid duration threshold corresponding to the first duration according to a pre-stored correspondence table between the classification duration range and the valid duration threshold.

It can be understood that the corresponding relationship between the classification duration range and the valid duration threshold pre-stored in the electronic device 10-1 may be obtained by statistical analysis of the electronic device 10-1 itself, or may be received by other electronic devices, which is not limited in this disclosure.

Specifically, the electronic device (e.g., the electronic device 10-1 or other electronic devices) may obtain the corresponding relationship between the total duration and the valid duration threshold through statistical analysis according to the following steps:

the method comprises the following steps: the electronic device obtains the playing time length and the total time length of the image works in the historical time period.

For example: the electronic device acquires the playing time length of one image work or a plurality of image works with the total time length of 20 seconds in the past week, acquires the playing time length of one image work or a plurality of image works with the total time length of 40 seconds in the past week, acquires the playing time length of one image work or a plurality of image works with the total time length of 60 seconds in the past week, and acquires the playing time length of one image work or a plurality of image works with the total time length of 65 seconds in the past week.

Step two: the electronic device divides the image works into image works in different classification time length ranges according to the total time length.

For example: the electronic device takes 20 seconds as a classification duration range, 40 seconds as a classification duration range, and 60 seconds as a classification duration range. The electronic device classifies the image works with the total duration of 60 seconds and the image works with the total duration of 65 seconds into the image works in the 60-second classification duration range, classifies the image works with the total duration of 20 seconds into the image works in the 20-second classification duration range, and classifies the image works with the total duration of 40 seconds into the image works in the 40-second classification duration range.

Step three: the electronic device obtains the quantiles of the playing time lengths of the image works in the same classification time length range.

Specifically, the electronic device obtains a plurality of playing durations of the image works in the same classification duration range, and analyzes the distribution of the plurality of playing durations to obtain quantiles of the plurality of playing durations. The quantile number is not limited in the present application, and the quantile number may be a median, a quartile, or the like, for example.

For example, the electronic device obtains the plurality of playing time lengths of the image work with the total time length of 40 seconds, wherein the plurality of playing time lengths are respectively 10 playing time lengths smaller than 10 seconds, 40 playing time lengths larger than or equal to 10 seconds and smaller than 30 seconds, 40 playing time lengths larger than or equal to 30 seconds and 10 playing time lengths larger than 30 seconds. It is understood that the plurality of playing time periods may be a playing time period of the image work with a total time period of 40 seconds, or may be a plurality of different playing time periods of the image work with a total time period of 40 seconds. The electronic device obtains the median of the plurality of playing time lengths as 30 seconds.

Step four: the electronic device determines an effective duration threshold of the image works in the classification duration range according to the obtained quantiles, and establishes a corresponding relation between the classification duration range and the effective duration threshold.

In a possible implementation manner, the electronic device selects one quantile from the acquired quantiles as an effective duration threshold of the image works in the duration range, and establishes a corresponding relationship between the classification duration range and the effective duration threshold.

In another possible implementation manner, the electronic device inputs the obtained quantiles into a preset algorithm based on the obtained quantiles to obtain an effective duration threshold of the image works in the classification duration range, and establishes a corresponding relationship between the classification duration range and the effective duration threshold. The preset algorithm may be to select a quantile from the obtained quantiles and perform mathematical operation (such as multiplication, addition, subtraction, division, etc.) on the selected quantile and a preset numerical value.

Based on the example in step three, the electronic device determines that the image work has a valid duration threshold value of 30 seconds and a total duration of 40 seconds, and establishes a correspondence relationship that the valid duration threshold value corresponding to the classification duration range of 40 seconds is 30 seconds.

In another possible implementation manner, the electronic device 10-1 obtains the playing time length of the target image work in the historical time period; the classification duration range corresponding to the total duration of the target image works is the same as the first duration, the image works in the same classification duration range correspond to the same effective duration threshold, and the electronic device 10-1 counts the playing duration of the target image works to obtain the effective duration threshold corresponding to the first duration.

Specifically, the electronic device 10-1 counts the invalid playing time of the target image work; the ratio of the number of the invalid playing time lengths to the total number of the playing time lengths is larger than a first preset threshold value; the total number of the playing time lengths is the total number of the playing time lengths of the target image works in the historical time period; the electronic device 10-1 obtains an effective duration threshold corresponding to the first duration by using a preset calculation method based on the invalid play duration. The preset calculation method may be to select the largest invalid playing time length from the invalid playing time lengths, and use the invalid playing time length as an effective time length threshold corresponding to the first time length. Or, taking a numerical value obtained by performing mathematical operation (such as multiplication, addition, subtraction and/or division) on the maximum invalid playing time length and a preset numerical value as the effective time length threshold corresponding to the first time length.

In a possible implementation manner, the electronic device 10-1 calculates an invalid playing time of the target image work, and obtains an effective time threshold corresponding to the first time based on the invalid playing time by using a preset calculation method, including the following steps:

the method comprises the following steps: the electronic device 10-1 acquires the play time length and the total time length of the target image work in the history time period.

For example: the electronic apparatus 10-1 acquires the play time period of one image work or a plurality of image works of which the total time period of the past one week is 20 seconds.

Step two: the electronic device 10-1 statistically analyzes the quantiles of the playing time lengths of the target image works.

Specifically, the electronic device 10-1 analyzes the distribution of the plurality of play durations to obtain the quantiles of the plurality of play durations. The quantile is not limited in the present disclosure, and the quantile may be a median, a quartile, or the like, for example.

Step three: the electronic device 10-1 obtains the invalid playing time length of the target image work according to the obtained quantiles.

Specifically, the electronic device 10-1 obtains the invalid playing time of the target image work according to the distribution of the obtained quantiles.

For example, the electronic device 10-1 obtains a plurality of playing time lengths of the image work with a total time length of 40 seconds, which are respectively 10 playing time lengths smaller than 10 seconds, 40 playing time lengths greater than or equal to 10 seconds and smaller than 30 seconds, 40 playing time lengths greater than or equal to 30 seconds, and 10 playing time lengths greater than 30 seconds. It is understood that the plurality of playing time periods may be a playing time period of the image work with a total time period of 40 seconds, or may be a plurality of different playing time periods of the image work with a total time period of 40 seconds. The electronic device 10-1 acquires the median of the plurality of play periods as 30 seconds. The electronic device 10-1 takes a play time period of 30 seconds or less as an invalid play time period of the target image work.

And step four, the electronic device 10-1 obtains an effective duration threshold corresponding to the first duration by using a preset calculation method based on the invalid playing duration.

Specifically, the electronic device 10-1 selects the largest invalid playing time length from the invalid playing time lengths, and uses the invalid playing time length as the valid time length threshold corresponding to the first time length. Or, taking a numerical value obtained by performing mathematical operation (such as multiplication, addition, subtraction and/or division) on the maximum invalid playing time length and a preset numerical value as the effective time length threshold corresponding to the first time length.

S102: the electronic device 10-1 determines that the image work belongs to the target type of image work according to the playing time length of the image work and the effective time length threshold corresponding to the first time length.

Specifically, the electronic device 10-1 determines whether the playing time of the image work is longer than the obtained valid time threshold, if so, determines that the image work belongs to the image work of the target type (for example, image work of the type that the viewing user is interested in), and if not, determines that the image work belongs to the image work of the non-target type (for example, image work of the type that the viewing user is not interested in).

It is understood that after the electronic device 10-1 performs the above S100, the first time length and the playing time length of the image work are transmitted to the server 10-2, and the above S101 to S102 are performed by the server 10-2. So that a new embodiment can be obtained.

In the above embodiment, the electronic device 10-1 more accurately reflects the effective playing time of the image work within the time range according to the effective time threshold obtained by the first time. And determining whether the image work is the image work of the target type according to the effective time length threshold and the playing time length of the image work, wherein the determination result is more accurate.

Fig. 3 is a flowchart illustrating another image work classification method according to an exemplary embodiment, as shown in fig. 3, the method including:

s200: the electronic device 10-1 acquires the first time length and the play time length of the image work. The first duration is a classification duration range corresponding to the total duration of the image works.

Specifically, reference is made to the detailed description of S100 in the foregoing embodiment, and details are not repeated.

S201: the electronic device 10-1 transmits the first time length and the play time length of the image work to the server 10-2.

S202: the server 10-2 inputs the first time length and the playing time length of the image works into the image work classification model to obtain whether the image works are the image works of the target type. The image work classification model may be a prediction model obtained by the server 10-2 through training according to the total duration of the plurality of image works obtained by the electronic device 10-1 or the server 10-2 in the above embodiment, the playing duration of the corresponding image work, and a result of whether the corresponding image work belongs to the image work of the type in which the viewing user is interested, where the input of the prediction model is the total duration of the image work and the playing duration of the corresponding image work, and the output is a prediction result of the type of the image work.

In one example, the server 10-2 inputs the image work classification model with a first duration of 30 seconds and a corresponding playing duration of 20 seconds, and obtains a prediction result that the image work has an 80% probability of belonging to the type of interest of the viewing user.

Subsequently, the server can analyze the content of the image works which are interested by the watching users, and further accurately push the image works which are possibly interested by the watching users to the watching users according to the analysis result.

It is understood that when the computing power of the electronic device 10-1 can support the computing in S202, the electronic device 10-1 will not need to execute S201, and the step in S202 is executed by the electronic device 10-1, thereby obtaining a new embodiment.

In the embodiment of the disclosure, according to the total time length and the playing time length of the image works, whether the image works belong to the image works of the type which is interested by the watching user is predicted by using the trained image work classification model, and the obtained prediction result is more accurate.

FIG. 4 is a flowchart illustrating a method for recommending image works according to an exemplary embodiment, applied to an electronic device (e.g., the electronic device 10-1 or the server 10-2) as shown in FIG. 4, the method including:

s300: the electronic device responds to an image work recommendation request requesting acquisition of an image work, the image work request including an account identification.

Specifically, when the electronic device is the electronic device 10-1, a client in the electronic device 10-1 receives an instruction that an account logs in the client through an account identifier or receives a refresh instruction in the process of playing an image work, and then generates an image work recommendation request.

When the electronic device is the server 10-2, the server 10-2 receives an image work recommendation request from the client, identifies an account identifier in the image work recommendation request, and facilitates subsequent video recommendation by obtaining corresponding recommendation features according to the account identifier. The account identification comprises an account nickname and/or an account number and the like.

S301: the electronic device obtains a recommendation feature corresponding to the account identification. The recommended features are obtained based on the image works of the target type determined by any image work classification method and belonging to the account indicated by the account identification. The recommended feature includes at least one of a subject of the image work of the target type, a genre of the image work of the target type, or a distributor of the image work of the target type.

Specifically, the electronic device obtains data of historical viewing image works of an account indicated by the account identifier, and classifies the historical viewing image works based on any image work classification method to obtain one or more target types of image works. The electronic device extracts and stores the features of the image works of the target type as recommended features of the account indicated by the account identification. The electronic device obtains the recommendation characteristics corresponding to the account identification through the method. Or the electronic device obtains the recommendation feature corresponding to the account identifier according to the stored correspondence between the account identifier and the recommendation feature.

It is to be understood that the process of analyzing the data of the image work viewed by the electronic device in history of the account indicated by the account identifier may be performed in response to the request for recommendation of the image work, or may be analyzed and stored in advance, and the disclosure is not limited thereto.

S302: the electronic device obtains an image work including the recommended feature from an image work library.

Specifically, the storage of image works in the image work library is associated with corresponding recommended features. Alternatively, the image works in the library of image works include the recommended features. The electronic device obtains an image work including the recommended feature from an image work library.

S303: the electronic device recommends the acquired image work including the recommended feature to the account indicated by the account identification.

Specifically, when the electronic apparatus is the electronic device 10-1, the electronic apparatus displays an image work including the recommended feature. When the electronic apparatus is the server 10-2, the electronic apparatus transmits the acquired image work including the recommended feature to the electronic device 10-1. The image work including the recommendation feature is used for client display, thereby completing image work recommendation.

In this way, after the image work classification method provided by the embodiment of the disclosure is used for classifying the historical viewing data of the account, the image works of the target type are analyzed to obtain the recommendation characteristic of the account, so that when the recommendation request of the image works including the account identifier of the account is responded, the image works related to the recommendation characteristic of the account can be more accurately obtained, and the image works recommended to the account are more accurate.

Fig. 5 is a block diagram illustrating a logical structure of an image work classification apparatus according to an exemplary embodiment. Referring to fig. 5, the image work classification apparatus 40 includes: a first obtaining module 401, a second obtaining module 402 and a determining module 403. The first obtaining module 401 is configured to obtain a first time length and a playing time length of the image work, where the first time length is a classification time length range corresponding to a total time length of the image work. A second obtaining module 402, configured to obtain an effective duration threshold corresponding to the first duration, where the effective duration threshold is used to represent a shortest duration for effectively playing the image work. A determining module 403 configured to determine that the image work belongs to the image work of the target type if the valid duration threshold is less than the playing duration of the image work. In conjunction with fig. 2, the first obtaining module 401 may be configured to perform S100, the second obtaining module 402 may be configured to perform S101, and the determining module 403 may be configured to perform S102. With reference to fig. 3, the first obtaining module 401 and the second obtaining module 402 may be configured to perform the receiving step in S201, and the determining module 403 may be configured to perform S202.

Optionally, the second obtaining module 402 is specifically configured to: acquiring the playing time of the target image work in a historical time period; the classification duration range corresponding to the total duration of the target image works is the same as the first duration, and the image works in the same classification duration range correspond to the same effective duration threshold; the image work classifying device 40 further includes a counting module 404 configured to count the playing time of the target image work to obtain an effective time threshold corresponding to the first time.

Optionally, the statistical module 404 is specifically configured to: counting the invalid playing time of the target image work; the ratio of the number of the invalid playing time lengths to the total number of the playing time lengths is larger than a first preset threshold value; the total number of the playing time lengths is the total number of the playing time lengths of the target image works in the historical time period; and based on the invalid playing time length, obtaining an effective time length threshold value corresponding to the first time length by using a preset calculation method.

Optionally, the second obtaining module 402 is specifically configured to: and inquiring to obtain the effective duration threshold corresponding to the first duration from a pre-stored corresponding relation table between the classification duration range and the effective duration threshold.

Optionally, the first obtaining module 402 is specifically configured to: acquiring the total duration of the image works; if the total duration of the image works is greater than or equal to the preset total duration threshold, taking the preset total duration threshold as a first duration; and if the total duration of the image works is smaller than the preset total duration threshold, taking the total duration of the image works as a first duration.

Optionally, the statistics module 404 is further configured to: counting a preselected total time length in the total time lengths of the plurality of image works; the ratio of the number of the image works in the total number of the plurality of image works in the total pre-selected duration is larger than a second preset threshold; and acquiring the preselected total time length meeting the preset condition from the preselected total time length as a preset total time length threshold value.

Fig. 6 is a block diagram illustrating a logical structure of an image work recommendation apparatus according to an exemplary embodiment. Referring to fig. 6, the image work recommendation apparatus 60 includes: a response module 601, an acquisition module 602, and a recommendation module 603. A response module 601, configured to respond to an image work recommendation request, where the image work recommendation request is used to request to acquire an image work, and the image work request includes an account identifier; an obtaining module 602, configured to obtain a recommendation feature corresponding to the account identifier, where the recommendation feature is obtained based on the image work of the target type determined by the image work classification method according to any one of claims 1 to 6, and the recommendation feature includes at least one of a subject of the image work of the target type, a genre of the image work of the target type, or a publisher of the image work of the target type; acquiring an image work including recommended features from an image work library; a recommending module 603 configured to recommend the obtained image work including the recommendation feature to the account indicated by the account identification.

Fig. 7 is a block diagram illustrating a structure of an electronic device according to an exemplary embodiment, where the electronic device 70 may be an image work classifying device or an image work recommending device, and the electronic device 70 may be: a smartphone, a tablet, a laptop, a desktop, or a server.

The electronic device 70 may include at least one processor 71, a communication bus 72, a memory 73, and at least one communication interface 74.

The processor 71 may be a Central Processing Unit (CPU), a micro-processing unit, an ASIC, or one or more integrated circuits for controlling the execution of programs according to the present disclosure.

The communication bus 72 may include a path for communicating information between the aforementioned components.

The communication interface 74 may be any device, such as a transceiver, for communicating with other devices or communication networks, such as a server, an ethernet, a Radio Access Network (RAN), a Wireless Local Area Network (WLAN), etc.

The memory 73 may be a read-only memory (ROM) or other type of static storage device that can store static information and instructions, a Random Access Memory (RAM) or other type of dynamic storage device that can store information and instructions, an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disk storage, optical disk storage (including compact disc, laser disc, optical disc, digital versatile disc, blu-ray disc, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer, but is not limited to these. The memory may be self-contained and connected to the processing unit by a bus. The memory may also be integrated with the processing unit.

The memory 73 is used for storing application program codes for executing the disclosed solution, and is controlled by the processor 71. The processor 71 is configured to execute application program code stored in the memory 73 to implement the functions of the disclosed method.

In particular implementations, processor 71 may include one or more CPUs such as CPU0 and CPU1 in fig. 7 as an example.

In particular implementations, the image work classification device 40 or the image work recommendation device 60 may include multiple processors, such as two processors 71 in FIG. 7, as one example. Each of these processors may be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. A processor herein may refer to one or more devices, circuits, and/or processing cores for processing data (e.g., computer program instructions).

In one embodiment, the image work classification apparatus 40 or the image work recommendation apparatus 60 may further include an input device 75 and an output device 76. The input device 75 is in communication with the processor 71 and can accept user input in a variety of ways. For example, the input device 75 may be a mouse, a keyboard, a touch screen device, or a sensing device, among others. The output device 76 is in communication with the processor 71 and may display information in a variety of ways. For example, the output device 76 may be a Liquid Crystal Display (LCD), a Light Emitting Diode (LED) display device, or the like.

In one example, in conjunction with fig. 5, the receiving functions of the first obtaining module 401 and the second obtaining module 402 in fig. 5 may be implemented by the communication interface 74, and the processing functions of the first obtaining module 401 and the second obtaining module 402 and the determining module 403 may be implemented by the processor 71 calling the application program code in the memory 73.

In one example, in conjunction with fig. 6, the receiving function of the obtaining module 602 in fig. 6 may be implemented by the communication interface 74, the receiving function of the obtaining module 602 may be implemented by the communication interface 74, and the processing function of the obtaining module 602, the responding module 601 and the recommending module 603 may all be implemented by the processor 71 calling the application code in the memory 73.

Those skilled in the art will appreciate that the configuration shown in fig. 7 does not constitute a limitation of the electronic device to which the present disclosure applies, and that the electronic device to which the present disclosure applies may include more or fewer components than those shown, or combine certain components, or employ a different arrangement of components.

The present disclosure also provides a computer-readable storage medium including instructions stored thereon, which when executed by a processor of a computer device, enable a computer to perform the image work classification method provided by the above-described illustrated embodiment. For example, the computer readable storage medium may be a memory 73 comprising instructions executable by the processor 71 of the terminal to perform the above described method. Alternatively, the computer readable storage medium may be a non-transitory computer readable storage medium, for example, which may be a ROM, a RAM, a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

The present disclosure also provides a computer program product containing instructions which, when run on a computer, cause the computer apparatus to perform the image work classification method provided by the above-described illustrative embodiments.

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 disclosure is intended to cover any variations, 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 will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims (10)

1. A method of classifying a work of an image, the method comprising:

acquiring a first time length and the playing time length of an image work, wherein the first time length is a classification time length range corresponding to the total time length of the image work;

obtaining an effective duration threshold corresponding to the first duration, wherein the effective duration threshold is used for representing the shortest duration for effectively playing the image works;

and if the effective duration threshold is smaller than the playing duration of the image works, determining that the image works belong to the image works of the target type.

2. The classification method according to claim 1, wherein the obtaining of the valid duration threshold corresponding to the first duration includes:

acquiring the playing time of the target image work in a historical time period; the classification duration range corresponding to the total duration of the target image works is the same as the first duration, and the image works in the same classification duration range correspond to the same effective duration threshold;

and counting the playing time of the target image work to obtain an effective time threshold corresponding to the first time.

3. The classification method according to claim 2, wherein the counting the playing duration of the target image work to obtain the effective duration threshold corresponding to the first duration comprises:

counting the invalid playing time of the target image work; the ratio of the number of the invalid playing time lengths to the total number of the playing time lengths is larger than a first preset threshold value; the total number of the playing time lengths is the total number of the playing time lengths of the target image works in the historical time period;

and based on the invalid playing time length, obtaining an effective time length threshold value corresponding to the first time length by using a preset calculation method.

4. The classification method according to claim 1, wherein the obtaining of the valid duration threshold corresponding to the first duration includes:

and inquiring to obtain the effective duration threshold corresponding to the first duration from a pre-stored corresponding relation table between the classification duration range and the effective duration threshold.

5. The classification method according to any one of claims 1 to 4, wherein the obtaining the first time length comprises:

acquiring the total duration of the image works;

if the total duration of the image works is greater than or equal to a preset total duration threshold, taking the preset total duration threshold as the first duration;

and if the total duration of the image works is smaller than the preset total duration threshold, taking the total duration of the image works as the first duration.

6. A method for recommending image works, the method comprising:

responding to an image work recommendation request, wherein the image work recommendation request is used for requesting to acquire an image work, and the image work request comprises an account identifier;

acquiring recommended features corresponding to the account identification, wherein the recommended features are obtained based on the image works of the target type determined by the image work classification method of any one of claims 1 to 6, and the recommended features comprise at least one of the subject of the image works of the target type, the style of the image works of the target type, or the publisher of the image works of the target type;

acquiring an image work including the recommended features from an image work library;

recommending the acquired image works comprising the recommended features to the account indicated by the account identification.

7. An image work classifying apparatus, comprising:

the system comprises a first acquisition module, a second acquisition module and a display module, wherein the first acquisition module is configured to acquire a first time length and the playing time length of an image work, and the first time length is a classification time length range corresponding to the total time length of the image work;

a second obtaining module configured to obtain an effective duration threshold corresponding to the first duration, where the effective duration threshold is used to represent a shortest duration for effectively playing the image work;

and the determining module is configured to determine that the image work belongs to the image work of the target type if the effective duration threshold is smaller than the playing duration of the image work.

8. An image work recommendation apparatus, comprising:

the system comprises a response module, a recommendation module and a recommendation module, wherein the response module is configured to respond to an image work recommendation request which is used for requesting to acquire an image work, and the image work request comprises an account identifier;

an obtaining module configured to obtain a recommendation feature corresponding to the account identifier, the recommendation feature being obtained based on the image work of the target type determined by the image work classification method according to any one of claims 1 to 5, the recommendation feature including at least one of a subject of the image work of the target type, a genre of the image work of the target type, or a publisher of the image work of the target type; acquiring an image work including the recommended features from an image work library;

and the recommending module is configured to recommend the acquired image works comprising the recommending characteristics to the account indicated by the account identification.

9. 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 image work classification method according to any one of claims 1 to 5 or to implement the image work recommendation method according to claim 6.

10. A computer-readable storage medium having instructions stored thereon, wherein the instructions in the computer-readable storage medium, when executed by a processor of an electronic device, enable the electronic device to perform the image work classification method of any one of claims 1-5 or implement the image work recommendation method of claim 6.

Images