Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present 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.
Referring to fig. 1, fig. 1 is a flowchart of an information processing method according to an embodiment of the present invention, and as shown in fig. 1, the method includes the following steps:
step 101, obtaining search information of resources to be transferred in a target video.
The target video comprises video content of a preset type, and resources to be transferred related to the video content of the preset type are arranged in the target video.
Wherein the target video may be any video. The preset type of video content may be, for example, advertisements embedded in the target video, songs inserted in the target video, and the like. The resource to be transferred may be, for example, a red packet, and the red packet may have a certain amount of money.
In the implementation of the present invention, the resource to be transferred is associated with the preset type of video content. By correlation, it is understood that a preset type of video content may be associated by an operation (e.g., clicking, etc.) on a resource to be transferred. For example, the resource to be transferred may be set in the video content of the preset type, and then, by performing operations such as clicking on the resource to be transferred, the video content of the preset type may be located, so that the attention and the click rate of the video content are increased. For another example, the resource to be transferred is not set in the preset type of video content, but the resource to be transferred can still be located on the preset type of video content or the content related to the preset type of content through clicking and other operations, so that the attention and the click rate of the video content are increased.
In this step, a first input to the target video by a user may be received, and the search information is obtained in response to the first input, wherein the search information includes at least one of:
and the first input is a corresponding target time in the target video, and the first input is a target position in a display picture of the target video.
The first input may be, for example, a click input, a double click, an in-and-out input, or the like.
For example, when the user clicks the target video, the display time of the video frame corresponding to the clicking operation of the user in the target video is the target time; the position of the click operation of the user on the screen can be converted into the position of the click operation in the display picture of the target video, namely the target position.
In order to limit the operation times of the user, in the embodiment of the present invention, an input accumulation time may be obtained in response to the first input, and the search information may be obtained when the input accumulation time is smaller than a preset click time. Wherein, the preset click times can be set at will. And if the input accumulated times are more than the preset click times, prompting information can be sent to the user.
And 102, acquiring the setting information of the resource to be transferred.
In the embodiment of the present invention, the setting information of the resource to be transferred set by the resource to be transferred setting device can be acquired. The resource setting device to be transferred may be, for example, an advertisement system. Then, the user of the advertisement system can set the setting information through the advertisement system, and the director can also set the setting information.
When a user of the advertisement system sets the setting information, the user may set the resource to be transferred on the advertisement object or character and set the setting information. When the director sets the setting information, the director can optionally select an object or a figure to set the resource to be transferred and set the setting information.
In an embodiment of the present invention, the setting information includes: the effective time period of the resource to be transferred in the target video, the information of the carrier of the resource to be transferred and the resource value of the resource to be transferred.
The valid time period refers to a time period in which the resource to be transferred is displayed in the target video and can be searched, and may be, for example, 1 minute 10 seconds to 1 minute 30 seconds of the target video. During this time period, the user may click on the target video to find the resource to be transferred.
Wherein the carrier of the resource to be transferred is preset or designated by the user. The carrier of the resource to be transferred may be, for example, an object or a person, and the resource value of the resource to be transferred may be, for example, a money amount, and in the case of a red packet, the resource value may be a money amount of a red packet.
And 103, acquiring video characteristic analysis parameters of the target video.
In this step, the characteristic parameters of the resource to be transferred may be obtained first. For example, the characteristic parameters of the resources to be transferred are obtained by analyzing the setting information. Wherein, the characteristic parameters of the resources to be transferred comprise: the effective time period of the resource to be transferred in the target video and the information of the carrier of the resource to be transferred. And then, performing video characteristic analysis on the video sub-segments according to the information of the carrier of the resource to be transferred to obtain the video characteristic analysis parameters.
Wherein the video feature analysis parameters include: the display time of the target carrier of the resources to be transferred in the target video, the display position of the target carrier in the display picture of the target video and the information of the target carrier, wherein the target carrier is any one or more carriers in the carriers of the resources to be transferred. Through the above process, the target carrier, such as a person or an object, carrying the resource to be transferred can be identified within the valid time period.
The method for analyzing the video features may include, but is not limited to, using a deep learning model such as FaceNet to identify and locate a human face, and identifying a target carrier such as a human or an object by combining an object detection and identification algorithm (e.g., RCNN (Region-CNN), YoLo (You Only Look Once), SSD (Single Shot Multi Box Detector), etc.).
And step 104, determining whether the search information corresponds to the resource to be transferred or not according to the search information, the setting information and the video characteristic analysis parameter.
In this step, in a case that the search information includes a target time corresponding to the first input in the target video and a target position of the first input in a display screen of the target video, matching the target time corresponding to the first input in the target video and the target position of the first input in the display screen of the target video in the search information with a display time of a target carrier of the resource to be transferred in the video feature analysis parameter in the target video and a display position of the target carrier in the display screen of the target video, and obtaining information of a candidate target carrier. And then matching the target time corresponding to the first input in the target video and the information of the candidate target carrier in the search information with the effective time period of the resource to be transferred in the target video and the information of the carrier of the resource to be transferred in the setting information, and determining whether the candidate target carrier carries the resource to be transferred.
In the embodiment of the invention, whether the search information corresponds to the resource to be transferred is determined according to the search information of the resource to be transferred, the setting information of the resource to be transferred and the video characteristic analysis parameter of the target video. Because the resource to be transferred is related to the preset type of video content in the target video, the attention to the preset type of video content is also improved while the resource to be transferred is searched, and therefore the exposure of the preset type of video content implanted in the target video is improved.
In addition, in practical application, the resource to be transferred can be set at any position in the display screen of the target video. Then, in this case, the search information includes a corresponding target time of the first input in the target video. Accordingly, the video feature analysis parameters may include: the display time of the target carrier of the resource to be transferred in the target video, and the information of the target carrier. In this step, the target time corresponding to the first input in the target video may be matched with the display time of the target carrier of the resource to be transferred in the video feature analysis parameter in the target video, so as to obtain information of a candidate target carrier. And then matching the target time corresponding to the first input in the target video and the information of the candidate target carrier in the search information with the effective time period of the resource to be transferred in the target video and the information of the carrier of the resource to be transferred in the setting information, and determining whether the candidate target carrier carries the resource to be transferred.
In addition, the resource to be transferred can be set at any time when the target video is played. Then, in this case, the search information includes a target position of the first input in the display of the target video. The video feature analysis parameters include: the display position of the object carrier in the display picture of the object video and the information of the object carrier. In this step, the target position of the first input in the display screen of the target video may be matched with the display position of the target carrier in the video feature analysis parameter in the display screen of the target video, so as to obtain information of a candidate target carrier. And then, matching the target position of the first input in the search information in the display picture of the target video and the information of the candidate target carrier with the display position of the target carrier in the display picture of the target video and the information of the target carrier in the setting information, and determining whether the candidate target carrier carries the resource to be transferred.
On the basis of the above embodiment, to further improve the exposure level, the method may further include: and sending a notification message to the resource setting device to be transferred according to the search information and the setting information, so that the resource setting device to be transferred calculates the cost according to the notification message. For example, the advertisement system may calculate an advertisement fee based on the notification message.
On the basis of the above embodiment, to facilitate the user to find the resource to be transferred, the method may further include: and displaying prompt information, wherein the prompt information is used for prompting that the target video carries the resource to be transferred.
Hereinafter, the implementation process of the embodiment of the present invention is described by taking the resource to be transferred as a red packet as an example.
As shown in fig. 2(a) and 2(b), the system structure of the embodiment of the present invention is schematically illustrated. As shown in fig. 2(a), the system may include: the system comprises a video red packet setting server 201, an advertisement system 202, a video analysis server 203, a video red packet server 204, a playing terminal 205, an encoder 206, a streaming media server 207 and the like.
The video red packet setting server 201 is configured to set a setting parameter of a red packet. In practical application, the director can set the setting parameters through the video red packet setting server, wherein the setting parameters are as follows: red-packed video time periods T < T1, T2>, and a regular set of red-packed.
Wherein the rule set for the red envelope may be set by an advertiser of the advertising system. The advertisement system 202 is used for acquiring the setting rule of the red envelope, calculating the corresponding advertisement fee, and the like.
In one approach, the red envelope is placed over the article on which the advertisement is placed. The advertiser may set the following rules for placing an advertisement: red envelope H < time period < th1, th2>, advertising item o, red envelope size a >. For example, < first third of red packet video period T < T1, T2>, coca-cola, 100 yuan >, < second third of red packet video period T < T1, T2>, coca-cola, 300 yuan >. The period < th1, th2> refers to a period in which the red packet is valid in the video, that is, the red packet occurs during the period < th1, th2> of the video. Through the setting, the money amount set by the red packet found at the later stage of the video time period is larger, because the red packet is found at the later stage, the time for finding the red packet in the video is longer, the time for seeing the coca cola is also longer, and the larger red packet is set.
There is also a regular arrangement of red envelope, which is arranged on randomly selected people or objects. The settings or people of the red envelope are randomly selected, for example, the randomly selected objects may be people or objects that appear within a red envelope video time period < th1, th2 >. Then, the setup parameters for the red packet are as follows: red envelope H < time period < th1, th2>, randomly selected random object, red envelope size >.
The video red packet setting server 201 sends the obtained setting parameter H of the red packet to the video red packet server 204. Meanwhile, the video red envelope setting server 201 transmits a message M containing < red envelope video start time t1, red envelope video end time t2, K objects or characters O < O1, O2, …, ok > >, hiding the red envelope, to the video analysis server 203. Wherein, the red-packed video start time t1 and the red-packed video end time t2 are determined according to the time period < th1, th2> in the red-packed H.
The red packet setting H and the message M may be JSON (JavaScript Object Notation) or Protobuf format messages.
After receiving the original video stream, the video analysis server 203 analyzes the video content of the video time period < red packet video start time t1 and red packet video end time t2> according to the message M to obtain video content data D < time td, position pd, object or character oi >, and sends the video content data D < time td, position pd, object or character oi > to the video feature library buffer. In the process, the video analysis server mainly utilizes a video object or person identification technology to identify objects or persons, can use a deep learning model such as FaceNet and the like to identify and position the faces, and combines an object detection and identification algorithm to identify the persons or the objects and perform corresponding positioning.
The video red packet server 204 receives and buffers the red packet setting message H < time period < th1, th2>, the advertisement item o, and the red packet size a > sent by the video red packet setting server 201. Meanwhile, the video red packet server 204 sets the number N of times that the user can find the red packet, and pushes a message to the play terminal 205 according to the message H to prompt that the red packet is about to appear. The cast terminal displays a prompt to the user that there is a red pack for a red pack video period T < T1, T2 >. The user can find the red pack by clicking on the person or thing on the screen, with N chances. In the above process, the video red packet server 204 and the playback terminal 205 communicate via a WebSocket based on an HTTP Protocol (HyperText Transfer Protocol).
Then, the video red packet server 204 receives the message S < the video frame time ts of the user finding click, and the position ps > of the user finding the clicked video of the red packet, which is fed back by the playing terminal 205 and is used by the user to find the clicked red packet. The video red packet server 204 receives the WebSocket communication based on HTTP from the play terminal 205.
The video red packet server 204 searches for the cached data D in the matching video feature library for time td, position pd, object or character oi', and judges whether the user finds the red packet according to the received message S < the video frame time ts for the user to find the red packet click, the position ps of the video frame for the user to find the red packet click > and the cached red packet setting H < the time period, the object or character, the red packet size >.
Specifically, the video red packet server 204 finds the object or person Oi by matching the video time ts in the message S with the time td and the position Pd in the data D with the position ps; then, by matching the time ts of the message S and the found object or task Oi with the time period and the object in the red-envelope setting message H, it can be determined whether the input of the user can find the red envelope.
Meanwhile, the video red packet server 204 accumulates the number of times that the user searches for a red packet, and if the accumulated number of times exceeds the set number of times N, the search is invalid. According to the search result, the video red packet server 204 sends the result of searching the red packet to the playing terminal 205, such as "find the original red packet" or "find the red packet more than N times".
In addition, the video red packet server 204 may combine the message S that the user finds the click of the red packet with the red packet setting message H to form a message body < S, H >, and send the message body < S, H > to the advertisement system. Then the advertisement system may design additional advertisement enhancement exposure charges based on the < S, H > message.
For example: when a user clicks a certain embedded advertisement when finding an advertisement, the advertisement system calculates the cost brought by the number of clicks:
firstly, calculating the exposure time of an item o in a user i, namely the click time tx of the user for finding a red packet for the last time-the red packet video start time th 1; then, the exposure time of the item o to the user i is converted into the number of clicks, where the number of clicks is the exposure time of the item o to the user i/the total playing time of the item o × the click coefficient r, where r is set by the advertising operator. And then calculating the cost through the number of clicks.
The original video stream is coded by the coder, then sent to the streaming media server, processed by the streaming media server, and then sent to the playing terminal for playing. In the playing process, if the playing terminal 205 receives the input of the user, it completes message interaction with the video red packet server 204 in the WebSocket manner of HTTP, and at the same time, completes the related user prompt display according to the message of the video red packet server 204.
The implementation principle of the system shown in fig. 2(b) is the same as that shown in fig. 2 (a). The difference is that the system shown in fig. 2(a) is applied in live scenes, and the system shown in fig. 2(b) is applied in video-on-demand scenes. Then, in fig. 2(a), the received original video is a live video stream, such as a live attraction program. In this case, the received video may be raw non-encoded video data; if encoded video data is received, decoding is required first. In fig. 2(b), the received video is the existing video, the video obtained from a CDN (Content Delivery Network) video source 209 is decoded by a decoder 210 and then sent to a video analysis server 203 for analysis and processing, and meanwhile, the video obtained from a CND video source is sent to a streaming media server 207.
One scenario in which embodiments of the present invention may be applied is that, in a certain integrated program, before a program with an embedded advertisement starts, a television viewer is prompted, and in the next few minutes, a red packet (normal television program and program content, and normal broadcast of a rebroadcast picture) may be hidden on some people or articles (including embedded advertisement products) in a television screen, and the viewer is asked to watch and search carefully. Through the video understanding technology, people or objects in the video are identified, and the red packet is intelligently arranged on the identified people or objects. The viewer can find the red envelope by clicking on the screen where the person or thing is located, and a player has only K opportunities. In this way, the implanted advertisement can have a higher exposure effect. The advertiser can buy the red envelope and directly put the red envelope on the product implanted by the advertiser, and also choose not to put the red envelope on the product implanted by the advertiser.
One scenario in which embodiments of the present invention may also be applied is that, in a video-on-demand program, before a video segment with an advertisement embedded therein begins, the user is prompted, and within the next few minutes, some objects (including the embedded advertisement product) appearing in the video or those objects may be hidden with red packets (normal tv programs and program contents, and normal broadcast of the rebroadcast picture), and the user is asked to watch and search carefully. Through the video understanding technology, people or objects in the video are identified, and the red packet is intelligently arranged on the identified people or objects. The viewer can find the red envelope by clicking on the position of the person or thing on the screen, and a player has only K opportunities. In this way, the implanted advertisement can have higher exposure effect. The advertiser can buy the red envelope and directly put the red envelope on the product implanted by the advertiser, and also choose not to put the red envelope on the product implanted by the advertiser.
The exposure degree of the implanted advertisements can be effectively increased in the two scenes, the exposure degree of different implanted advertisements can be improved through the red packet setting, and advertisement charging calculation can be carried out through the exposure degree.
Therefore, in the embodiment of the invention, the red packet is combined with the content of the video content, so that the flexibility of red packet setting is improved, and more importantly, the effective exposure rate of the video embedded advertisement is effectively increased by utilizing the video entertainment interaction mode of finding the red packet.
The embodiment of the invention also provides an information processing device. Referring to fig. 3, fig. 3 is a block diagram of an information processing apparatus according to an embodiment of the present invention. As shown in fig. 3, the information processing apparatus 300 includes:
a first obtaining module 301, configured to obtain search information of a resource to be transferred in a target video; the target video comprises video content of a preset type, and resources to be transferred related to the video content of the preset type are arranged in the target video; a second obtaining module 302, configured to obtain setting information of the resource to be transferred; a third obtaining module 303, configured to obtain video feature analysis parameters of the target video; the processing module 304 is configured to determine whether the search information corresponds to a resource to be transferred according to the search information, the setting information, and the video feature analysis parameter.
Optionally, the first obtaining module 301 includes:
the receiving submodule is used for receiving a first input of a user to the target video; the obtaining sub-module is configured to obtain the search information in response to the first input, where the search information includes a target time corresponding to the first input in the target video, and a target position of the first input in a display picture of the target video.
Optionally, the obtaining sub-module includes: a first obtaining unit, configured to obtain an input accumulation number in response to the first input; and the second acquisition unit is used for acquiring the search information under the condition that the input accumulation times are less than the preset click times.
Optionally, the second obtaining module 302 is specifically configured to obtain setting information of the resource to be transferred, where the setting information is set by the resource setting device to be transferred, and the setting information includes: the effective time period of the resource to be transferred in the target video, the information of the carrier of the resource to be transferred and the resource value of the resource to be transferred.
Optionally, the third obtaining module 303 includes:
the first obtaining submodule is used for obtaining the characteristic parameters of the resources to be transferred, wherein the characteristic parameters of the resources to be transferred include: the effective time period of the resource to be transferred in the target video and the information of the carrier of the resource to be transferred; the positioning sub-module is used for positioning the video sub-segment corresponding to the effective time period in the target video according to the effective time period; the analysis submodule is used for carrying out video characteristic analysis on the video sub-segment according to the information of the carrier of the resource to be transferred to obtain the video characteristic analysis parameters; wherein the video feature analysis parameters include: the display time of the target carrier of the resources to be transferred in the target video, the display position of the target carrier in the display picture of the target video and the information of the target carrier, wherein the target carrier is any one or more carriers in the carriers of the resources to be transferred.
Optionally, the processing module 304 includes:
a first matching sub-module, configured to, when the search information includes a target time corresponding to the first input in the target video and a target position of the first input in a display screen of the target video, match the target time corresponding to the first input in the search information in the target video and the target position of the first input in the display screen of the target video with a display time of a target carrier of the resource to be transferred in the video feature analysis parameter in the target video and a display position of the target carrier in the display screen of the target video, and obtain information of a candidate target carrier;
and the second matching submodule is used for matching the target time corresponding to the first input in the target video in the search information and the information of the candidate target carrier with the effective time period of the resource to be transferred in the target video in the setting information and the information of the carrier of the resource to be transferred, and determining whether the candidate target carrier carries the resource to be transferred.
Optionally, the apparatus may further include: and the sending module is used for sending a notification message to the resource setting device to be transferred according to the search information and the setting information so that the resource setting device to be transferred calculates the cost according to the notification message.
Optionally, the apparatus may further include: and the display module is used for displaying prompt information, and the prompt information is used for prompting that the target video carries the resource to be transferred.
The apparatus provided in the embodiment of the present invention may implement the method embodiments, and the implementation principle and the technical effect are similar, which are not described herein again.
As shown in fig. 4, the electronic device according to the embodiment of the present invention includes: the processor 400, which is used to read the program in the memory 420, executes the following processes:
acquiring search information of resources to be transferred in a target video; the target video comprises video content of a preset type, and resources to be transferred related to the video content of the preset type are arranged in the target video;
acquiring the setting information of the resource to be transferred;
acquiring video characteristic analysis parameters of the target video;
and determining whether the search information corresponds to the resource to be transferred or not according to the search information, the setting information and the video characteristic analysis parameter.
A transceiver 410 for receiving and transmitting data under the control of the processor 400.
Where in fig. 4, the bus architecture may include any number of interconnected buses and bridges, with various circuits of one or more processors, represented by processor 400, and memory, represented by memory 420, being linked together. The bus architecture may also link together various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. The bus interface provides an interface. The transceiver 410 may be a number of elements, including a transmitter and a transceiver, providing a means for communicating with various other apparatus over a transmission medium. The processor 400 is responsible for managing the bus architecture and general processing, and the memory 420 may store data used by the processor 400 in performing operations.
The processor 400 is responsible for managing the bus architecture and general processing, and the memory 420 may store data used by the processor 400 in performing operations.
The processor 400 is further adapted to read the computer program and perform the following steps:
receiving a first input of a user to the target video;
and obtaining the search information in response to the first input, wherein the search information comprises a target time corresponding to the first input in the target video, and the target position of the first input in the display picture of the target video.
The processor 400 is further adapted to read the computer program and perform the following steps:
obtaining an input accumulation number in response to the first input;
and acquiring the search information under the condition that the input accumulation times are smaller than the preset click times.
The processor 400 is further adapted to read the computer program and perform the following steps:
acquiring setting information of resources to be transferred, which is set by a resource setting device to be transferred, wherein the setting information includes: the effective time period of the resource to be transferred in the target video, the information of the carrier of the resource to be transferred and the resource value of the resource to be transferred.
The processor 400 is further adapted to read the computer program and perform the following steps:
acquiring characteristic parameters of resources to be transferred, wherein the characteristic parameters of the resources to be transferred comprise: the effective time period of the resource to be transferred in the target video and the information of the carrier of the resource to be transferred;
according to the effective time period, positioning a video sub-segment corresponding to the effective time period in the target video;
performing video characteristic analysis on the video sub-segments according to the information of the carrier of the resource to be transferred to obtain video characteristic analysis parameters;
wherein the video feature analysis parameters include: the display time of the target carrier of the resources to be transferred in the target video, the display position of the target carrier in the display picture of the target video and the information of the target carrier, wherein the target carrier is any one or more carriers in the carriers of the resources to be transferred.
The processor 400 is further adapted to read the computer program and perform the following steps:
under the condition that the search information comprises a target time corresponding to the first input in the target video and a target position of the first input in a display picture of the target video, matching the target time corresponding to the first input in the target video and the target position of the first input in the display picture of the target video in the search information with the display time of the target carrier of the resource to be transferred in the target video and the display position of the target carrier in the display picture of the target video in the video feature analysis parameters to obtain information of candidate target carriers;
matching the target time corresponding to the first input in the target video and the information of the candidate target carrier in the search information with the effective time period of the resource to be transferred in the target video and the information of the carrier of the resource to be transferred in the setting information, and determining whether the candidate target carrier carries the resource to be transferred.
The processor 400 is further adapted to read the computer program and perform the following steps:
and sending a notification message to the resource setting device to be transferred according to the search information and the setting information, so that the resource setting device to be transferred calculates the cost according to the notification message.
And displaying prompt information, wherein the prompt information is used for prompting that the target video carries the resource to be transferred.
The embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program implements each process of the information processing method embodiment, and can achieve the same technical effect, and in order to avoid repetition, details are not repeated here.
In the several embodiments provided in the present application, it should be understood that the disclosed method and apparatus may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be physically included alone, or two or more units may be integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
The integrated unit implemented in the form of a software functional unit may be stored in a computer readable storage medium. The software functional unit is stored in a storage medium and includes several instructions to enable a computer device (which may be a personal computer, a server, or a network device) to execute some steps of the transceiving method according to various embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention as defined in the appended claims.