WO2019114633A1

WO2019114633A1 - Image information processing method and apparatus, and storage medium

Info

Publication number: WO2019114633A1
Application number: PCT/CN2018/119861
Authority: WO
Inventors: 李赋然
Original assignee: 李赋然
Priority date: 2017-12-13
Filing date: 2018-12-07
Publication date: 2019-06-20
Also published as: CN108062381B; CN108062381A

Abstract

Disclosed is an image information processing method, comprising: at least shielding a part of the content of an image; providing a question related to the image; and acquiring answer information sent by a user when answering the question. By means of the method in the present invention, instead of passively accepting information delivered by an image, a user gives feedback regarding the information delivered by the image by answering a question; in this way, the obtained answer information and the user's understanding and cognition about the content of the image are closely associated, thereby facilitating the reflection of the user's ideas about the content of the image; therefore, collected user data can be closely related to the content of the image information, thereby facilitating the mining of the potential data value of the image by means of the collected data. Furthermore, also provided are an image information processing apparatus based on the method, and a storage medium.

Description

Image information processing method, device and storage medium

Technical field

The present invention relates to the field of media propagation technologies, and in particular, to an image information processing method, apparatus and storage medium.

Background technique

In Internet technology, pictures and videos are more common sources of information. With the popularization of smart terminals represented by smart phones and the increasing data throughput and information transmission speed of communication networks, a large number of pictures and video files are continuously generated at a geometrical rate. Although a large number of pictures and video files are stored in the Internet company's servers, the data values of these pictures and video files are not fully exploited and utilized.

In the process of advertising the information dissemination, advertisers usually display their products in the form of text, pictures, videos, and so on. The current technology mainly analyzes and utilizes the data provided by the user through the keyword classification of the text, the browsing habit of the browser, the viewing preference of the video, etc., and pushes the advertisement to the user based on a certain algorithm. When a user browses an advertisement, most of the cases are passive ad acceptance behaviors, and it is difficult to count the true thoughts of the user. Although a large amount of pictures and video data are generated in the process of advertising, these pictures and videos themselves cannot be related to the propagation effect of advertisements, and the value of pictures and video data with great data potential cannot be fully utilized.

In addition, some video games include content related to image interaction, but they are still completely independent of entertainment and fun, and still do not take into account the data value of the image.

Summary of the invention

An object of the present invention is to provide an image information processing method for collecting information related to image content fed back by an image information content during propagation of the image information, thereby digging the data value of the image information.

In order to achieve the above object, an image information processing method provided by the present invention includes:

Blocking at least part of the content of the image;

Providing questions related to the image; and

Get the answer information sent by the user when answering the question.

Optionally or preferably, before the obtaining the answer information sent by the user when answering the question, the method further includes:

Obtain information generated by the user in preparation for answering the question.

Optionally or preferably, the obtaining information generated by the user in preparing to answer the question comprises:

Acquiring information generated by the user during the first operation of the masked portion of the image, the first operation being capable of removing the mask such that the image is displayed by the content of the masked portion.

Optionally or preferably, the information generated during the performing the first operation includes at least one of removing information of the occlusion area, masking area removal trajectory information, and time information.

Optionally or preferably, the removing the information of the obscured area comprises removing the area of the obscured area and/or removing the position of the obscured area.

Optionally or preferably, the method further comprises: dividing the image into a plurality of units, and assigning value information to each unit; and the obtaining information generated by the acquiring user during the performing the first operation on the masked portion of the image comprises: The value information of the unit that is revealed after the user removes the masked area is counted.

Alternatively or preferably, the value information for the unit is determined based on the relevance of the unit to the question.

Optionally or preferably, after the obtaining the answer information fed back by the user when answering the question, the method further includes:

The answer information sent by the plurality of users and the information generated in the process of preparing to answer the question are counted, and the value information of the unit is adjusted according to the statistical result.

Optionally or preferably, said assigning value information to each unit comprises assigning a score to each unit, the size of said score being positively correlated with the degree of relevance of said unit to said question.

Optionally or preferably, the method further comprises: before acquiring information generated by the user in preparing to answer the question, the method further comprising:

Selecting a first region in a portion of the image that is obscured, the first region being selected as an area that assists the user in answering the question after learning the content;

Acquiring the information generated by the user in preparing to answer the question includes: acquiring a second area of the user to remove the masked portion of the image, so as to combine the answer information of the user and the degree of fit of the first area and the second area The accuracy of the first region selection is determined.

Optionally or preferably, after the obtaining the answer information sent by the user when answering the question, the method further includes:

Acquiring the verification information sent by the user, the verification information including feedback information of the correctness and/or accuracy of the user and the preset answer corresponding to the question.

Optionally or preferably, after the obtaining the verification information sent by the user, the method further comprises: sending the reward information to the user according to a predetermined policy.

Optionally or preferably, the obtaining information generated by the user in preparing to answer the question further comprises: acquiring time information generated by the user in preparing to answer the question.

Optionally or preferably, the at least part of the content of the shadow image comprises:

Generating a masked area;

The position of the obscured region on the image is moved in accordance with a predetermined strategy.

Acquiring information generated by the user in preparing to answer the question; the information generated by the user in preparing to answer the question includes at least one of time information, moving speed information of the obscured area, and movement track information.

Optionally or preferably, the method further comprises:

The information obtained from the user is counted to establish a data model and/or to quantify the image.

Optionally or preferably, the method further comprises:

Encrypting at least some of the information generated by the user in preparing to answer the question by the encryption algorithm to form a key;

Obtaining verification information sent by the user, so that the user uses the key to compete for the reward obtained according to the sending of the verification information;

The verification information includes feedback information of the user on the correctness and/or accuracy of the question and/or the preset answer corresponding to the question.

Optionally or preferably, the image comprises a multi-layer superimposed image, wherein the image located in the upper layer is determined as the obscuring layer of the next layer image; the method further comprises:

Obtaining a second operation performed by the user; the second operation is capable of removing content displayed by the image of the previous layer such that the content of the next layer of image is displayed.

Optionally or preferably, the method further comprises:

Obtaining a third operation performed by the user; the third operation can mask an area displayed by the underlying image and cause the content of the upper layer image to be displayed.

Alternatively or preferably, the image consists of a plurality of sub-images, at least part of which is assigned a question associated with the sub-image.

In another aspect, the present invention provides an image information processing apparatus, including:

a masking module for shielding at least part of the content of the image;

a questioning module for providing questions related to the image;

The first obtaining module is configured to obtain answer information sent by the user when answering the question.

Optionally or preferably, it further comprises:

The second obtaining module is configured to obtain information generated by the user in preparing to answer the question.

Optionally or preferably, the second obtaining module is further configured to:

Optionally or preferably, the apparatus further comprises: a value assignment module for dividing the image into a plurality of units, each of which is given value information; and the obtaining user performs a first operation on the masked portion of the image The generating information in the process includes: counting the value information of the unit that is revealed after the user removes the masked area.

Optionally or preferably, the device further comprises:

The adjustment module is configured to count the answer information sent by the plurality of users and the information generated in the process of preparing to answer the question, and adjust the value information of the unit according to the statistical result.

Optionally or preferably, the apparatus further comprises: a selection module, configured to obtain information generated by the user in preparing to answer the question,

The second obtaining module is further configured to: acquire a second area of the user to remove the masked portion of the image, so as to determine the first area selection according to the answer information of the user and the degree of fit of the first area and the second area The accuracy.

Optionally or preferably, the device further includes: a verification module, configured to acquire, after the obtaining the answer information sent by the user when answering the question, the verification information sent by the user, where the verification information includes the user Feedback information describing the correctness and/or accuracy of the question and/or the preset answer corresponding to the question.

Optionally or preferably, the device further includes: a reward module, configured to send the reward information to the user according to a predetermined policy after the obtaining the verification information sent by the user.

Optionally or preferably, the at least shielding module is further configured to:

Generating a masked area;

Optionally or preferably, the apparatus further includes a third obtaining module, configured to acquire information generated by the user in preparing to answer the question before the obtaining the answer information sent by the user when answering the question; The information generated by the user in preparing to answer the question includes at least one of time information, moving speed information of the obscured area, and moving track information.

Optionally or preferably, the apparatus further comprises a statistics module for counting information obtained from the user to establish a data model and/or to quantitatively evaluate the image.

Optionally or preferably, the device further comprises:

And an encryption module, configured to encrypt, by using an encryption algorithm, at least a part of the information generated by the user in preparing to answer the question to form a key;

a third obtaining module, configured to acquire verification information sent by the user, so that the user uses the key to compete for the reward obtained according to the sending of the verification information;

Optionally or preferably, the image comprises a multi-layer superimposed image, wherein the image located in the upper layer is determined as the obscuring layer of the next layer of image; the apparatus further comprising:

And a fourth acquiring module, configured to acquire a second operation performed by the user; and the second operation is capable of removing the content displayed by the image of the previous layer to display the content of the image of the next layer.

Optionally or preferably, the device further comprises:

And a fifth acquiring module, configured to acquire a third operation performed by the user; the third operation is capable of obscuring the area displayed by the underlying image and causing the content of the upper layer image to be displayed.

In a third aspect, the present invention provides a storage medium storing a plurality of instructions adapted to be loaded by a processor to perform the image information processing method described in the first aspect.

The image information processing method provided by the present invention forms an occlusion on at least part of the content of the image, causes interference to the user to understand the content information of the image, and then sends a question related to the image content to the user for the user to answer, and finally obtains the answer sent by the user. Information, in the above interaction process, the user is no longer passively accepting the information conveyed by the image, but feedbacks the information conveyed by the image in a manner of answering the question, such that the obtained answer information and the user's understanding of the image content It has a large correlation with cognition, which helps to reflect the user's thoughts on the image content. Therefore, the collected user data can be related to the content of the image information, which is beneficial to mine the potential data value of the image through the collected data. .

DRAWINGS

1 is a scene diagram of image display in an image information processing method according to an embodiment of the present invention;

2 is a scene view of the image shielding state in FIG. 1;

3 is a scene diagram in which the masked area of the masked image in FIG. 2 is partially removed;

FIG. 4 is a flowchart of a method for processing image information according to an embodiment of the present invention;

FIG. 5 is a flowchart of a method for processing image information according to another embodiment of the present invention; FIG.

FIG. 6 is a flowchart of a method for processing image information according to another embodiment of the present invention;

FIG. 7 is a flowchart of a method for processing image information according to another embodiment of the present invention;

FIG. 8 is a flowchart of a method for processing image information according to another embodiment of the present invention;

FIG. 9 is a schematic diagram of an image unit division manner and value assignment according to an embodiment of the present invention; FIG.

FIG. 10 is a schematic diagram of a process of changing a value of an image unit according to an embodiment of the present invention; FIG.

11 is a process diagram of forming a key area and a transition area in an image according to an embodiment of the present invention;

FIG. 12 is a schematic diagram of an image encryption method according to an embodiment of the present invention; FIG.

FIG. 13 is a schematic diagram of performing image segmentation in an embodiment of the present invention; FIG.

FIG. 14 is a schematic diagram of a combined image in an embodiment of the present invention; FIG.

Figure 15 is a schematic diagram of a combined image in another embodiment of the present invention;

FIG. 16 is a schematic diagram of a system architecture in which an embodiment of the present invention may be implemented;

FIG. 17 is a schematic structural diagram of an image information processing apparatus according to an embodiment of the present invention;

FIG. 18 is a schematic diagram showing the relationship between a first area and a second area according to an embodiment of the present invention; FIG.

Figure 19 is a schematic diagram showing the relationship between a first area and a second area in another embodiment of the present invention;

20 is a schematic diagram showing the relationship between a first area and a second area in another embodiment of the present invention.

Detailed ways

The principles and spirit of the present invention are described below with reference to a few exemplary embodiments illustrated in the drawings. It is to be understood that the description of the embodiments is merely intended to provide a better understanding of the invention, and is not intended to limit the scope of the invention.

In an embodiment of the present invention, an image information processing method is provided, which has various types of images, including static pictures, dynamic pictures, videos, and augmented reality images. The presentation form of the image includes a planar form and also includes a form of a three-dimensional stereoscopic image.

It should be understood that the image in the embodiment of the present invention is shown to the user as a carrier with a display device. Such well-known terminals are, for example, mobile phones, personal computers, PDAs, and smart wearable devices with display functions. Among these terminals are processors, memories, display devices, and other input and output device devices. The input device may be a touch screen, a keyboard, a mouse, a microphone, a camera, or the like.

The following describes the specific steps included in the image information processing method (hereinafter referred to as the method) provided by the embodiment of the present invention.

Step S1: Block at least part of the content of the image.

In step S1, the purpose of masking at least part of the content on the image is to form an obstacle for the observer to acquire information in the image. The masking method may be to occlude the original content of the image by using a monochrome, colored, opaque or translucent masking layer. The occlusion layer may be static. For example, the occlusion layer always blocks a certain area or all areas of the image, or may be dynamic. In the dynamic occlusion mode, the occlusion area is first generated, and then the occlusion area is moved according to a predetermined strategy. The location on the image. A specific implementation manner may be: generating a monochrome area that blocks the image, and setting a trajectory for eliminating the occlusion area according to a predetermined rule, the trajectory may be a moving strip trajectory, which is similar to the video game "greedy" "Snake", that is, a strip-like trajectory like "snake snake", the occluded area that passes through it eliminates the monochromatic occlusion on the area, and reveals the original content of the image. When the strip trajectory moves away from the occlusion area, Restore the original occlusion state. Another way of dynamic masking is to first produce a masked area that can be removed to display the original content of the image (as described below), but after a predetermined time interval, the masking of the image is resumed again.

It should be understood that the occlusion layer itself may have commercial information, such as the occlusion layer may be an advertisement image.

Next, the method proceeds to step S2: providing a problem related to the image.

The problem associated with the image is generally determined by the uploader of the image. In an embodiment of the present invention, the image uploader transmits the image to the server through the terminal, and sets a problem related to the image content, and then the server transmits the question and image to the audience terminal of the image, of course, the image uploading and The step of providing the problem may also be done locally at the terminal, and after another user (the audience of the image) uses the terminal and the image to complete the interaction (as described below), the relevant information is sent to the server for collection. The form of several problems is exemplarily given below, but the content of the pictures and the content of the problems do not constitute a limitation of the scope of the present invention.

Example 1: User A uploads a landscape picture, and the part of the selected landscape picture relates to the area of the landmark building, which is obscured by the terminal and asks a question: Where is this?

Example 2: Merchant B uploads a product picture through the terminal, selects part of the pattern area of the trademark in the product, and the terminal blocks it, and asks the question: What brand is this?

Example 3: The film distributor C uploads a video of the video through the terminal, completely obscures the video playback window, and asks questions. What is the title?

Example 4: Consumer D purchases a vacuum cup, and a two-dimensional code storing a network address is printed on the heat preservation cup. The server corresponding to the network address stores the 3D image of the vacuum cup, when the consumer D passes the After scanning the QR code, the mobile phone can read the 3D image of the vacuum cup and share the image with social software. At the same time, the terminal also forms a shadow on the 3D image and asks questions: What is this product? The occlusion image is also a 3D image, and may have an advertising feature, such as an iconic character in a cartoon movie.

After receiving the problem information and the image information, the server sends the image and the question together to the terminal held by the image-spreading audience. In the context of a social application, the audience may be a friend in the communication list of the terminal held by the user. In the context of advertising, the audience is the recipient of the business advertising information.

1 and 2 show an image in a specific embodiment, and a masking method and a questioning method. In FIG. 1, the terminal is a tablet computer with a touch display screen, and an unshielded picture of the Great Wall scenery is displayed thereon. In Figure 2, most of the area of the Great Wall picture is obscured by a black obscuration layer. The user settings question is displayed at the bottom of the picture: What is this? The question is followed by an input box with the prompt message: Please enter the answer.

Next, the method proceeds to step S3: acquiring information generated by the user in preparation for answering the question.

Then, after the user answers the question through the terminal, the method proceeds to step S4: acquiring the answer information sent by the user when answering the question.

Steps S3 and S4 are both interaction processes with the user after the image is sent to the user. During this interaction, the user is no longer a passive information receiver, but can input the terminal by answering questions related to the image. Information fed back to the image so that the terminal sends the feedback information to the server. After obtaining the information on the server side, it is equivalent to acquiring the data related to the image, thus overcoming the problem that the image itself is difficult to digitize and the information resource is wasted. It should be understood that the server side herein refers to a terminal used by a subject that needs to acquire these image-related data for operation. The server is only a proxy for such a terminal, and in other embodiments, it may also be Other types of terminal equipment.

In steps S3 and S4, the obtained answer information of S4 is the most basic way of obtaining information. As a preferred solution, the information generated by the user in preparing to answer the question may be acquired (ie, step S3), and the amount of information obtained may be obtained. It is more abundant, and has more related factors with image content. It can generate more data related to image propagation, which is more conducive to establishing a multi-factor related big data model after pooling data.

In an embodiment, step S3 specifically includes: acquiring information generated during a first operation performed by the user on the image-masked portion, the first operation being capable of removing the shadow such that the image is displayed by the content of the masked portion.

The first operation can take many forms depending on the input device of the terminal. Taking a smart phone with a touch screen as an example, the first operation may be a sliding operation of the user on the touch screen, and after the sliding operation is over the area where the image is blocked, the terminal determines that it is an action of reducing the shadow area, and then the image is further The masked area on the top is removed, showing the original content of the image. In other embodiments, the input device of the terminal is a mouse, and the first operation is a mouse to control the movement of the cursor on the image. In some other embodiments, the input device of the terminal is a camera (such as a camera and an external camera provided by the mobile phone), and the first operation may be a gesture made by the user toward the image capturing area of the camera for the terminal to perform the gesture. Identifying, determining that it is an action of performing removal of the image masking area.

An implementation of the first operation in a particular embodiment on the basis of the images shown in Figures 1 and 2 is illustrated in Figure 3. In FIG. 3, the user's finger touches the black masked area, and after detecting the user's touch signal, the terminal removes the mask of the area and displays the original content of the image.

During the answering of the question, if the image is obscured, the area of the user's identification image creates sufficient obstacles for the user to answer the question provided in step S2, and the user will actively perform the first operation. In the process of performing the first operation, the information generated may include information of removing the occlusion area, occlusion area removal trajectory information, and time information. When these information and answer information are combined, it will reflect the user's cognition of the content of the image, which is beneficial to integrate the information to establish a data model and analyze the user's behavior and/or image transmission effect. In one embodiment, it preferably includes information for removing the occlusion region, and in another embodiment, including information for removing the occlusion region and removing trajectory information, and in another embodiment, further including removing information of the occlusion region and removing Track information and time information. It should be understood that in addition to the above three implementations, the information may be any other permutation combination.

The information of removing the occlusion area includes the area of the occlusion area removed or the position of the occlusion area removed when the user performs the first operation. The location information may reflect which part of the image the user answers the question, and the area information may reflect how much the user has removed the area to answer the question. After obtaining this part of the data, the user's awareness of the image can be analyzed, so that the uploader of the image makes a decision based on the obtained user feedback data. The example 2 described above is taken as an example. It is assumed that the answer information of a plurality of users in queuing the brand name and the position information and area information of the removed mask area generated during the answering process are obtained, and it is found that a higher proportion of users remove the area of the part A. , this can explain that part A is the design point of the trademark, with a higher degree of recognition, in the process of packaging design, the merchant should pay attention to make the part A focus, in order to attract users who recognize the brand to buy, and strengthen the user Brand awareness. The example 1 described above is taken as an example. It is assumed that the answer information of multiple users in the name of the quiz and the position information and area information of the removed obscured area generated during the answering process are obtained, and it is found that a relatively high proportion of users remove a large range of obscuration. The area still has no guessing the name of the attraction, which means that the attraction may not be well-known to the user. The management of the tourist attraction may consider re-development of the attraction and other channels to attract tourists.

The occlusion removal track information can also reflect the user's cognition of the image. For example, according to the statistical result of the trajectory removal, it can be known which trajectories the user can easily answer the correct answer.

The time information can reflect the time taken by the user in answering the question, which can include the time from the start of the user to the total time spent submitting the answer (ie, the total time information consumed by the user in preparing to answer the question), or It includes time information when performing the first operation (such as the time the user stays on removing the masked area, which reflects the user's attention to the area). In general, the longer the time spent is, the more difficult it is for the user to answer the question raised in step S2.

The above description is the information generated when the user actively performs the first operation, and according to the above description, the operation of removing the mask does not necessarily require the user to actively operate, but can realize the shadowing and display of the image region in a dynamic manner. . In the dynamic masking mode, the masked area is first generated, and then the position of the masked area on the image is moved according to a predetermined strategy. At this time, the information acquired in step S3 includes at least one of time information, moving speed information of the obscured area, and movement locus information.

The time information and the role of the occlusion area to remove the trajectory information are substantially the same as the time information acquired when the first operation is actively performed. The moving speed information of the occlusion area may reflect the speed at which the occlusion area switches between the occlusion and the display state to determine the user's awareness of the image content. If the user can still answer correctly if the switching is fast, the terminal can determine that the user has a high degree of cognition of the image content.

In the above two ways of collecting information in the process of the user preparing to answer the question, one requires the user to actively perform the operation of removing the masked area, and the other is not required. Both methods have their own advantages. The former can increase the interaction between users and images, and the types of data obtained are more abundant. The latter can reduce the user's operation.

In a preferred embodiment, the method further comprises the step S5 of dividing the image into a plurality of units, and assigning value information to each unit. On the basis of this, acquiring the information generated during the first operation performed by the user on the masked portion of the image includes: counting the value information of the unit that is revealed after the user removes the masked area. Step S5 is performed before step S3.

As described above, the removal of the location information of the masked area is an effective data for analyzing the user's perception of the image. In an image, some areas may have a higher degree of relevance to the questions raised in step S2, which helps the user guess the correct answer to the question after removing the shadow of the part. Some areas are less relevant to the issue. If only the location of the removed area is obtained, the coordinate information of the position may be involved, and even for the two-dimensional image of the plane, the two-dimensional coordinate information involves two parameters of the horizontal and vertical coordinates, and the statistics of the masked area are removed. In the process, the coordinates and calculations need to be performed, and the calculation amount of the computer processor is relatively large. To this end, in a preferred embodiment, the image may be divided into a plurality of units, and value information is given, such that when the masked area of the image is removed, step S3 simultaneously performs the recording of the value of the corresponding unit of the removed masked area, and finally The user's perception of the image content is judged based on the total value information generated by the user in the process of answering the question, and the process involves only simple addition or subtraction, and the computing burden of the terminal processor is low. In addition, the process of digitizing the image by means of the value information is realized, and the transition from image to data is realized, which is advantageous for establishing a data model related to the image or quantitatively evaluating the image content.

The division form of the image unit may be various, such as dividing in units of pixels of the image, or dividing by a grid. The shape of the mesh can also be various, such as a quadrangle, a hexagon, or other regular or irregular shapes.

According to an embodiment of the present invention, the value information of the image unit is positively correlated with the degree of relevance of the problem, that is, the greater the degree of correlation between the image unit and the problem, the greater the value given, and the smaller the degree of relevance to the problem, the smaller The value given is smaller.

The value of the value information can be calculated in a variety of ways, such as the use of points, grades or a combination of points and grades. In the present embodiment, the manner in which the value information is given is described by way of a score.

As shown in FIG. 9, in a two-dimensional planar image, it is divided into a plurality of cells by a rectangular mesh, and the scores in each cell are varied from 65 to 100. A larger score indicates a higher degree of association of the unit with the problem. In the process of the user answering the question, the statistical method of the score can be subtracted, that is, the scores of the units in the image are first summed, and the image is subtracted every time the user removes the masked area of one image unit. The score corresponding to the unit. In this way, if the area of the masked area removed by the user is smaller, or the score of the removed area is smaller, it means that the user may answer correctly by acquiring less image information with less relevance to the problem, and thus can judge The user has a higher awareness of the image, and vice versa. In addition, after assigning a score to the image, the user can obtain a score after answering the question. This score not only reflects the user's awareness of the image, but also increases the gameplay in the process of answering the question, and also facilitates the terminal or server according to the score. Score to send rewards to users. In one embodiment, the form of the reward may be an electronic coupon, a cash red envelope, or the like. Of course, it should be understood that the above-mentioned score calculation method is only an example, and in other embodiments, other calculation methods may be used, and the calculation of the score value of the user may also be combined with time information, trajectory information, and answer. The correctness of factors such as the correctness or not.

It should be understood that the operation of assigning the value of the image unit may be initiated by the user who uploaded the image. When uploading an image, the terminal receives an operation signal input by the user, which is used to assign value to the image unit. At this time, the user can measure the value of the image unit by himself, and assign high value to the image unit that he thinks is highly correlated with the problem set by the user, and the low relevance gives low value. For example, suppose a user uploads a landscape picture of an attraction through the terminal they hold and provides a question: Where is this? For this problem, the user believes that the landmark building area in the picture is highly correlated with the problem, because for the average person, the name of the attraction can be known by seeing the building. Therefore, in the operation of giving the value of the image unit, more scores are assigned to the image units corresponding to the landmark buildings, and smaller scores are assigned to the other regions. When the user is operating, the terminal may send a prompt message to the user to give value to the image unit, for example, please select the area that is most useful for answering the question. After seeing the prompt information, the user performs the operation of delineating the area range, delineating the area that it considers to be high value, and after receiving the demarcation operation, the terminal assigns a preset score to the image unit in the area. Then, the user can continue to be prompted to delineate the area that is useful for answering the question, and to assign value to the remaining area. In other embodiments, the user's assignment of image unit values can also be accomplished by directly entering values. In some other embodiments, the initial value of each unit of the image may be fixed and the same, and the server may adjust the score based on the information collected by the user when performing the first operation (as described below).

As mentioned above, the value of the image unit is usually determined by the user, but the value of the image selected by the user may not be accurate for the audience of the image, or the user deliberately misleads when selecting the value of the image unit, the original and the problem Areas with low relevance give high value, while areas with high relevance to problems give low value. In this way, when the user who is the audience of the image transmission answers the question, the generated value statistics cannot truly reflect the user's recognition of the image content, which affects the accuracy of the decision based on the big data. In order to solve this problem, in the embodiment of the present invention, after the step S5, the method further includes:

S6: The answer information sent by the plurality of users and the information generated in the process of preparing to answer the question are counted, and the value information of the unit is adjusted according to the statistical result.

If the image uploading user is wrong in designing the value of the image unit, the server can collect the answer information of multiple users and generate information in the process of answering the question, and judge the rationality of the unit value design through the statistical result, and carry out the unit value. Dynamic correction. In one embodiment, the information generated in the process of preparing to answer the question includes the shaded time of the image unit, the time that is displayed to the user after being masked, the number of times the mask is removed by the user, and the adjacent image unit. The score between the two, etc. For example, suppose an image unit has an initial score of 100, which represents a higher correlation between the image unit and the problem. However, after the server collects a large number of samples of the answer information, according to the statistical results, it is found that although the unit has been removed for a long time and has a large number of times, the user still has not made the correct answer according to the content of the area (ie, the answer is incorrect). Therefore, it is determined that the score of the image unit is too high, and the score of the image unit is lowered. Thus, the more the statistical sample size is, the more accurate the value of the image unit will be. In addition, the change strategy of the score can be changed according to factors such as user information and answer time, so that the adjustment result will be more reasonable. In one embodiment, the user information includes the region, age range, gender, and the like. For example, for a cosmetic-related image, the male user may not be able to answer the question even if the mask of the high-value area in the image is removed during the answering process. At this time, according to the male gender of the user, the data unit can be appropriately reduced. The magnitude of the value.

Figure 10 shows the process of score change of an image. In the initial state (shown on the left of Figure 10), the picture is divided into 9 squares, the square score in the middle is 100 points, and the rest are 80 points. After a period of time, the user collected a certain sample amount of data, and the score of each cell was adjusted to obtain the score result shown on the right side of FIG.

According to an embodiment of the invention, between steps S2 and S3, the method further comprises:

A first region is selected in the portion of the image that is obscured, the first region being selected as an area that helps the user answer the question after learning its content.

Further, in step S3, acquiring information generated by the user in preparing to answer the question includes: acquiring a second area of the user to remove the masked portion of the image, so as to combine the answer information of the user with the first area and the The degree of fit of the second region determines the accuracy of the selection of the first region.

The above steps are basically the same as the above-mentioned dynamic adjustment steps for the value information, and the purpose is to determine whether the user of the image upload is reasonable when setting an area with a high degree of relevance to the answer question.

As shown in FIG. 11, in one embodiment, the horizontal A area represents the first area selected by the image uploading user A, and the oblique B area represents the second area removed by the image transmitting audience on the terminal, which will be the first Comparing the region with the second region, it is found that only a part of the overlap can be judged that the overlap region can accurately represent that it has a high correlation with the question to be answered, and other regions in the first region may be associated with the problem. Degree is not very high. Calculating the overlapping area is advantageous for presenting the calculation result to the uploading user of the image in a visual manner, that is, directly displaying the overlapping portion, the overlapping area, the overlapping ratio, and the like of the first area and the second area, and actively adjusting the position of the first area. Get a more intuitive reference.

After the server collects a certain number of user response question samples from the terminal, the statistics user removes the masked areas, which can be roughly divided into the following types:

Key areas:

When the data points of a certain score interval are linked together, it is judged that this is a key area of data. Key areas are generally identified as users, and areas that have certain influencing factors on products or interactive questions and answers. This area can objectively reflect the accuracy and value of the data.

For example, when answering a question, different image unit areas selected by different users are different, but some image units are necessarily the same. When the sample reaches a certain base number to judge the area as a key area, the interaction data of most users is determined.

Q&A area:

When the user shares the picture through the terminal, a question and answer area is set, and at least one question is generated in the area, and at least one correct answer is provided for answering.

When the question-and-answer area and the key area have a high degree of coincidence, it can be judged that the design of the problem is reasonable, and vice versa, the setting of the problem is not reasonable enough.

Data transition area:

Compared with the score interval of the key area, the score of the data transition area will be lower, which means that the information provided by these areas can only be used as a reference factor. By systematically intervening in the evaluation criteria of the transition zone and the key zone score interval, the key zone and transition zone area of different sizes can be obtained. On this basis, some information is exchanged to analyze the change of the size of these zones to obtain the user. Interactive data information for certain issues or preferences.

In FIG. 11, the overlapping area of the A area and the B area may also indicate the position of the critical area, and the other areas may be represented as the transition area.

In Figs. 18-20, it is shown in other embodiments whether or not the user is reasonable in determining the area in which the degree of association with the answer question is high based on the degree of fit of the first area and the second area. In FIGS. 18-20, the A area represents the first area selected by the user, and the B area represents the second area obtained according to the statistical result of the acquisition user removing the masked area. By calculating the overlapping area and/or inclusion relationship of the A area and the B area, the rationality of the first area setting can be determined.

In Fig. 18, the A area and the B area are in an intersecting relationship, and the overlapping area is C. By calculating the area of C, it is possible to determine the reasonable degree of the first area setting. Further, in order to determine whether it is necessary to adjust the position of the first region, it may be designed according to the combination of the area of the overlapping area, the weight occupied, the ratio between the areas of the parts, the difference, and the like. A predetermined judgment strategy to determine whether the first area needs to be adjusted. The following several exemplifying strategies are given exemplarily, but it should be understood that they do not constitute a limitation of the invention.

In one embodiment, when A-C>C/2, it is determined that the area division is inaccurate and correction is required (where A and C represent the area of the area A and the area of the area C, respectively, the same applies hereinafter). When A-C<C/2, it is judged that the area division is inaccurate, but the influence is not large, and the user may not be prompted to make correction or not automatically correct the first area.

In another embodiment, when BC>C/2, it is determined that the area division is inaccurate and needs to be corrected (B and C here respectively indicate the area of the area B and the area of the area C, the same applies hereinafter) . When B-C<C/2, it is judged that the area division is inaccurate, but the influence is not large, and the user may not be prompted to make correction or not automatically correct the first area.

In FIG. 19, when it is detected that the A area is within the B area, it is determined that the range of the first area is too small, and the statistical result shows that most users cannot answer the question only through the A area, and the problem design is difficult. Correct the first area.

In FIG. 20, when it is detected that the B area is within the A area, it is determined that the first area is too large, and the statistical result shows that most users can answer the question by simply removing the B area, and the problem design is easy. It is recommended to amend the first area.

The above describes the adjustment mechanism of the region and value information of the embodiment of the present invention when the selected region having a higher degree of relevance to the question is unreasonable. In addition, there may be problems with incorrect and inaccurate answers to the default answers to the questions. For example, the user who uploads the image may incorrectly fill in the typo or the answer is inaccurate when setting the answer to the question, or may intentionally fill in the wrong answer. This phenomenon does not truly reflect the user's awareness of the image content. , affecting the accuracy of decisions based on big data. To this end, in accordance with an embodiment of the present invention, after step S4, the method further includes:

S7: Acquire verification information sent by the user, where the verification information includes feedback information about the correctness and/or accuracy of the problem and/or the preset answer corresponding to the problem.

As the image propagation audience terminal, the user can answer after partially or completely removing the masked area, and the terminal will feedback the correct answer after the user answers. If the error is wrong, the user can also be fed back with the correct answer (the answer is now the answer set by the user who uploaded the image). When the audience finds that the answer is wrong, it can correct the error and use the terminal to send verification information to the server that the problem is wrong or the problem is inaccurate. In this way, the server can notify the user who uploaded the image to verify and correct the answer to the question according to the feedback result of the user.

Further, after step S7, the method further includes step S8: transmitting the reward information to the user according to a predetermined policy.

The information sent by the reward may motivate the user to actively correct the question and answer. In one embodiment, the reward information may be in the form of an electronic coupon, a cash red envelope, an electronic voucher, or the like.

According to an embodiment of the present invention, in another way of correcting the correct answer, the following steps may also be taken:

S9: encrypt, by using an encryption algorithm, at least part of the information generated by the user in preparing to answer the question to form a key;

Next, the method proceeds to step S10: acquiring verification information sent by the user, so that the user uses the key to compete for the reward obtained according to the transmission verification information; the verification information includes the user corresponding to the problem and/or the problem Feedback information on the correctness and/or accuracy of the default answer.

This step is similar to S7 in that the user is required to send feedback information correcting the preset answer as the verification information. However, unlike step S7, in this step, at least some of the information generated by the user in preparing to answer the question is encrypted by an encryption algorithm, such as by a hash algorithm. If the user needs to obtain the reward, it needs to adopt the competition mechanism, that is, the right to transmit the feedback information in the propagation network of the verification information, and the reward information can be obtained only after obtaining the transmission right, which is similar to the competition information of each node in the blockchain technology. Block weight mechanism. After adopting this method, it is possible and fair to use the decentralization mechanism in the blockchain technology for the process of user competition reward. In an embodiment, step S9 may be specifically performed in the following manner:

As shown in FIG. 12, the masking area is divided into a plurality of rectangular image units to form an array of n*m. Where n and m are positive integers, n is the number of rows of the array, and m is the number of columns. When an image unit is masked by the user, the image unit is assigned a value of “1”, and other image units that are not masked are assigned. It is "0", of course, it can also be reversed, the masked unit is assigned a value of "0", and the unmasked image unit is assigned a value of "1". Thus, when the question is answered, the user's operation record of the image forms an n*m array consisting of "0" and "1", and each row or column of the array can be judged as a set of binary A number, multi-line or multi-column binary number is combined to form a set of ciphertexts, which can be used as a key corresponding to the user's answer operation. In addition, this set of ciphertext can also be converted into decimal, hexadecimal, and so on. When the user requests to obtain the reward information through the feedback information, the set of keys can encrypt the user's verification information, so that if the verification information or the reward information is written in the blockchain, the user can use the set of keys to ensure privacy. And the data is not tampered with.

In one embodiment, the image is a single layer image, and in other embodiments, the image may also be a multi-layer image, such as multiple image overlays. After multiple images are superimposed, the user can perform operations on removing the masked areas of multiple images, so that more interactive information can be obtained. In this case, the image located in the upper layer is determined as the masking layer of the image of the next layer. Further, the method further includes the following steps:

A second operation performed by the user is obtained, the second operation being capable of removing the content displayed by the image of the previous layer such that the content of the next layer of image is displayed. In this way, the image of the upper layer is equivalent to the function of integrating the mask layer, and the user can see the content of the lower layer image by removing the upper layer image. Further, the step further includes: acquiring a third operation performed by the user, the third operation being capable of obscuring the area of the underlying image display and causing the content of the upper layer image to be displayed. This way, when the user wants to re-observe the upper layer image content, it is convenient for the user to switch between the upper and lower images.

In one embodiment, the image is composed of a plurality of sub-images, at least a portion of which is assigned a question associated with the sub-image. After the sub-image problem is given, the user will answer multiple times during the entire interaction with the image, and the answer information obtained by the terminal and the information generated in the process of preparing to answer the question are more hierarchical. For example, in an image, if only one problem is designed, most users may not answer because the difficulty of setting the problem is too large, so that the server obtains less data information, which is not conducive to establishing a data model. To this end, an image can be segmented into multiple sub-images, giving each sub-image a question, so that the user can answer questions step by step, so that the collected user and image interaction data is also richer. In addition, in other embodiments, the sub-images are not necessarily a part of an entire image, but are independent images, and the content between the independent sub-images may be related to each other or may not be related to each other. .

The above-mentioned multi-layer image overlay and multi-sub-image stitching involve the interaction of the user and multiple images, and thus can be applied to scenes in which multiple people and images interact. In particular, it is possible to satisfy the operation of removing the masked area by a plurality of users, competing for answering questions, and scoring the answers of each user in combination with the score system described above, which increases the interest in the image interaction process.

The following describes two ways in which multiple sub-images are combined in this embodiment.

In one embodiment, a picture or video may be equally divided according to a certain scale or size to obtain a number of small size pictures or videos. Some of them have at least one quiz in a small size, while others have no quiz.

At this time, an original picture or video can generate a plurality of pictures of different contents, as shown in FIG. The user can make multiple question and answer interactions on the entire original image based on the small size map.

In Fig. 13, the original picture is cut into 4x7 square cells, and 3x4 is selected as the interactive part, wherein A and I have different directions, but both have a question and answer part, and K has no question and answer part. (The shaded square is the question and answer area with question and answer content). Among them, the 3x4 image including the I and K regions is equivalent to a 90° counterclockwise rotation of the 4x7 image.

It is known that in addition to K, 12 combinations of A, B, C, D, E, F, G, H, I, J, L, M, etc. can produce new small-sized pictures with question and answer parts. The original image produces 12 new variants, increasing the chances of all the answers in a single guess. The user can interact multiple times with a single original image, increasing the accuracy.

In another embodiment, a plurality of sub-images are combined and displayed on one terminal for user interaction. In FIG. 14, six small-size images (AF) consist of a six-question interface, the six Small size images can be provided by one user or multiple users. These issues may or may not be related to each other.

Figure 15 is a four-dimensional problem interface of two small-size pictures (A and B). The two small-size pictures can be provided by one user or two users. These issues can be related to each other and there can be no connection.

This design increases interactivity and enhances data accuracy.

At the same time, by increasing the number of pictures and the number of questions and answers, you can increase the overall score and rating of the overall picture. Create more challenging questions and answers.

In the above embodiments, the problems associated with the image may be proposed in various ways, such as using keyboard input (physical keyboard or virtual keyboard), voice input, gesture recognition, and the like. The problem can also be applied in a variety of ways when presented to the user. In some embodiments, the problem may be displayed next to or below the image for user convenience, and in other embodiments, the problem may appear on the image, particularly the area that is obscured on the image. In some embodiments, the problem may be presented to the user while the image is presented to the user, and in other embodiments, the problem may be a gradual appearance. For example, the terminal may detect the location information of the user to remove the occlusion area, and the problem may arise when it is detected that the location is close to the image unit with a high degree of relevance to the problem.

In the above embodiments, the user may trigger the image, the question, and the answering manner. In one embodiment, a graphic code (a two-dimensional code or a barcode) may be provided in a certain scene. The network address is stored, the network address is linked to the content of the image and the question, and the user can start answering the question or sharing the question by scanning the QR code with the terminal. This method allows the user to directly scan the code through the smart terminal, which improves the efficiency of triggering and answering questions.

In addition to raising the issue of higher relevance to image content, the method also includes the steps of providing additional questions. This step can be displayed to the user after the user has answered the questions related to the image content.

In one embodiment, the step of providing additional questions includes inserting a certain area of text or graphical content into the image, which portion may provide an additional question, and the question and answer results of the question may affect the value of the image unit in the above description. The inserted text or graphic can be changed according to the classification of the user. Two specific attachment questions are given below.

Additional question 1: "Buy 2 get 1" and "Buy 2 pay 1" Although it is only a different text, but the discount strength is different, the problem is designed to "buy 2 mouth 1", let the user guess whether it is a gift or a payment, The user's consumption preferences and the value of the advertising product can be counted. Of course, the wrong question and answer here does not affect the calculation of the image unit value, because the answer to this question is not determined by the objective content of the image, but depends on the user's subjective judgment.

Additional question 2: If the background is set to "30% off" offer, the front end will be displayed as "mouth fold". If the user guesses "7", then jump to the corresponding link, and the system will count "greater than 7", "7", User distribution and classification of "less than 7" will be questioned and digitized. For the same reason, the wrong answer here does not affect the calculation of the image unit value.

When a new mobile phone product is priced as "1799-1999", you can set "1 port 99" or "1 port 9" to set up interactive Q&A. The system provides feedback to the mobile phone manufacturer by analyzing the interactive question and answer. Market pricing for new products. For the same reason, the wrong answer here does not affect the calculation of the image unit value.

After performing the above steps, the method may further comprise the step S11 of counting information obtained from the user in order to establish a data model and/or perform quantitative evaluation of the image. The system architecture implementing step S11 is as shown in FIG. 16. The system includes a plurality of user terminals and servers. The user terminals 161 and the server 160 are communicatively connected through the network 162, and the user can provide the blocked content on each user terminal. The images and questions, after the user answers the question, the answer information and the information generated during the preparation of the answer are sent to the server, according to which the server can establish a big data model or quantitatively evaluate the image. In addition, in some other embodiments, the information may be uniformly sent by the user terminal that answers the question to the terminal that issues the problem through the network, and the data modeling and/or the quantitative evaluation of the image may be completed on the terminal that issues the problem. In one embodiment, the quantitative evaluation of the image may employ a ranking mechanism that is calculated by counting answer information for multiple users and information generated during the answering of questions. For example, by statistic analyzing the data of the user interaction result, the picture or video can be scored according to the area of removing the masked area, the correct rate of the answer, the time of removing the masked area, the favorite image, the like image, the browsing image, and the like, and Rate images or videos based on ratings. S, A, B, C, etc. represent the quality of the picture, and different letters represent different score intervals. The determination of the image level can also be combined with the score system provided above.

For example, if someone uses WeChat or FACEBOOK, Instagram and other social software friends to share the function, a S-level full-shadow picture is involved in an interactive question and answer under a car classification. The picture, 100 people data is 50% correct, 50% like The number is 90+, the interactive question is 3, and the total score of the key area is 5000 points.

The actual answering situation of a person is: answer 2 questions, answer 1 question, unlock data points account for 78% of the total area, and then complete the cooperation and answer time and other data, the final score is 3256 points, rated as B level. In this process, both the rating of the image and the rating of the user's response are included.

Through the scoring and rating system, you can enhance the social relationship between users (friend circle, Weibo FACEBOOK, Instagram map), while increasing the accuracy of the user interaction process, in order to obtain more accurate data.

The system can be widely used in social pictures, short videos and other software to generate data value based on social interaction. At the same time, it can also be applied to e-commerce platforms such as reviews and sun orders.

In the following, a specific application scenario of the image information processing method provided by the preferred embodiment of the present invention is introduced.

Application example 1 Tourism sharing

Tourists from the United States traveled to the Great Wall and took a selfie on the background of some Great Walls. By setting keywords, associate your own selfie classification to the travel directory, and select some of the Great Wall backgrounds in the picture as the problem area. Set the question: The problem is to guess where I am, the answer is 2, 1 and the Forbidden City. The initial score of the image is 3000 points and belongs to the B-level picture.

Mike shared the pictures with friends through software, some of them participated in the interaction, chose the Great Wall, and several friends chose the Forbidden City. More than 100 friends interacted with the picture one day later, 70 of them chose the Great Wall and 30 chose the Forbidden City. The final picture score was revised to 4000 points and belonged to the A-level picture.

Two days later, Mike went to a certain attraction A and took a second selfie with a spot A as the background. Through speech recognition, associate your own self-photographing classification to a certain attraction A directory, and select some of the attractions in the picture A background is the problem area, set the problem: the problem is to guess where I am, the answer is 3, 1 Attractions A, Great Wall, Forbidden City. The image has an initial score of 2,500 points and is a C-rated image.

In order to increase the fun, Mike combined the Great Wall selfie taken in the previous two days with a selfie of a scenic spot A into a new picture, which contains two parts of the self-photograph and contains two questions and answers. The new picture has an initial score of 4,500 points and belongs to the A-level picture. And sent to a friend to interact with the new picture. Another 100 friends interacted with the pictures. Among them, 50 people answered 2 questions, 35 people answered 1 question, and 15 people answered the wrong questions. The final picture score was 5000 points, which belonged to S-level pictures.

Application Example 2 Shopping Sharing

Tom bought a branded T-shirt at Amazon. The brand currently offers a photo-taking activity to share with friends to get a $2 reward. After filming the selfie, Tom found that the brand still has a paid text question and answer question in the system. The question is “Is the mouth value 99?” The answer is 2 to 1, and “0/1”, where 1 is the correct answer. Under the paid text answer, the merchant promises that every friend who participates in the interaction can earn a profit of 0.2 yuan for Tom. In the end, 100 friends participated in Tom's self-portrait interaction, and Tom won a 2 yuan self-timer + 20 yuan interaction, a total of 22 yuan. Among them, 44 people chose "0", 56 people chose "1", and the merchants found through data analysis that more than 40 people chose "1" under the student classification. Through this interaction between Tom and friends, the merchant thinks that this T The pricing of the shirt is reasonable, and the target customers of the brand are in line with the actual sales strategy.

Application three friends gathering

Frank and Tony are good friends and they all like to drink wine. One day, two people want to have a competition about wine at the party. They each choose an S-level picture from their own photo library to share with each other.

Frank's picture is a total of 6000 points, with 4 questions and answers, 2-3 options per question. Tony's picture is a total score of 5,500 points, with 3 questions, 3 options per question.

After receiving the picture of Tony, Frank took 2 minutes and answered 3 questions. The system scored 5100 points for this answer and the rating was S.

After receiving the picture of Frank, Tony took 1 minute, answered 3 questions, and answered 1 question. The system scored 4900 points and rated A for this answer.

Tony and Frank felt that the challenge was not exciting enough. They felt that they were free to choose two random pictures in the system library wine category to adopt the PVP mode for the second round of competition.

The system randomly assigns two popular pictures under the wine to match. The first picture is rated S, with a score of 7000 points, a total of 5 questions, 2 options for each question; the second picture is rated A, with a score of 4400 points, a total of 3 questions, and 3 options for each question.

The game rules must select a basic data point every 10 seconds, all 8 questions are answered, and the correct rate is the highest, and the person with the shortest time wins. Frank took 3 minutes and answered 8 questions; Tony took 2 minutes and answered 6 questions.

Frank scored 9999 points and Tony scored 8111 points. Frank won.

Based on the image information processing method described in the above embodiment, the embodiment of the present invention further provides an image information processing apparatus 170 for performing the method. As shown in FIG. 17, the apparatus 170 includes the following modules:

a masking module 171, configured to block at least part of the content of the image;

a questioning module 172 for providing a question related to the image;

The first obtaining module 173 is configured to obtain answer information sent by the user when answering the question.

Further, it also includes:

The second obtaining module 174 is configured to obtain information generated by the user in preparing to answer the question.

The above modules 171-174 are respectively used to perform steps S1-S4 of the method described above.

Further, the second obtaining module is further configured to:

Further, the information generated during the performing the first operation includes at least one of removing information of the occlusion area, masking area removal trajectory information, and time information.

Further, the removing the information of the shielding area includes removing an area of the shielding area and/or removing a position of the shielding area.

Further, the apparatus further includes: a value assigning module, configured to divide the image into a plurality of units, and assign value information to each unit; and the acquiring user generates information during performing the first operation on the blocked portion of the image The method includes: counting the value information of the unit that is revealed after the user removes the masked area. The value assignment module is operative to perform step S5 of the method recited above.

Further, the value information of the unit is determined according to the degree of relevance of the unit to the question.

Further, the device further includes:

The adjustment module is configured to count the answer information sent by the plurality of users and the information generated in the process of preparing to answer the question, and adjust the value information of the unit according to the statistical result. The adjustment module is for performing step S6 of the method described above.

Further, the assigning value information to each unit includes assigning a score to each unit, the size of the score being positively correlated with the size of the unit and the degree of relevance of the question.

Further, the apparatus further includes: a selection module, configured to acquire information generated by the user in preparation for answering the question,

Further, the device further includes: a verification module, configured to acquire, after the obtaining the answer information sent by the user when answering the question, the verification information sent by the user, where the verification information includes the user facing the problem and/ Or feedback information about the correctness and/or accuracy of the preset answer corresponding to the question. The verification module is for performing step S7 of the method described above.

Further, the device further includes: a reward module, configured to send the reward information to the user according to a predetermined policy after the obtaining the verification information sent by the user. The reward module is for performing step S8 of the method described above.

Further, the obtaining information generated by the user in preparing to answer the question further includes: acquiring time information generated by the user in preparing to answer the question.

Further, the at least shielding module is further configured to:

Generating a masked area;

Further, the apparatus further includes a third obtaining module, configured to acquire information generated by the user in preparing to answer the question before the obtaining the answer information sent by the user when answering the question; The information generated in the process of preparing to answer the question includes at least one of time information, moving speed information of the obscured area, and movement locus information.

Further, the apparatus further includes a statistics module for counting information obtained from the user to establish a data model and/or to quantitatively evaluate the image. The statistic module is operative to perform step S11 of the method described above.

Further, the device further includes:

And an encryption module, configured to encrypt, by an encryption algorithm, at least a portion of the user to form a key in the process of preparing to answer the question; the encryption module is configured to perform step S9 of the method described above.

And a third obtaining module, configured to obtain verification information sent by the user, so that the user uses the key to compete for the reward obtained according to the sending verification information; and the third obtaining module is configured to perform step S10 of the method described above.

Further, the image includes a multi-layer superimposed image, wherein an image located in the upper layer is determined as an obscuring layer of the next layer image; the device further includes:

Further, the device further includes:

Further, the image is composed of a plurality of sub-images, at least part of which is given a problem associated with the sub-image.

It should be understood that each of the above-mentioned modules is used to perform the steps in the image information processing method described above. For the specific implementation, functions, and effects, reference may be made to the description of the related steps in the method, and details are not described herein again.

The embodiment of the invention further provides a storage medium storing a plurality of instructions, the instructions being adapted to be loaded by a processor to execute the image information processing method described in the above embodiments. For specific steps of the method, refer to the description of the foregoing embodiments, and details are not described herein again.

The implementation of the present invention and all of the functional operations provided herein may be in digital electronic circuitry, or in computer software, firmware or hardware, including the structures disclosed in the specification and its structural equivalents, or a combination of one or more of them. to fulfill. Implementations of the present disclosure can be implemented as one or more computer program products, ie, one or more modules of computer program instructions encoded on a computer readable medium, executed by a data processing apparatus or used to control a data processing apparatus operating. The computer readable medium can be a machine readable storage device, a machine readable storage substrate, a memory device, a composition that affects a machine readable propagated signal, or a combination of one or more of them. The term "data processing apparatus" encompasses all apparatus, devices, and machines for processing data, including, for example, a programmable processor, a computer, or a plurality of processors or computers. In addition to hardware, the apparatus can include code for creating an execution environment for the described computer program, such as code that constitutes a processor firmware, a protocol stack, a database management system, an operating system, or a combination of one or more of them.

A computer program (also referred to as a program, software, software application, script, or code) can be written in any form of programming language, including a compiled or interpreted language, and the computer program can be deployed in any form, including as a stand-alone program or As a module, component, subroutine, or other unit suitable for use in a computing environment. The computer program does not have to correspond to a file in the file system. The program may be stored in a portion of a file that holds other programs or data (eg, one or more scripts stored in a markup language document), stored in a single file dedicated to the described program, or stored in multiple collaborative files (for example, a file that stores one or more modules, subroutines, or parts of code). The computer program can be deployed to be executed on one computer or on a plurality of computers located at one site or distributed across multiple sites and interconnected by a communication network.

The processes and logic flows described in this disclosure can be performed by one or more programmable processors executing one or more computer programs to perform functions by operating input data and generating output. The process and logic flow may also be performed by dedicated logic circuitry, and the apparatus may also be implemented as the dedicated logic circuitry, such as an FPGA (Field Programmable Gate Array) or an ASIC (Application Specific Integrated Circuit).

Processors suitable for the execution of a computer program include, for example, both general and special purpose microprocessors, and any one or more processors of any kind of digital computer. Generally, a processor receives instructions and data from a read only memory or a random access memory or both. Elements of a computer may include a processor for executing instructions and one or more memory devices for storing instructions and data. Typically, the computer will also include one or more mass storage devices for storing data, or the computer is operatively coupled to receive or transfer data to or from the mass storage device, such as a magnetic disk, magnetic CD or CD. However, the computer does not need to have such a device. Moreover, the computer can be embedded in another device, such as a mobile phone, a personal digital assistant (PDA), a mobile audio player, a global positioning system (GPS) receiver, and the like. Computer readable media suitable for storing computer program instructions and data include all forms of nonvolatile memory, media and memory devices including, for example, semiconductor memory devices such as EPROM, EEPROM and flash memory devices; magnetic disks such as internal hard disks or removable Disks; magneto-optical disks; and CD ROM and DVD-ROM disks. The processor and memory can be supplemented by or incorporated in dedicated logic.

In order to provide interaction with a user, implementations of embodiments of the present invention may be provided with a display device (eg, a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user, as well as a keyboard and pointing device (eg, a mouse) Or the trackball is implemented by a computer whose user can provide input to the computer. Other kinds of devices may also be used to provide interaction with the user; for example, feedback provided to the user may be any form of sensory feedback, such as visual feedback, audible feedback, or haptic feedback; and input from the user may be received in any form , including auditory, voice, or tactile input.

The present invention is not to be construed as limiting the scope of the invention or the scope of the claimed invention, but should be understood as a description of the features of the example implementation of the invention. Certain features that are described in this disclosure in the context of a single implementation can also be provided in combination with a single implementation. Conversely, various features that are described in the context of a single implementation can also be provided in a plurality of implementations or in any suitable subcombination. Moreover, although features may be described above as being performed in some combination and even requiring such protection initially, in some cases one or more features from the claimed combination may be removed from the combination, and the claimed combination is claimed. Changes in sub-combinations or sub-combinations may be involved.

Similarly, although the operations are depicted in a particular order in the figures, this should not be construed as requiring that such operations be performed in the particular order shown, or in a sequential order, or Achieve the desired results. In some situations, multitasking and parallel processing may be advantageous. Moreover, the separation of various system components in the implementations described above should not be understood as requiring such separation in all implementations, and it should be understood that the described program components and systems can generally be integrated together in a single software product. Or be packaged into multiple software products.

Therefore, specific implementations of the invention have been described, and other implementations are within the scope of the following claims. For example, the actions recited in the claims can be performed in a different order, and the acts can still achieve the desired results. A number of implementations have been described. However, it will be understood that various modifications may be made without departing from the spirit and scope of the invention. For example, various forms of the flow shown above may be used, where the steps may be reordered, added, or removed. Accordingly, other implementations are within the scope of the claims.

Claims

Image information processing method, including:

Blocking at least part of the content of the image;

Providing questions related to the image; and

Get the answer information sent by the user when answering the question.
The image information processing method according to claim 1, wherein before the obtaining the answer information sent by the user when answering the question, the method further comprises:

Obtain information generated by the user in preparation for answering the question.
The image information processing method according to claim 2, wherein the obtaining information generated by the user in preparing to answer the question comprises:

Acquiring information generated by the user during the first operation of the masked portion of the image, the first operation being capable of removing the mask such that the image is displayed by the content of the masked portion.
The image information processing method according to claim 3, wherein the information generated during the execution of the first operation comprises at least one of removing information of a masked area, masking area removal track information, and time information.
The image information processing method according to claim 4, wherein the removing the information of the masking area comprises removing an area of the masking area and/or removing a position of the masking area.
The image information processing method according to claim 3, wherein the method further comprises: dividing the image into a plurality of units, and assigning value information to each unit; and the acquiring user performing the masked portion of the image The generating information during the first operation includes: counting the value information of the unit that is revealed after the user removes the masked area.
The image information processing method according to claim 6, wherein the value information of the unit is determined according to a degree of correlation between the unit and the question.
The image information processing method according to claim 6 or 7, wherein after the obtaining the answer information fed back by the user when answering the question, the method further comprises:

The answer information sent by the plurality of users and the information generated in the process of preparing to answer the question are counted, and the value information of the unit is adjusted according to the statistical result.
The image information processing method according to claim 7, wherein the assigning value information to each unit comprises: assigning a score to each unit, the size of the score and the unit and the problem The correlation size is positively correlated.
The image information processing method according to claim 3, wherein before the obtaining information generated by the user in preparing to answer the question, the method further comprises:

Selecting a first region in a portion of the image that is obscured, the first region being selected as an area that assists the user in answering the question after learning the content;

Acquiring the information generated by the user in preparing to answer the question includes: acquiring a second area of the user to remove the masked portion of the image, so as to combine the answer information of the user and the degree of fit of the first area and the second area The accuracy of the first region selection is determined.
The image information processing method according to any one of claims 1 to 7, 9 and 10, wherein after the obtaining the answer information sent by the user when answering the question, the method further comprises:

Acquiring the verification information sent by the user, the verification information including feedback information of the correctness and/or accuracy of the user and the preset answer corresponding to the question.
The image information processing method according to claim 11, wherein after the obtaining the verification information sent by the user, the method further comprises: transmitting the reward information to the user according to a predetermined policy.
The image information processing method according to any one of claims 1 to 7, 9 and 10, wherein the obtaining information generated by the user in preparing to answer the question further comprises: acquiring the user in preparation to answer the question Time information generated during the problem process.
The image information processing method according to claim 1, wherein the at least part of the content of the masked image comprises:

Generating a masked area;

The position of the obscured region on the image is moved in accordance with a predetermined strategy.
The image information processing method according to claim 14, wherein before the obtaining the answer information sent by the user when answering the question, the method further comprises:

Acquiring information generated by the user in preparing to answer the question; the information generated by the user in preparing to answer the question includes at least one of time information, moving speed information of the obscured area, and movement track information.
The image information processing method according to any one of claims 1 to 7, 9, 10, 14 and 15, wherein the method further comprises:

The information obtained from the user is counted to establish a data model and/or to quantify the image.
The image information processing method according to any one of claims 2-7, 9, 10, and 15, wherein the method further comprises:

Encrypting at least some of the information generated by the user in preparing to answer the question by the encryption algorithm to form a key;

Obtaining verification information sent by the user, so that the user uses the key to compete for the reward obtained according to the sending of the verification information;

The verification information includes feedback information of the user on the correctness and/or accuracy of the question and/or the preset answer corresponding to the question.
The image information processing method according to any one of claims 2-7, 9 and 10, wherein said image comprises a plurality of superimposed images, wherein an image located in the upper layer is determined as an image of the next layer The shielding layer; the method further includes:

Obtaining a second operation performed by the user; the second operation is capable of removing content displayed by the image of the previous layer such that the content of the next layer of image is displayed.
The image information processing method according to claim 18, wherein the method further comprises:

Obtaining a third operation performed by the user; the third operation can mask an area displayed by the underlying image and cause the content of the upper layer image to be displayed.
The image information processing method according to any one of claims 1 to 7, 9, 10, 14 and 15, wherein said image is composed of a plurality of sub-images, at least part of said sub-images being given Sub-image related issues.
An image information processing apparatus, comprising:

a masking module for shielding at least part of the content of the image;

a questioning module for providing questions related to the image;

The first obtaining module is configured to obtain answer information sent by the user when answering the question.
The image information processing apparatus according to claim 21, further comprising:

The second obtaining module is configured to obtain information generated by the user in preparing to answer the question.
The image information processing apparatus according to claim 22, wherein the second acquisition module is further configured to:

Acquiring information generated by the user during the first operation of the masked portion of the image, the first operation being capable of removing the mask such that the image is displayed by the content of the masked portion.
The image information processing apparatus according to claim 23, wherein the information generated during the execution of the first operation includes at least one of removing information of a masked area, masking area removal track information, and time information.
The image information processing apparatus according to claim 24, wherein the removing the information of the masking area comprises removing an area of the masking area and/or removing a position of the masking area.
The image information processing apparatus according to claim 23, wherein the apparatus further comprises: a value giving module for dividing the image into a plurality of units, and assigning value information to each unit; The generating information during the execution of the first operation by the masked portion includes: counting the value information of the unit that is revealed after the user removes the masked area.
The image information processing apparatus according to claim 26, wherein said value information of said unit is determined based on a correlation degree of said unit with said question.
The image information processing apparatus according to claim 26 or 27, wherein the apparatus further comprises:

The adjustment module is configured to count the answer information sent by the plurality of users and the information generated in the process of preparing to answer the question, and adjust the value information of the unit according to the statistical result.
The image information processing apparatus according to claim 27, wherein said assigning value information to each unit comprises: assigning a score to each unit, said size of said score and said unit and said problem The correlation size is positively correlated.
The image information processing apparatus according to claim 23, wherein said apparatus further comprises: a selection module for capturing the portion of the image that is obscured before acquiring information generated by the user in preparing to answer the question Selecting a first region, the first region being selected as an area that helps the user to answer the question after learning the content thereof;

The second obtaining module is further configured to: acquire a second area of the user to remove the masked portion of the image, so as to determine the first area selection according to the answer information of the user and the degree of fit of the first area and the second area The accuracy.
The image information processing apparatus according to any one of claims 21 to 27, 29, and 30, wherein said apparatus further comprises: a verification module, configured to: in response to the answer sent by the user when answering the question After the information, the verification information sent by the user is obtained, and the verification information includes feedback information of the correctness and/or accuracy of the user and the preset answer corresponding to the question.
The image information processing apparatus according to claim 31, wherein the apparatus further comprises: a reward module, configured to send the reward information to the user according to a predetermined policy after the obtaining the verification information sent by the user.
The image information processing apparatus according to any one of claims 21-27, 29 and 30, wherein the obtaining information generated by the user in preparing to answer the question further comprises: acquiring the user in preparation to answer the question Time information generated during the problem process.
The image information processing apparatus according to claim 21, wherein the at least masking module is further configured to:

Generating a masked area;

The position of the obscured region on the image is moved in accordance with a predetermined strategy.
The image information processing apparatus according to claim 34, wherein the apparatus further comprises a third obtaining module, configured to acquire the user in preparation for answering before the obtaining the answer information sent by the user when answering the question The information generated in the process of the problem; the information generated by the user in preparing to answer the question includes at least one of time information, moving speed information of the obscured area, and movement track information.
The image information processing apparatus according to any one of claims 21 to 27, 29, 30, 34 and 35, wherein said apparatus further comprises a statistical module for counting information acquired from said user so as to A data model is established and/or the image is quantitatively evaluated.
The image information processing apparatus according to any one of claims 22-27, 29, 30, and 35, wherein the apparatus further comprises:

And an encryption module, configured to encrypt, by using an encryption algorithm, at least a part of the information generated by the user in preparing to answer the question to form a key;

a third obtaining module, configured to acquire verification information sent by the user, so that the user uses the key to compete for the reward obtained according to the sending of the verification information;

The verification information includes feedback information of the user on the correctness and/or accuracy of the question and/or the preset answer corresponding to the question.
The image information processing apparatus according to any one of claims 22-27, 29 and 30, wherein said image comprises a plurality of superimposed images, wherein an image located in the upper layer is determined as an image of the next layer The shielding layer; the device further comprises:

And a fourth acquiring module, configured to acquire a second operation performed by the user; and the second operation is capable of removing the content displayed by the image of the previous layer to display the content of the image of the next layer.
The image information processing apparatus according to claim 38, wherein the apparatus further comprises:

And a fifth acquiring module, configured to acquire a third operation performed by the user; the third operation is capable of obscuring the area displayed by the underlying image and causing the content of the upper layer image to be displayed.
The image information processing apparatus according to any one of claims 21-27, 29, 30, 34 and 35, wherein said image is composed of a plurality of sub-images, at least part of said sub-images being given Sub-image related issues.
A storage medium storing a plurality of instructions adapted to be loaded by a processor to perform the image information processing method of any of claims 1-20.