Advertising resource data processing method, device, electronic device and readable storage medium
By receiving ad requests from the client on the server side, finding and selecting target advertising inventory data with similarity less than the preset threshold to send it to the client, solving the problem of repeated display of advertising inventory data and improving the usage of advertising time and advertising inventory data display accuracy.
Patent Information
- Application Number
- CN202011606189.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2020-12-28
- Publication Date
- 2024-12-06
- Estimated Expiration
- 2040-12-28
AI Technical Summary
Repeated display of inventory data leads to low advertising time usage, affecting the display of other inventory data.
By receiving ad requests from the client, find recommended inventory data corresponding to the identity, and select target inventory data with similarity less than the preset threshold from the alternative inventory data to send it to the client to avoid repeated display of similar advertisements Resource data.
It improves the usage of advertising time, reduces the repeated display of advertising inventory data, and improves the accuracy of advertising inventory data recommended to the client.
Smart Images

Figure CN112767006B_ABST
Abstract
Description
Technical Field
[0001] The present application belongs to the field of communication technology, and specifically relates to an advertising resource data processing method, device, electronic device and readable storage medium. Background Art
[0002] With the development of Internet technology, Internet advertising revenue has become one of the main sources of income for many companies. The server can respond to the advertising request sent by the client and send advertising resource data to the client to realize the distribution of advertising resource data, such as videos, animations and pictures.
[0003] At present, in the process of displaying advertising resource data, in the prior art, the advertising resource data is now displayed randomly, and the probability of advertisement duplication is high. A large amount of repeated advertising resource data occupies a large amount of advertising time, resulting in low utilization rate of advertising time and affecting the display of other advertising resource data.
[0004] Application Contents
[0005] The purpose of the embodiments of the present application is to provide an advertising resource data processing method, device, electronic device and readable storage medium, which can solve the problem of low utilization rate of advertising time.
[0006] In order to solve the above technical problems, this application is implemented as follows:
[0007] In a first aspect, an embodiment of the present application provides a method for processing advertising resource data, the method comprising:
[0008] Receiving an advertisement request sent by a client; the advertisement request includes an identity identifier of the client;
[0009] In response to the advertisement request, searching for recommended advertisement resource data corresponding to the identity identifier, and acquiring candidate advertisement resource data to be sent; the recommended advertisement resource data includes a first advertisement image; the recommended advertisement resource data is advertisement resource data that has been sent to the client;
[0010] Select target advertising resource data from the candidate advertising resource data and send them to the client; wherein the target advertising resource data includes a second advertising picture, and the similarity between the second advertising picture and the first advertising picture is less than a preset threshold.
[0011] In a second aspect, an embodiment of the present application provides an advertising resource data processing device, the device comprising:
[0012] A receiving module, configured to receive an advertisement request sent by a client; the advertisement request includes an identity identifier of the client;
[0013] A response module, configured to respond to the advertisement request, search for recommended advertisement resource data corresponding to the identity identifier, and obtain candidate advertisement resource data to be sent; the recommended advertisement resource data includes a first advertisement image; the recommended advertisement resource data is advertisement resource data that has been sent to the client;
[0014] A selection module is used to select target advertising resource data from the candidate advertising resource data and send the target advertising resource data to the client; wherein the target advertising resource data includes a second advertising picture, and the similarity between the second advertising picture and the first advertising picture is less than a preset threshold.
[0015] In a third aspect, an embodiment of the present application provides an electronic device, which includes a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the method described in the first aspect.
[0016] In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a program or instruction is stored, and when the program or instruction is executed by a processor, the steps of the method described in the first aspect are implemented.
[0017] In a fifth aspect, an embodiment of the present application provides a chip, comprising a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run a program or instruction to implement the method described in the first aspect.
[0018] In an embodiment of the present application, the server receives an advertisement request sent by a client, and in response to the advertisement request, searches for recommended advertisement resource data corresponding to the identity identifier, obtains candidate advertisement resource data to be sent, and selects target advertisement resource data from the candidate advertisement resource data and sends it to the client. By selecting target advertisement resource data from the candidate advertisement resource data based on the similarity between the advertisement images respectively included in the recommended advertisement resource data and the candidate advertisement resource data, it is possible to avoid recommending similar advertisement resource data to the client, thereby avoiding the client from repeatedly displaying similar advertisement resource data, and improving the utilization rate of advertisement time. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] Figure 1 is a flowchart of a method for processing advertising resource data according to an exemplary embodiment;
[0020] Figure 2 is a structural diagram of an advertising resource data processing device provided according to an exemplary embodiment;
[0021] Figure 3 is a structural diagram of an electronic device provided according to an exemplary embodiment;
[0022] Figure 4 A schematic diagram of the hardware structure of an electronic device to implement an embodiment of the present application. DETAILED DESCRIPTION
[0023] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0024] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here. In addition, the "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally represents that the objects associated with each other are in an "or" relationship.
[0025] The term "session" refers to one use of a client, where the client is an application (Application, App). The start of a session is when the client is displayed from the non-foreground to the foreground (including cold start and hot start of the client), and the end of a session is when the client switches from the foreground to the non-foreground (including returning to the desktop, killing the process, or switching to another client, etc.).
[0026] In conjunction with the accompanying drawings, a method for processing advertising resource data provided by an embodiment of the present application is described in detail below through specific embodiments and application scenarios.
[0027] Reference Figure 1 , Figure 1 is a flowchart of a method for processing advertising resource data according to an exemplary embodiment. Figure 1 As shown, the method may include:
[0028] Step 101: Receive an advertisement request sent by a client.
[0029] The advertisement request includes the client's identity. The client is, for example, an application installed on a terminal device such as a mobile phone, laptop, tablet computer, or wearable device. The identity is used to uniquely identify the user who uses the client, such as the identity document (ID) obtained by the user through client registration.
[0030] In this embodiment, the server can receive an advertisement request sent by the client, and in response to the advertisement request, send advertisement resource data to the client. During operation, the client can send an advertisement request to the server under certain conditions to obtain and display the advertisement resource data sent by the server. For example, the client can send an advertisement request to the server at startup to obtain advertisement resource data so as to display the advertisement resource data in the startup screen of the client. For another example, during operation, the client can send an advertisement request to the server to obtain advertisement resource data when a certain application page in the client is opened, and display the advertisement resource data at a preset position in the application page. The specific process of the client sending an advertisement request to the server can be based on the demand device, and this embodiment does not limit this.
[0031] The advertisement resource data includes multimedia data such as pictures, videos, and animations. This embodiment does not limit the specific form of the advertisement resource data.
[0032] Step 102: In response to the advertisement request, search for recommended advertisement resource data corresponding to the identity identifier, and obtain candidate advertisement resource data to be sent.
[0033] The recommended advertising resource data includes the first advertising image; the recommended advertising resource data is the advertising resource data that has been sent to the client.
[0034] In one embodiment, the first advertising picture is a picture pre-set in the recommended advertising resource data, or a frame image directly selected from all frame images included in the recommended advertising resource data, and the first advertising picture can represent the type of the recommended advertising resource data. The server can obtain the first advertising picture from the recommended advertising resource data by a preset method. For example, if the recommended advertising resource data is a picture, the server can directly use the recommended advertising resource data as the first advertising picture; if the recommended advertising resource data is an animation or a video, the server can select the first frame image or the last frame image in the animation or video from the recommended advertising resource data by a preset method as the first advertising picture. The first frame image and the last frame image can be frame images pre-set to represent the type of the recommended advertising resource data, or frame images in the advertising resource data that can be used to represent the type of the recommended advertising resource data. The specific process of the server determining the first advertising picture included in the recommended advertising resource data can be set according to demand, and this embodiment does not limit this.
[0035] In one embodiment, the server may record the advertising resource data that has been sent to the client. For example, the server may establish a corresponding first resource record queue for each client's identity identifier, and after each time the advertising resource data is sent to the client, the advertising identifier of the advertising resource data may be added to the first resource record queue to record the advertising resource data that has been sent to the client, that is, the recommended advertising resource data. Alternatively, after receiving and displaying the advertising resource data, the client may send the advertising identifier of the displayed advertising resource data to the server, and the server may receive the advertising identifier sent by the client and record it in the first resource record queue. The specific form of the advertising identifier can be set according to demand, and this embodiment does not limit this.
[0036] When the client sends an advertisement request to the server, it may send the advertisement request including the identity identifier to the server. Accordingly, after receiving the advertisement request, the server may first parse the advertisement request, determine the identity identifier included in the advertisement request, and then determine the first resource record queue corresponding to the identity identifier, and determine that the advertisement resource data corresponding to the advertisement identifier in the first resource record queue is the recommended advertisement resource data. For example, if the first resource record queue includes the advertisement identifier of advertisement resource data A and the advertisement identifier of advertisement resource data B, it may be determined that the recommended advertisement resource data includes advertisement resource data A and advertisement resource data B.
[0037] In this embodiment, after receiving the advertisement request sent by the client, the server may search for the advertisement resource data to be sent, i.e., the alternative advertisement resource data, in response to the advertisement request, so as to select the target advertisement resource data to be sent to the client from the alternative advertisement resource data. For example, after receiving the advertisement request, the server may send an advertisement resource data acquisition request to a third-party demand-side platform (DSP) to obtain the advertisement resource data returned by the third-party DSP, i.e., the alternative advertisement resource data. Alternatively, after receiving the advertisement request, the server may directly obtain multiple advertisement resource data as alternative advertisement resource data from the local DSP, such as advertisement resource data X, advertisement resource data Y, and advertisement resource data Z. The specific process of the server obtaining the alternative advertisement resource data from the third-party DSP or the local DSP can be set according to the needs, and this embodiment does not limit this.
[0038] Step 103: Select target advertising resource data from the candidate advertising resource data and send it to the client.
[0039] The target advertisement resource data includes a second advertisement picture, and the similarity between the second advertisement picture and the first advertisement picture is less than a preset threshold.
[0040] In one embodiment, a second advertisement picture may be set in advance in each candidate advertisement resource data, for example, the first frame image in the candidate advertisement resource data may be set as the second advertisement picture. Alternatively, a frame image may be directly selected from all frame images included in the candidate advertisement resource data as the second advertisement picture, and the second advertisement picture may represent the type of the candidate advertisement resource data. The understanding of the second picture may refer to the first advertisement picture, and this embodiment will not be elaborated on.
[0041] After obtaining the alternative advertising resource data, the server can first obtain the corresponding second advertising image from each alternative advertising resource data, and then determine the similarity between the first advertising image and each second advertising image, and determine the alternative advertising resource data to which the second advertising image whose similarity is less than a preset threshold belongs as the target advertising resource data.
[0042] Optionally, the method for determining the similarity between the first advertisement image and the second advertisement image may be implemented in the following manner:
[0043] Acquire the outline features of the first advertisement picture and the outline features of the second advertisement picture;
[0044] The similarity between the second advertisement picture and the first advertisement picture is calculated according to the outline feature of the first advertisement picture and the outline feature of the second advertisement picture.
[0045] In one embodiment, the contour similarity between the first advertisement image and the second advertisement image can be determined based on the contour features of the first advertisement image and the contour features of the second advertisement image, and the similarity between the first advertisement image and the second advertisement image can be represented by the contour similarity. For example, the first advertisement image included in the advertisement resource data A is a 32×32 image, that is, an image with a length of 32 pixels and a width of 32 pixels. The size of the first advertisement image can be reduced, and the 32×32 first advertisement image can be reduced to an 8×8 image, that is, an image with a length of 8 pixels and a width of 8 pixels, so as to reduce the data volume of the first advertisement image and reduce the amount of calculation. After the size of the first advertisement image is reduced, the reduced first advertisement image can be grayed to obtain a grayed image of the first advertisement image. The specific method of reducing and graying the image can be set according to the needs, and this embodiment does not limit this.
[0046] After obtaining the grayscale image of the first advertising picture, a discrete cosine transform (DCT) can be performed on the grayscale image to transform the 8×8 grayscale image into a 32×32 vector matrix, and extract the 64 vectors located in the first 8 rows and the first 8 columns of the 32×32 vector matrix, that is, the 8×8 vector matrix in the upper left corner. The 8×8 vector matrix is the low-frequency component in the first advertising picture, and the low-frequency component represents the contour features of the target object in the first advertising picture. The specific process of the DCT transformation can be set according to demand, and this embodiment does not limit this.
[0047] After extracting the low-frequency components in the first advertising image, the 64 low-frequency components in the 8×8 vector matrix can be binarized. First, the average value of the 64 low-frequency components is calculated, and then the low-frequency components greater than or equal to the average value are set to 1, and the low-frequency components less than the average value are set to 0, to obtain the 64 binarized low-frequency components. Finally, the hash value of the 64 low-frequency components after binarization can be calculated, and the 64 low-frequency components can be stretched into a 64-bit integer, that is, the contour feature vector of the first advertising image included in the advertising resource data A. The specific method of binarization can be set according to demand, and this embodiment does not limit this. Similarly, the contour feature vector of the first advertising image included in the advertising resource data B, as well as the contour feature vectors of the second advertising image respectively included in the advertising resource data X, the advertising resource data Y and the advertising resource data Z can be calculated.
[0048] It should be noted that the method of extracting the contour feature vectors of the first advertisement picture and the second advertisement picture may include but is not limited to a method of extracting low-frequency components after DCT transformation. In the process of reducing the first advertisement picture and the second advertisement picture, the first advertisement picture and the second advertisement picture may be reduced to the same size, for example, both reduced to 8×8 pictures, so as to avoid errors caused by the different sizes between the first advertisement picture and the second advertisement picture.
[0049] In this embodiment, after obtaining the contour feature vector of the first advertisement picture included in each recommended advertisement resource data and the contour feature vector of the second advertisement picture included in each alternative advertisement resource data, the cosine similarity between the contour feature vector of the second advertisement picture included in the alternative advertisement resource data and the contour feature vector of the first advertisement picture included in each recommended advertisement resource data can be calculated, that is, the similarity between the first advertisement picture and the second advertisement picture. For example, for advertisement resource data X, the cosine similarity between the contour feature vector of the second advertisement picture included in advertisement resource data X and the contour feature vector of the first advertisement picture included in advertisement resource data A can be calculated to obtain the similarity between the second advertisement picture included in advertisement resource data X and the first advertisement picture included in advertisement resource data A. Similarly, the similarity between the second advertisement picture included in advertisement resource data X and the first advertisement picture included in advertisement resource data B, the similarity between the second advertisement picture included in advertisement resource data Y and the first advertisement picture included in advertisement resource data A, and the similarity between the second advertisement picture included in advertisement resource data Y and the first advertisement picture included in advertisement resource data B can be calculated.
[0050] In actual applications, if the similarity between the first advertising image and the second advertising image is greater than or equal to a preset threshold, it means that the recommended advertising resource data corresponding to the first advertising image and the alternative advertising resource data corresponding to the second advertising image are advertising resource data of the same type. When the similarity between the first advertising image and the second advertising image is represented by contour similarity, the preset threshold may be a contour similarity threshold. In combination with the above example, if the cosine similarity between the second advertising image included in the advertising resource data X and the first advertising image included in the advertising resource data A is greater than or equal to the preset threshold, it means that the advertising resource data X and the advertising resource data A are the same type of advertising resource data, i.e., similar advertising resource data. The preset threshold can be set according to demand, and this embodiment does not impose any restrictions on this.
[0051] After determining the similarity between the first advertisement image and the second advertisement image, the server can determine the alternative advertisement resource data whose similarity between the first advertisement image and the second advertisement image is less than a preset threshold from all the alternative advertisement resource data, that is, determine the advertisement resource data that is not similar to each recommended advertisement resource data from all the alternative advertisement resource data, and send the dissimilar alternative advertisement resource data to the client as the target advertisement resource data. In combination with the above example, it can be determined that the advertisement resource data X and the advertisement resource data A are similar advertisement resource data. If the similarity between the second advertisement image included in the advertisement resource data Y and the first advertisement image included in the advertisement resource data A is less than the preset threshold, and the similarity between the second advertisement image included in the advertisement resource data Y and the first advertisement image included in the advertisement resource data B is less than the preset threshold, then it can be determined that the advertisement resource data Y is not similar to each recommended advertisement resource data. Similarly, it can be determined that the advertisement resource data Z is not similar to the recommended advertisement resource data. At this time, the advertisement resource data Y and the advertisement resource data Z can be sent to the client as the target advertisement resource data.
[0052] Among them, when there are multiple target advertising resource data, the server can select one or more of them as target advertising resource data and send them to the client according to preset conditions. In combination with the above example, the server can select one of the advertising resource data Y and the advertising resource data Z as the target advertising resource data and send the target advertising resource data to the client. The target advertising resource data can be the advertising resource data Z with the highest price among the advertising resource data Y and the advertising resource data Z. Accordingly, after receiving the target advertising resource data Z, the client can display the target advertising resource data Z.
[0053] In practical applications, the similarity between the first advertisement picture and the second advertisement picture is calculated by using the contour features of the first advertisement picture and the contour features of the second advertisement picture. The similarity between the first advertisement picture and the second advertisement picture can be accurately calculated by using the contour features of the target objects in the first advertisement picture and the second advertisement picture. The method for calculating the similarity between the first advertisement picture and the second advertisement picture may include but is not limited to the method using cosine similarity.
[0054] In summary, in this embodiment, the server receives an advertisement request sent by a client, and in response to the advertisement request, searches for recommended advertisement resource data corresponding to the identity identifier, obtains alternative advertisement resource data to be sent, and selects target advertisement resource data from the alternative advertisement resource data and sends it to the client. By selecting target advertisement resource data from the alternative advertisement resource data based on the similarity between the advertisement images respectively included in the recommended advertisement resource data and the alternative advertisement resource data, it is possible to avoid recommending similar advertisement resource data to the client, thereby avoiding the client from repeatedly displaying similar advertisement resource data and improving the utilization rate of advertisement time. At the same time, compared with the method of identifying similar advertisement resource data through an algorithm model, there is no need to manually annotate sample data, which can improve the accuracy of the advertisement resource data recommended to the client and avoid recommending similar advertisement resources to the client.
[0055] Optionally, the advertisement request may further include a session identifier of the client, and the step of searching for the recommended advertisement resource data corresponding to the identifier may be implemented in the following manner:
[0056] Find the recommended advertising resource data recorded under the identity ID corresponding to the session ID;
[0057] Accordingly, the step of obtaining the candidate advertisement resource data to be sent can be implemented in the following manner:
[0058] Determine candidate advertising inventory data from the advertising inventory data excluding the recommended advertising inventory data.
[0059] The session ID is used to uniquely identify each session of the client. The client can create a session ID to identify this session at the beginning of each session. For example, the client can generate a session ID to uniquely identify this session by combining the International Mobile Equipment Identity (IMEI) of the electronic device and the timestamp at the beginning of this session through the MD5 message digest algorithm or hash algorithm at each startup. The specific form and creation method of the session ID can be set according to the needs, and this embodiment does not limit this.
[0060] In this embodiment, the server can record the advertising resource data recommended to the client during each session of the client. For example, when the server receives a new session identifier, it can establish an empty second resource record queue, that is, when the client sends an advertisement request to the server for the first time during a session of the client, the server establishes a second resource record queue corresponding to the session included in the advertisement request. Specifically, each time the server receives an advertisement request, when it is determined that the advertisement request includes a session identifier, it can compare whether the session identifier received this time is the same as the session identifier in the advertisement request received last time. When the two session identifiers are the same, it can be determined that the advertisement request received this time and the advertisement request received last time are two advertisement requests sent during the same session; on the contrary, when the two session identifiers are different, it can be determined that the advertisement request received this time and the advertisement request received last time are not advertisement requests sent during the same session, that is, the session corresponding to the advertisement request this time is a new session, and an empty second resource record queue corresponding to the current session is established.
[0061] The second resource record queue is used to record the advertising identifiers of the advertising resource data sent by the server to the client and / or the advertising identifiers of the advertising resource data displayed by the client during this session. In combination with the above example, if the server receives an advertising request sent by the client at 9 o'clock, and the session identifier in the advertising request is different from the session identifier received at 8:52, the server can establish an empty second resource record queue. After 9 o'clock, if the server has sent advertising resource data C to the client, the advertising identifier of advertising resource data C can be recorded in the second resource record queue. Similarly, after 9 o'clock, if the client has displayed advertising resource data D during operation, the client can send the advertising identifier of advertising resource data D to the server, and the server can record the advertising identifier of advertising resource data D through the second resource record queue.
[0062] When the client sends an advertisement request to the server, it may send the advertisement request including the session identifier of this session to the server. After receiving the advertisement request, the server may first determine the second resource record queue corresponding to the identity identifier in the advertisement request, and determine the second resource record queue corresponding to the session identifier of this session from all second resource record queues, and further determine that the advertisement resource data C and advertisement resource data D corresponding to the advertisement identifier in the second resource record queue are recommended advertisement resource data.
[0063] Accordingly, in acquiring alternative advertising resource data, the server may determine alternative advertising resource data from other advertising resource data except advertising resource data C and advertising resource data D. For example, in the process of acquiring alternative advertising resource data from the local DSP, the server may directly use other advertising resource data except advertising resource data C and advertising resource data D as alternative advertising resource data. Alternatively, in the process of acquiring alternative advertising resource data from a third-party DSP, the server may send the advertising identifier of advertising resource data C and the advertising identifier of advertising resource data D to the third-party DSP, so that the third-party DSP returns other advertising resource data except advertising resource data C and advertising resource data D, i.e., alternative advertising resource data, based on the advertising identifier of advertising resource data C and the advertising identifier of advertising resource data D.
[0064] In this embodiment, when the server receives a new session identifier for the first time, it establishes a second resource record queue, and records the recommended advertising resource data through the second resource record queue during the session. When the advertising request sent by the client according to this session is received for the second, third, and subsequent times, the alternative advertising resource data is screened and determined according to the advertising resource data recorded in the second resource record queue, so as to avoid repeatedly sending the same advertising resource data to the client in one session. For example, during this session, when the server receives an advertising request for the first time, it sends advertising resource data X to the client, and the advertising identifier of advertising resource data X is recorded in the second resource record queue. Each time an advertising request is received thereafter, the second resource record queue includes the advertising identifier of advertising resource data X, so as to avoid repeatedly sending advertising resource data X to the client in this session, and solve the problem of repeated display of advertising resource data X during one session of the client.
[0065] Optionally, the method may further include:
[0066] If the session identifier is not found under the identity identifier, obtain the time interval between the advertisement request and the last advertisement request received;
[0067] When the time interval is less than or equal to the first preset time length, the recommended advertisement resource data recorded corresponding to the session identifier of the last advertisement request is obtained.
[0068] In this embodiment, when the server receives a new session identifier, it can obtain the recommended advertising resource data recorded corresponding to the session identifier of the last advertising request if the time interval between the current advertising request and the last received advertising request is less than or equal to the first preset duration.
[0069] For example, the server can record the receiving time of each advertising request, so as to compare the receiving time of this advertising request with the receiving time of the last advertising request received when receiving a new session identifier. Based on the above example, the server receives an advertising request including a new session identifier at 9 o'clock. If the second resource record queue corresponding to the session identifier in this advertising request is not found, if the receiving time of the last advertising request received is 8:52, it can be determined that the time interval between the advertising request received this time and the advertising request received last is less than or equal to the first preset time length, and the first preset time length is, for example, 5 minutes. At this time, the server can use the advertising resource data corresponding to the advertising identifier in the second resource record queue corresponding to the session identifier in the last advertising request as the recommended advertising resource data.
[0070] In actual applications, when the server receives a new session identifier, if the time interval between the advertisement request received this time and the advertisement request received last time is less than or equal to the first preset time length, it means that the interval between the two sessions is short, indicating that the user is continuously using the client. Using the same recommended advertisement resource data during the two sessions can avoid repeatedly sending the same advertisement resource data to the user during the user's continuous use of the client, reduce invalid advertisement resource data display, and improve the efficiency of using advertisement time.
[0071] Optionally, the method for determining the similarity between the first advertisement image and the second advertisement image may also be implemented in the following manner:
[0072] Obtaining the grayscale features of the first advertisement image and the grayscale features of the second advertisement image;
[0073] The similarity between the second advertisement grayscale and the first advertisement grayscale is calculated according to the grayscale feature of the first advertisement picture and the grayscale feature of the second advertisement picture.
[0074] In this embodiment, the grayscale similarity between the first advertising picture and the second advertising picture can also be calculated based on the grayscale features of the first advertising picture and the grayscale features of the second advertising picture, and the similarity between the first advertising picture and the second advertising picture can be represented by the grayscale similarity. For example, if the first advertising picture included in the advertising resource data A is a 32×32 picture, the first advertising picture can be reduced to an 8×8 picture, and the reduced first advertising picture is grayscaled to obtain an 8×8 grayscale image. Then, the 8×8 grayscale image can be binarized. First, the average value of the grayscale value of each pixel in the 8×8 grayscale image is calculated, and then the grayscale values greater than or equal to the average value are set to 1, and the grayscale values less than the average value are set to 0, to obtain 64 binarized vectors. Finally, the hash value of the 64 binarized vectors can be calculated, and the 64 vectors can be stretched into a 64-bit integer, that is, the grayscale feature vector of the first advertising picture included in the advertising resource data A. Similarly, the grayscale feature vector of the first advertisement picture included in the advertisement resource data B and the grayscale feature vectors of the second advertisement pictures included in the advertisement resource data X, advertisement resource data Y and advertisement resource data Z respectively can be calculated.
[0075] After obtaining the grayscale feature vector of the first advertising picture included in each recommended advertising resource data and the grayscale feature vector of the second advertising picture included in each alternative advertising resource data, the cosine similarity between the grayscale feature vector of the second advertising picture included in the alternative advertising resource data and the grayscale feature vector of the first advertising picture included in each recommended advertising resource data can be calculated, that is, the similarity between the second advertising picture and the first advertising picture. For example, for advertising resource data X, the cosine similarity between the grayscale feature vector of the second advertising picture included in advertising resource data X and the grayscale feature vector of the first advertising picture included in advertising resource data A can be calculated to obtain the similarity between the second advertising picture included in advertising resource data X and the first advertising picture included in advertising resource data A. Similarly, the similarity between the second advertising picture included in advertising resource data X and the first advertising picture included in advertising resource data B, the similarity between the second advertising picture included in advertising resource data Y and the first advertising picture included in advertising resource data A, and the similarity between the second advertising picture included in advertising resource data Y and the first advertising picture included in advertising resource data B can be calculated.
[0076] When the similarity between the first advertisement picture and the second advertisement picture is represented by grayscale similarity, the preset threshold may be a grayscale similarity threshold.
[0077] In practical applications, the similarity between the first advertising picture and the second advertising picture is calculated by the grayscale features of the first advertising picture and the grayscale features of the second advertising picture. The similarity between the first advertising picture and the second advertising picture can be accurately calculated by the grayscale features of the target objects in the first advertising picture and the second advertising picture.
[0078] Optionally, the server can select target advertising resource data from the alternative advertising resource data in combination with the contour features and grayscale features of the first advertising image and the second advertising image. In combination with the above example, if it is calculated that the contour similarity between the second image included in the alternative advertising resource data and the first image included in the recommended advertising resource data is less than the contour similarity threshold, and the grayscale similarity is less than the grayscale similarity threshold, then it is determined that the alternative advertising resource data and the recommended advertising resource data are similar advertising resource data; on the contrary, if the contour similarity between the second image included in the alternative advertising resource data and the first image included in the recommended advertising resource data is greater than or equal to the contour similarity threshold, or the grayscale similarity is greater than or equal to the grayscale similarity threshold, then it is determined that the alternative advertising resource data and the recommended advertising resource data are dissimilar advertising resource data, and the dissimilar advertising resource data can be used as the target advertising resource data to be sent to the client.
[0079] In practical applications, the target advertisement resource data may be selected from the candidate advertisement resource data according to the contour similarity and grayscale similarity between the second advertisement image and the first advertisement image, so that the target advertisement resource data may be selected more accurately.
[0080] Optionally, the method may further include:
[0081] In the case where the session identifier is the same as the last received session identifier, if the number of pre-recorded negative feedbacks from the user on the advertising resource data displayed by the client is greater than or equal to a preset number, sending the advertising resource data to the client is prohibited;
[0082] The number of negative feedbacks is set to zero when the session identifier is received for the first time.
[0083] In this embodiment, negative feedback indicates that the user does not like the advertising resource data or is not interested in the advertising resource data. After receiving the negative feedback from the user on the advertising resource data, the client may send a notification to the server, and the server may respond to the notification sent by the client and accumulate the number of negative feedbacks. For example, during the process of displaying the advertising resource data, if the user clicks a "close" button, a "not interested" button, or a "do not show again" button and performs negative feedback operations on the advertising resource data, the client may respond to each negative feedback from the user and send a notification to the server, and the server may accumulate the number of negative feedbacks received.
[0084] After receiving the advertisement request sent by the client, if the session identifier is different from the session identifier received last time, the server can determine that this session is different from the last session, and can set the number of negative feedbacks to zero, and restart recording the number of negative feedbacks during this session. On the contrary, if the session identifier is the same as the session identifier received last time, it can be determined that this session is the same as the last session. At this time, the number of negative feedbacks can be compared with the preset number. If the number of negative feedbacks is greater than or equal to the preset number, the advertisement resource data will not be sent to the client, and the corresponding client will not display the advertisement resource data. On the contrary, if the number of negative feedbacks is less than the preset number, the step of sending the target advertisement resource data to the client is executed.
[0085] In actual applications, whether to send advertising resource data to users can be determined based on the number of negative feedbacks from users during each session, to avoid sending advertising resource data to users when the number of negative feedbacks is high during each session, causing user discomfort and reducing the efficiency of using advertising resource data.
[0086] Optionally, the process of setting the number of negative feedbacks to zero can be achieved as follows:
[0087] In the case where the session identifier is received for the first time, if the time interval between the advertisement request corresponding to the session identifier and the last advertisement request received is greater than a preset time length, the number of negative feedbacks is set to zero.
[0088] In this embodiment, when the server receives a new session identifier, it can set the number of negative feedbacks to zero if the time interval between the current advertisement request and the last advertisement request received is greater than the preset time length. On the contrary, if the time interval between the current advertisement request and the last advertisement request received is less than or equal to the preset time length, the number of negative feedbacks in the last session is directly used.
[0089] In actual applications, when the server receives a new session identifier, it sets the number of negative feedbacks to zero when the time interval between the current ad request and the previous ad request is greater than the preset duration, and directly uses the number of negative feedbacks during the previous session when the time interval between the current ad request and the previous ad request is less than or equal to the preset duration. This can accumulate the number of negative feedbacks in a shorter period of time, avoid clearing the number of negative feedbacks in a shorter period of time, and improve the accuracy of negative feedback control.
[0090] It should be noted that the advertising resource data processing method provided in the embodiment of the present application can be executed by an advertising resource data processing device, or by a control module in the advertising resource data processing device for executing and loading an advertising resource data processing method. In the embodiment of the present application, the advertising resource data processing method provided in the embodiment of the present application is described by taking the advertising resource data processing device executing and loading an advertising resource data processing method as an example.
[0091] Reference Figure 2 , Figure 2 is a structural diagram of an advertising resource data processing device provided according to an exemplary embodiment. Figure 2 As shown, the device 200 may include: a receiving module 201 , a responding module 202 and a selecting module 203 .
[0092] The receiving module 201 is used to receive an advertisement request sent by a client; the advertisement request includes an identity identifier of the client.
[0093] The response module 202 is used to respond to the advertisement request, find the recommended advertisement resource data corresponding to the identity identifier, and obtain the candidate advertisement resource data to be sent; the recommended advertisement resource data includes the first advertisement image; the recommended advertisement resource data is the advertisement resource data that has been sent to the client.
[0094] The selection module 203 is used to select target advertising resource data from the candidate advertising resource data and send it to the client; wherein the target advertising resource data includes a second advertising picture, and the similarity between the second advertising picture and the first advertising picture is less than a preset threshold.
[0095] In summary, in this embodiment, the server receives an advertisement request sent by a client, and in response to the advertisement request, searches for recommended advertisement resource data corresponding to the identity identifier, obtains candidate advertisement resource data to be sent, and selects target advertisement resource data from the candidate advertisement resource data and sends it to the client. By selecting target advertisement resource data from the candidate advertisement resource data based on the similarity between the advertisement images respectively included in the recommended advertisement resource data and the candidate advertisement resource data, it is possible to avoid recommending similar advertisement resource data to the client, thereby avoiding the client from repeatedly displaying similar advertisement resource data, and improving the utilization rate of advertisement time.
[0096] Optionally, the advertisement request further includes a session identifier of the client, and the response module 202 may include:
[0097] The search unit is used to search for the recommended advertising resource data recorded corresponding to the session identifier under the identity identifier.
[0098] The determining unit is used to determine the candidate advertising resource data from the advertising resource data without the recommended advertising resource data recorded corresponding to the session identifier.
[0099] Optionally, the search unit is also used to obtain the time interval between the advertisement request and the last advertisement request received when no session identifier is found under the identity identifier; and to obtain the recommended advertisement resource data recorded corresponding to the session identifier of the last advertisement request when the time interval is less than or equal to a first preset duration.
[0100] Optionally, the apparatus 200 may include:
[0101] An acquisition module, used to acquire the outline features of the first advertisement picture and the outline features of the second advertisement picture;
[0102] The calculation module is used to calculate the similarity between the second advertisement picture and the first advertisement picture according to the outline feature of the first advertisement picture and the outline feature of the second advertisement picture.
[0103] Optionally, the apparatus 200 may include:
[0104] An acquisition module, used to acquire the grayscale features of the first advertisement image and the grayscale features of the second advertisement image;
[0105] The calculation module is used to calculate the similarity between the second advertisement grayscale and the first advertisement grayscale according to the grayscale features of the first advertisement picture and the grayscale features of the second advertisement picture.
[0106] The advertising resource data processing device in the embodiment of the present application can be a device, or a component, integrated circuit, or chip in a terminal. The device can be a mobile electronic device or a non-mobile electronic device. Exemplarily, the mobile electronic device can be a mobile phone, a tablet computer, a laptop computer, a PDA, an in-vehicle electronic device, a wearable device, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (PDA), etc. The non-mobile electronic device can be a server, a network attached storage (NAS), a personal computer (PC), a television (TV), a teller machine or a self-service machine, etc., which is not specifically limited in the embodiment of the present application.
[0107] The advertising resource data processing device in the embodiment of the present application may be a device having an operating system. The operating system may be an Android operating system, an iOS operating system, or other possible operating systems, which are not specifically limited in the embodiment of the present application.
[0108] The advertising resource data processing device provided in the embodiment of the present application can achieve Figure 1 To avoid repetition, the various processes implemented by the advertising resource data processing device in the illustrated method embodiment will not be described again here.
[0109] Optionally, an embodiment of the present application further provides an electronic device, such as Figure 3 As shown, Figure 3 It is a structural diagram of an electronic device provided according to an exemplary embodiment, and the electronic device includes a processor 301, a memory 302, and a program or instruction stored in the memory 302 and executable on the processor 301. When the program or instruction is executed by the processor 301, each process of the above-mentioned advertising resource data processing method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.
[0110] It should be noted that the electronic devices in the embodiments of the present application include the mobile electronic devices and non-mobile electronic devices described above, and the electronic devices include the client in the above embodiments to implement the methods described in the above embodiments.
[0111] Figure 4 A schematic diagram of the hardware structure of an electronic device to implement an embodiment of the present application.
[0112] The electronic device 400 includes but is not limited to components such as a radio frequency unit 401 , a network module 402 , an audio output unit 403 , an input unit 404 , a sensor 405 , a display unit 406 , a user input unit 407 , an interface unit 408 , a memory 409 , and a processor 410 .
[0113] Those skilled in the art will appreciate that the electronic device 400 may also include a power source (such as a battery) for supplying power to each component, and the power source may be logically connected to the processor 410 through a power management system, thereby implementing functions such as managing charging, discharging, and power consumption management through the power management system. Figure 4 The electronic device structure shown in the figure does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently, which will not be described in detail here.
[0114] The processor 410 is configured to receive an advertisement request sent by a client; the advertisement request includes an identity identifier of the client;
[0115] In response to the advertisement request, the recommended advertisement resource data corresponding to the identity identifier is searched, and the candidate advertisement resource data to be sent is obtained; the recommended advertisement resource data includes the first advertisement image; the recommended advertisement resource data is the advertisement resource data that has been sent to the client;
[0116] Select target advertising resource data from the candidate advertising resource data and send them to the client; wherein the target advertising resource data includes a second advertising picture, and the similarity between the second advertising picture and the first advertising picture is less than a preset threshold.
[0117] In summary, in this embodiment, the server receives an advertisement request sent by a client, and in response to the advertisement request, searches for recommended advertisement resource data corresponding to the identity identifier, obtains candidate advertisement resource data to be sent, and selects target advertisement resource data from the candidate advertisement resource data and sends it to the client. By selecting target advertisement resource data from the candidate advertisement resource data based on the similarity between the advertisement images respectively included in the recommended advertisement resource data and the candidate advertisement resource data, it is possible to avoid recommending similar advertisement resource data to the client, thereby avoiding the client from repeatedly displaying similar advertisement resource data, and improving the utilization rate of advertisement time.
[0118] Optionally, the advertisement request also includes a session identifier of the client;
[0119] The processor 410 is specifically used to search for the recommended advertising resource data recorded corresponding to the session identifier under the identity identifier;
[0120] Determine candidate advertising inventory data from the advertising inventory data excluding the recommended advertising inventory data.
[0121] In this embodiment, when the server receives a new session identifier for the first time, it establishes a second resource record queue, and records the recommended advertising resource data through the second resource record queue during the session. When the advertising request sent by the client according to this session is received for the second, third, and subsequent times, the alternative advertising resource data is screened and determined according to the advertising resource data recorded in the second resource record queue, so as to avoid repeatedly sending the same advertising resource data to the client in one session. For example, during this session, when the server receives an advertising request for the first time, it sends advertising resource data X to the client, and the advertising identifier of advertising resource data X is recorded in the second resource record queue. Each time an advertising request is received thereafter, the second resource record queue includes the advertising identifier of advertising resource data X, so as to avoid repeatedly sending advertising resource data X to the client in this session, and solve the problem of repeated display of advertising resource data X during one session of the client.
[0122] Optionally, the processor 410 is further used to obtain the time interval between the advertisement request and the last advertisement request received when no session identifier is found under the identity identifier; and to obtain the recommended advertisement resource data recorded corresponding to the session identifier of the last advertisement request when the time interval is less than or equal to a first preset duration.
[0123] In actual applications, when the server receives a new session identifier, if the time interval between the advertisement request received this time and the advertisement request received last time is less than or equal to the first preset time length, it means that the interval between the two sessions is short, indicating that the user is continuously using the client. Using the same recommended advertisement resource data during the two sessions can avoid repeatedly sending the same advertisement resource data to the user during the user's continuous use of the client, reduce invalid advertisement resource data display, and improve the efficiency of using advertisement time.
[0124] Optionally, the processor 410 is further configured to obtain contour features of the first advertisement picture and contour features of the second advertisement picture; and calculate the similarity between the second advertisement picture and the first advertisement picture based on the contour features of the first advertisement picture and the contour features of the second advertisement picture.
[0125] In practical applications, the similarity between the first advertising picture and the second advertising picture is calculated by using the contour features of the first advertising picture and the contour features of the second advertising picture. The similarity between the first advertising picture and the second advertising picture can be accurately calculated by using the contour features of the target objects in the first advertising picture and the second advertising picture.
[0126] Optionally, processor 410 is further configured to obtain grayscale features of the first advertisement image and grayscale features of the second advertisement image; and calculate the similarity between the second advertisement grayscale and the first advertisement grayscale based on the grayscale features of the first advertisement image and the grayscale features of the second advertisement image.
[0127] In practical applications, the similarity between the first advertising picture and the second advertising picture is calculated by the grayscale features of the first advertising picture and the grayscale features of the second advertising picture. The similarity between the first advertising picture and the second advertising picture can be accurately calculated by the grayscale features of the target objects in the first advertising picture and the second advertising picture.
[0128] An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, each process of the above-mentioned advertising resource data processing method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.
[0129] The processor is a processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.
[0130] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned advertising resource data processing method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.
[0131] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.
[0132] It should be noted that, in this article, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.
[0133] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present application.
[0134] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.
Claims
1. A method for processing advertising resource data, characterized in that: include: Receive the advertisement request sent by the client; The advertisement request includes the identity of the client; In response to the advertisement request, the recommended advertisement resource data corresponding to the identity identifier is searched, and the candidate advertisement resource data to be sent is obtained; the recommended advertisement resource data includes a first advertisement picture; the recommended advertisement resource data is the advertisement resource data sent to the client; the first advertisement picture is a preset image representing the type of the recommended advertisement resource data; Selecting target advertising resource data from the candidate advertising resource data and sending the target advertising resource data to the client; wherein the target advertising resource data includes a second advertising picture, and the similarity between the second advertising picture and the first advertising picture is less than a preset threshold; The step of selecting target advertisement resource data from the candidate advertisement resource data and sending the target advertisement resource data to the client includes: Obtaining the corresponding second advertisement picture from each candidate advertisement resource data, respectively, the second advertisement picture being a preset image representing the type of the candidate advertisement resource data, determining the similarity between the first advertisement picture and each second advertisement picture, respectively, and determining the candidate advertisement resource data to which the second advertisement picture having the similarity less than a preset threshold belongs as the target advertisement resource data; The determining of the similarity between the first advertisement picture and each of the second advertisement pictures comprises: Based on the grayscale feature vector or the contour feature vector, the similarity between the first advertisement picture and each of the second advertisement pictures is determined.
2. The method according to claim 1, characterized in that The advertisement request also includes a session identifier of the client, and searching for recommended advertisement resource data corresponding to the identity identifier includes: Searching for the recommended advertising resource data recorded under the identity identifier and corresponding to the session identifier; The step of obtaining the candidate advertisement resource data to be sent includes: The candidate advertising resource data is determined from the advertising resource data excluding the recommended advertising resource data.
3. The method according to claim 2, characterized in that Also includes: If the session identifier is not found under the identity identifier, obtaining a time interval between the advertisement request and the last advertisement request received; When the time interval is less than or equal to the first preset duration, the recommended advertisement resource data recorded corresponding to the session identifier of the last advertisement request is obtained.
4. The method according to any one of claims 1 to 3, characterized in that Before selecting target advertisement resource data from the candidate advertisement resource data and sending the target advertisement resource data to the client, the method further includes: Acquire outline features of the first advertisement picture and outline features of the second advertisement picture; The similarity between the second advertisement picture and the first advertisement picture is calculated according to the outline feature of the first advertisement picture and the outline feature of the second advertisement picture.
5. The method according to any one of claims 1 to 3, characterized in that: Before selecting target advertisement resource data from the candidate advertisement resource data and sending the target advertisement resource data to the client, the method further includes: Obtaining the grayscale features of the first advertisement picture and the grayscale features of the second advertisement picture; The similarity between the second advertisement picture and the first advertisement picture is calculated according to the grayscale feature of the first advertisement picture and the grayscale feature of the second advertisement picture.
6. A device for processing advertising resource data, characterized in that: include: A receiving module, used for receiving an advertisement request sent by a client; The advertisement request includes the identity of the client; A response module, configured to respond to the advertisement request, search for the recommended advertisement resource data corresponding to the identity identifier, and obtain the candidate advertisement resource data to be sent; the recommended advertisement resource data includes a first advertisement image; the recommended advertisement resource data is the advertisement resource data that has been sent to the client; the first advertisement image is a preset image representing the type of the recommended advertisement resource data; A selection module is used to select target advertising resource data from the alternative advertising resource data and send it to the client; wherein the target advertising resource data includes a second advertising picture, and the similarity between the second advertising picture and the first advertising picture is less than a preset threshold; wherein the selection of the target advertising resource data from the alternative advertising resource data and sending it to the client includes: respectively obtaining the corresponding second advertising picture from each of the alternative advertising resource data, the second advertising picture being a preset image representing the type of the alternative advertising resource data, determining the similarity between the first advertising picture and each of the second advertising pictures, and determining that the alternative advertising resource data to which the second advertising picture with the similarity less than the preset threshold belongs is the target advertising resource data; the determination of the similarity between the first advertising picture and each of the second advertising pictures includes: determining the similarity between the first advertising picture and each of the second advertising pictures based on a grayscale feature vector or a contour feature vector.
7. The device according to claim 6, characterized in that The advertisement request also includes a session identifier of the client, and the response module includes: A searching unit, configured to search for the recommended advertising resource data recorded under the identity identifier and corresponding to the session identifier; The determining unit is used to determine the candidate advertising resource data from the advertising resource data excluding the recommended advertising resource data.
8. The device according to claim 7, characterized in that The search unit is further configured to, when the session identifier is not found under the identity identifier, obtain the time interval between the advertisement request and the last advertisement request received; and, when the time interval is less than or equal to a first preset duration, obtain the recommended advertisement resource data recorded corresponding to the session identifier of the last advertisement request.
9. The device according to any one of claims 6 to 8, characterized in that Also includes: An acquisition module, used to acquire the outline features of the first advertisement picture and the outline features of the second advertisement picture; A calculation module is used to calculate the similarity between the second advertisement picture and the first advertisement picture according to the outline features of the first advertisement picture and the outline features of the second advertisement picture.
10. The device according to any one of claims 6 to 8, characterized in that Also includes: An acquisition module, used to acquire the grayscale features of the first advertisement picture and the grayscale features of the second advertisement picture; A calculation module is used to calculate the similarity between the second advertisement picture and the first advertisement picture according to the grayscale features of the first advertisement picture and the grayscale features of the second advertisement picture.
