An advertising placement method, device, electronic device, and readable storage medium

Abstract

An embodiment of the present invention provides an advertisement delivery method, device, electronic device, and readable storage medium. The method includes: receiving a traffic request initiated by a client in an information flow object; in response to the traffic request, reading a target operation gesture of the user corresponding to the client and a feedback parameter of the client for the advertisement, where the feedback parameter is used to describe the degree of positive feedback of the user for the advertisement; determining a delivery parameter negatively correlated with the feedback parameter, where the delivery parameter is used to describe the number of information items browsed by the user in the information flow object when the advertisement to be delivered is first displayed, and the display interval of the advertisement to be delivered; and delivering the advertisement to be delivered according to the delivery parameter and the target operation gesture. According to the embodiment of the present invention, the personalization degree of advertisement delivery can be improved.

Description

Technical Field

[0001] The present invention relates to the field of information processing technologies, and in particular, to an advertisement placement method, device, electronic device, and readable storage medium. Background Art

[0002] With the continuous development of the Internet, information flow objects have been widely used due to the characteristics of a large number of displayed information and good browsing experience. As a form of advertisement placed in the information flow, advertisements in the information flow are naturally integrated into the information flow objects.

[0003] Currently, the display methods of advertisements in the vast majority of information flows are relatively fixed. That is, after determining the first display position of the advertisement on the page of the information flow object, advertisements are inserted every fixed number thereafter. Therefore, the current advertisement placement method has the problem of lacking personalization. Summary of the Invention

[0004] The purpose of the embodiments of the present invention is to provide an advertisement placement method, device, electronic device, and readable storage medium, which can improve the degree of personalization of advertisement placement. The specific technical solutions are as follows:

[0005] In the first aspect of the present invention, first, an advertisement placement method is provided, including:

[0006] Receiving a traffic request initiated by a client in an information flow object;

[0007] In response to the traffic request, reading the target operation gesture of the user corresponding to the client and the feedback parameter of the client for the advertisement; the feedback parameter is used to describe the degree of positive feedback of the user for the advertisement;

[0008] Determining a placement parameter negatively correlated with the feedback parameter, the placement parameter is used to describe the number of information items browsed by the user in the information flow object when the advertisement to be placed is first displayed, and the display interval of the advertisement to be placed;

[0009] Placing the advertisement to be placed according to the placement parameter and the target operation gesture.

[0010] In the second aspect of the present invention, an advertisement placement device is further provided, including:

[0011] A receiving module, configured to receive a traffic request initiated by a client in an information flow object;

[0012] A reading module, configured to read the target operation gesture of the user corresponding to the client and the feedback parameter of the client for the advertisement in response to the traffic request; the feedback parameter is used to describe the degree of positive feedback of the user for the advertisement;

[0013] A determination module, configured to determine delivery parameters that are negatively correlated with feedback parameters, where the delivery parameters are used to describe the number of pieces of information that a user browses in an information flow object when a to-be-delivered advertisement is first displayed, and the display interval of the to-be-delivered advertisement;

[0014] A delivery module, configured to deliver the to-be-delivered advertisement according to the delivery parameters and a target operation gesture.

[0015] In yet another aspect of the implementation of the present invention, there is also provided a computer-readable storage medium storing instructions that, when run on a computer, cause the computer to execute the advertisement delivery method described in any one of the above.

[0016] In yet another aspect of the implementation of the present invention, there is also provided a computer program product containing instructions that, when run on a computer, cause the computer to execute the advertisement delivery method described in any one of the above.

[0017] In an embodiment of the present invention, in response to a traffic request initiated by a client in an information flow object, a target operation gesture of a user corresponding to the client and a feedback parameter of the client for an advertisement are read, and delivery parameters that are negatively correlated with the feedback parameter are determined. Among them, the feedback parameter is used to describe the degree of positive feedback of the user for the advertisement, that is, the acceptance degree of the user for the advertisement. The larger the feedback parameter, the higher the acceptance degree of the user for the advertisement. The feedback parameter is negatively correlated with the delivery parameters, and the delivery parameters are used to describe the number of pieces of information that a user browses in an information flow object when a to-be-delivered advertisement is first displayed, and the display interval of the to-be-delivered advertisement. Then, the larger the feedback parameter, the smaller the number of pieces of information that a user browses in an information flow object when the to-be-delivered advertisement is first displayed, and the smaller the display interval of the to-be-delivered advertisement, that is, the to-be-delivered advertisement appears earlier in the process of the user using the information flow object, and the appearance frequency can also be relatively high. Finally, according to the delivery parameters that are negatively correlated with the feedback parameter and the target operation gesture, the to-be-delivered advertisement is delivered, which can combine the feedback situation of the user for the advertisement and the target operation gesture, and perform targeted advertisement delivery, making the advertisement delivery more flexible and personalized. Description of the Drawings

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art.

[0019] Figure 1 It is a schematic diagram of an information flow object provided by an embodiment of the present invention;

[0020] Figure 2 It is a flowchart of an advertisement delivery method provided by an embodiment of the present invention;

[0021] Figure 3It is a schematic diagram of an advertisement placement provided by an embodiment of the present invention;

[0022] Figure 4 It is another schematic diagram of an advertisement placement provided by an embodiment of the present invention;

[0023] Figure 5 It is a schematic structural diagram of an advertisement placement device provided by an embodiment of the present invention;

[0024] Figure 6 It is a schematic hardware structure diagram of an electronic device provided by an embodiment of the present invention. Detailed implementation manners

[0025] Next, the technical solutions in the embodiments of the present invention will be described in conjunction with the accompanying drawings in the embodiments of the present invention.

[0026] Next, a brief description will be given to the technical terms involved in the present invention.

[0027] Information flow, the information can include short videos, news, products, etc. The flow can refer to the way the information appears, that is, it continuously flows like a waterfall, presenting new information content to the user.

[0028] Information flow object, refers to an object used to display the information flow, such as an application program, which has the characteristics of a large amount of content and a good mobile client experience. It can continuously present new content during the user's refresh process. The way suitable for sliding by the mobile client can provide a more convenient browsing experience for the user.

[0029] The advertisement placement method provided by the embodiments of the present invention can be applied to at least the following application scenarios, which will be described below.

[0030] Currently, in recent years, with the rapid development of information flow objects, advertisements in the information flow, as a form of advertisement placed in the information flow, naturally integrate into the information flow objects. However, currently, the display methods of the vast majority of advertisements in the information flow are relatively fixed, that is, after determining the first display position of the advertisement on the page of the information flow object, advertisements are inserted every fixed number thereafter. As Figure 1 shown, four pieces of content are displayed in the information flow object. If it is set to display one advertisement every three pieces of content, then during the user's sliding operation on the information flow object, one advertisement to be placed will be displayed every time three pieces of information flow content are displayed, and the advertisement placement method is relatively fixed. Therefore, the current advertisement placement method has the problem of lacking personalization.

[0031] Based on the above application scenarios, the advertisement placement method provided by the embodiments of the present invention will be described in detail below.

[0032] Next, the advertisement placement method provided by the embodiments of the present invention will be described.

[0033] Figure 2 Flowchart of an advertising placement method provided by an embodiment of the present invention.

[0034] As Figure 2 shown, the advertising placement method may include step 210 - step 240. This method is applied to an advertising placement device, and is specifically as follows:

[0035] Step 210, receiving a traffic request initiated by a client in an information flow object.

[0036] Step 220, in response to the traffic request, reading the target operation gesture of the user corresponding to the client and the feedback parameter of the client for the advertisement; the feedback parameter is used to describe the positive feedback degree of the user for the advertisement.

[0037] Step 230, determining a placement parameter negatively correlated with the feedback parameter, where the placement parameter is used to describe the number of information browsed by the user in the information flow object when the to-be-placed advertisement is first displayed, and the display interval of the to-be-placed advertisement.

[0038] Step 240, placing the to-be-placed advertisement according to the placement parameter and the target operation gesture.

[0039] In the embodiment of the present invention, by responding to the traffic request initiated by the client in the information flow object, reading the target operation gesture of the user corresponding to the client and the feedback parameter of the client for the advertisement, and determining the placement parameter negatively correlated with the feedback parameter. Among them, the feedback parameter is used to describe the positive feedback degree of the user for the advertisement, that is, the reception degree of the user for the advertisement. The larger the feedback parameter, the higher the acceptance degree of the user for the advertisement. The feedback parameter is negatively correlated with the placement parameter, and the placement parameter is used to describe the number of information browsed by the user in the information flow object when the to-be-placed advertisement is first displayed, and the display interval of the to-be-placed advertisement. Then, the larger the feedback parameter, the smaller the number of information browsed by the user in the information flow object when the to-be-placed advertisement is first displayed, and the smaller the display interval of the to-be-placed advertisement, that is, the to-be-placed advertisement appears earlier in the process of the user using the information flow object, and the appearance frequency can also be relatively high. Finally, placing the to-be-placed advertisement according to the placement parameter negatively correlated with the feedback parameter and the target operation gesture can combine the feedback situation of the user for the advertisement and the target operation gesture, and perform targeted advertising placement, making the advertising placement more flexible and personalized.

[0040] The following introduces the specific implementation manners of the above steps.

[0041] Regarding step 210.

[0042] Receive the traffic request initiated by the client in the information flow object. Specifically, it can be that the client receives the user's refresh operation, and in response to the refresh operation, initiates a traffic request to the backend server corresponding to the information flow object, and the backend server corresponding to the information flow object receives the traffic request initiated by the client in the information flow object.

[0043] It involves step 220.

[0044] In response to the traffic request, obtain the target operation gesture of the user corresponding to the client and the feedback parameter of the client on the advertisement.

[0045] Among them, specifically, it can be achieved by setting a buried point object in the information flow object, collecting buried point data using the buried point object, analyzing the buried point data, and determining the target operation gesture of the user and the feedback parameter of the client on the advertisement.

[0046] The buried point object can specifically be used to collect the operation behaviors of the user in the information flow object, such as the number of pull-down operations, the number of upward-sliding operations, clicks on different forms of advertisements, favorites, shares, and the residence duration of the advertisement in the information flow object, etc. Analyze and calculate these collected buried point data, so as to insert and place the advertisement in a personalized manner.

[0047] The client reports and delivers the buried point data collected by the buried point object. After the backend server corresponding to the information flow object receives these buried point data, it analyzes them to determine the target operation gesture of the user and the feedback parameter of the client on the advertisement.

[0048] In a possible embodiment, before step 220, the following steps may further be included:

[0049] Collect the operation data of the user on the advertisement in the information flow object, as well as the display duration of the advertisement;

[0050] Generate the feedback parameter of the user on the advertisement according to the operation data and the display duration.

[0051] When the user uses the information flow object, there will be interaction behaviors with the information flow object. The operation data of the user will be recorded and reported to the user log storage system. Various operation data of the user are recorded in the log, and these operation data are used to help with better content push.

[0052] Collect the operation data of the user on the advertisement in the information flow object, as well as the display duration of the advertisement; further statistically analyze the reported operation data and display duration of the user, and calculate the degree of preference of the user for the advertisement, that is, determine the feedback parameter of the user on the advertisement.

[0053] The magnitude of the feedback parameter indicates whether the user is interested in the advertisement. Further, the feedback parameter can correspond to the advertisement type respectively. Based on the feedback parameter, it can be determined which advertisement form the user prefers more (graphic or video) and which type of advertisement the user is more interested in (exposure, landing page, or app download).

[0054] Among them, the landing page refers to the web page that is displayed to the user after the user clicks on the advertisement or uses the search engine to search. Generally, this page will display extended content related to the clicked advertisement or search result link, and this page should be optimized for a certain keyword (or phrase) in the search engine.

[0055] Among them, the operation data includes: the number of inputs of the negative feedback identifier for the advertisement, the number of times the advertisement is collected, the number of times the advertisement is clicked, and the number of times the advertisement is shared. The above-mentioned generation of the feedback parameter of the user for the advertisement based on the operation data and the display duration specifically can include the following steps:

[0056] Determine the first feedback parameter according to the display duration of the advertisement;

[0057] Determine the second feedback parameter according to the operation data and the preset coefficient corresponding to each operation data respectively; the preset coefficient is related to the operation type of the operation data;

[0058] Perform a weighted calculation on the first feedback parameter and the second feedback parameter based on the preset weight to obtain the feedback parameter.

[0059] Before determining the second feedback parameter according to the operation data and the preset coefficient corresponding to each operation data respectively, different weights can be assigned to each behavior for different positive and negative classifications. For example, if the user collects, clicks, shares the advertisement or the advertisement stays in the information flow object for a long time (that is, exceeds the expected set time, such as the first threshold), it is classified as a positive operation. If the user clicks the negative feedback or is not interested or stays on the information flow object for a very short time, it is classified as a negative operation. If other user behavior indicators are added later, the weight values of each indicator can be adjusted and recalculated.

[0060] Among them, the preset coefficient is related to the operation type of the operation data. That is, when the operation data includes collection, click, sharing or the advertisement display time is greater than the first threshold, the operation type is determined as a positive operation type; when the operation data includes receiving the input of the negative feedback identifier or the advertisement display time is less than the second threshold, the operation type is determined as a negative operation type.

[0061] Specifically, the feedback parameter can be determined according to the following formula:

[0062] s = α * avgnorm(average ad dwell time) + β * norm((-2 * number of disliked ads + -1 * number of negatively - feedbacked ads + 1 * number of clicked ads + 2 * number of favorited ads + 3 * number of shared ads) / number of ads)

[0063] Among them, s is the feedback parameter, α and β are preset weights, "avgnorm(average ad dwell time)" is the first feedback parameter, "β * norm((-2 * number of disliked ads + -1 * number of negatively - feedbacked ads + 1 * number of clicked ads + 2 * number of favorited ads + 3 * number of shared ads) / number of ads)" is the second feedback parameter, and "-2, -1, 1, 2, and 3" are preset coefficients.

[0064] avgnorm means taking the average duration that the user stays on each ad after normalization, and norm means taking the result after normalization. Currently, the min - max method can be used for normalization. The sum of the weights of α and β is 1.0. Normalization is a way to simplify calculations, that is, to transform a dimensional expression into a dimensionless expression to become a scalar.

[0065] Thus, by determining the first feedback parameter according to the display duration of the ad; determining the second feedback parameter according to the operation data and the preset coefficients corresponding to each operation data respectively, since the preset coefficients are related to the operation types of the operation data, different positive and negative operations can be assigned different coefficients. Finally, by performing a weighted calculation on the first feedback parameter and the second feedback parameter based on the preset weights, an accurate feedback parameter that can reflect the user's preference for the ad can be obtained, and then it can be used to determine the delivery parameters in the future.

[0066] In a possible embodiment, before step 220, the following steps may further be included:

[0067] Collect the number of operation gestures of the user on the information flow object within a preset time period. The operation gestures include a first operation gesture along a first direction and a second operation gesture along a second direction, and the first direction is opposite to the second direction;

[0068] Determine the larger value between the number of the first operation gestures and the number of the second operation gestures;

[0069] Determine the operation gesture corresponding to the larger value as the target operation gesture.

[0070] Since different users have different operation habits in the information flow object, some users are used to pulling down, some are used to swiping up, some are used to swiping left, and some are used to swiping right. Among them, the pull - down operation gesture and the swipe - up operation gesture are the first operation gesture along the first direction and the second operation gesture along the second direction that correspond to each other; the same is true for swiping left and swiping right.

[0071] Here, by collecting the number of user operation gestures on information flow objects within a preset time period, the larger value of the number of first operation gestures and the number of second operation gestures is determined; the operation gesture corresponding to the larger value is determined as the target operation gesture, and the user's accustomed operation gesture can be determined as the target operation gesture, which is convenient for subsequent determination of the delivery method based on the user's accustomed operation gesture, thereby improving the delivery effect.

[0072] This involves step 230 .

[0073] The delivery parameters are used to describe the amount of information that a user browses in an information flow object when the advertisement to be delivered is displayed for the first time, and the display interval of the advertisement to be delivered.

[0074] The number of information browsed in the information flow object can be any type of information except advertisements. For example, the user browsed 9 pieces of information of any type except advertisements, and the 10th piece was an advertisement to be delivered. Therefore, when the advertisement to be delivered is displayed for the first time, the number of information browsed by the user in the information flow object is 9. The display interval of the advertisement to be delivered is used to represent the display interval between two advertisements to be delivered. The interval between the two advertisements to be delivered does not include other advertisements to be delivered. That is, every time there are a number of pieces of information of any type except advertisements, the advertisement to be delivered is displayed.

[0075] In a possible embodiment, step 230 may specifically include the following steps:

[0076] The feedback parameters of the client to the advertisement are input into the pre-trained delivery model to determine the delivery parameters.

[0077] In order to improve the computing efficiency, before the step of inputting the feedback parameters of the client to the advertisement into the pre-trained delivery model to determine the delivery parameters, the following steps may be further included:

[0078] Acquire multiple training samples, each training sample including a sample feedback parameter of a sample user to an advertisement, and a target delivery parameter that is negatively correlated with the sample feedback parameter;

[0079] Input the training samples into the preset model and output the predicted delivery parameters;

[0080] The preset model is trained according to the predicted delivery parameters and the target delivery parameters until the training stop condition is met to obtain the delivery model.

[0081] Here, a suitable supervised learning algorithm can be selected as the preset model, and the sample feedback parameters can be used as the training set for learning and training to obtain the optimal results of predicting the delivery parameters under different sample feedback parameters. The delivery model can control the delivery parameters in a personalized manner based on the feedback parameters.

[0082] Among them, the predicted placement parameters may include: the identification information of the page displayed for the first time and the position x in the page displayed for the first time, as well as the display interval y of the advertisement in the information flow object.

[0083] Taking the user's target operation gesture of swiping up as an example, if the value of the feedback parameter s is high, the position x is set to be small, and at the same time the advertisement density y is set to be small. If the value of the feedback parameter s is low, the first position x can be set to be large, and at the same time the display interval y is set to be large; taking the user's target operation gesture of swiping down as an example, combined with the value of s, calculate the number of times x that the user refreshes and the advertisement appears for the first time and the number of times y that the user refreshes and the next advertisement appears, and continuously adjust according to the user's behavior.

[0084] Among them, the sample feedback parameter of the user can be determined according to the collected sample operation data of the user, and the target placement parameter corresponding to the sample feedback parameter is manually marked.

[0085] The sample operation data may include: the number of times of input of the negative feedback identifier for the advertisement, the number of times of collection of the advertisement, the number of times of click on the advertisement, and the number of times of sharing of the advertisement.

[0086] Among them, in the step of training the preset model according to the predicted placement parameter and the target placement parameter until the training stop condition is satisfied to obtain the placement model, it may specifically include the following steps:

[0087] Determine the loss value according to the predicted placement parameter and the target placement parameter;

[0088] Train the preset model according to the loss value until the loss value is less than the preset threshold to obtain the placement model.

[0089] Finally, it involves step 240.

[0090] In a possible embodiment, there are multiple advertisements to be placed. Step 240 includes:

[0091] In the case where the target operation gesture is the first operation gesture, the placement parameters include: the first display position of the advertisement to be placed in the information flow object and the display interval of the advertisement to be placed. The first display position includes the identification information of the page displayed for the first time and the position in the page displayed for the first time; the display interval is used to characterize the display interval of the advertisement to be placed in the information flow object; place the advertisement to be placed according to the first display position and the display interval; or,

[0092] In the case where the target operation gesture is the second operation gesture, the placement parameters include: the first refresh times and the second refresh times, which are used to display the advertisement to be placed for the first time when it is detected that the user refreshes the first refresh times, and which are used to display the advertisement to be placed when it is detected that the user refreshes the second refresh times each time; place the advertisement to be placed according to the first refresh times and the second refresh times.

[0093] Among them, multiple groups of sample feedback parameters and target placement parameters collected can be used for fitting to obtain a feedback curve, where two variables in the feedback curve are negatively correlated; in the feedback curve, the placement parameter corresponding to the feedback parameter is found.

[0094] Specifically, when the target operation gesture is the first operation gesture, the placement parameters include: the first display position of the advertisement to be placed in the information flow object, and the first display position includes the identification information of the page where the first display occurs and the position on the page where the first display occurs.

[0095] For example, as Figure 3 shown, the advertisement to be placed first appears at the first display position on the third page, that is, the identification information is the third page, and the position on the page where the first display occurs is the first display position; and the display interval of the advertisement in the information flow object, such as displaying an advertisement to be placed every five information flow contents; according to the first display position and the display interval, the advertisement to be placed is placed.

[0096] When the target operation gesture is the second operation gesture, the placement parameters include: the first refresh count and the second refresh count. For example, as Figure 4 shown, the advertisement to be placed first appears after pulling down and refreshing five times, that is, the first refresh count is 5 times, and the second refresh count can be 3 times. That is, when it is detected that the user has refreshed 5 times, the advertisement to be placed is first displayed, and when it is detected that the user refreshes 3 times each time, the advertisement to be placed is displayed.

[0097] Among them, in the step of placing the advertisement to be placed according to the first refresh count and the second refresh count as described above, it specifically may include:

[0098] When it is detected that the client has completed the refresh operation of the first refresh count, the advertisement to be placed is first displayed;

[0099] After the advertisement to be placed is first displayed, whenever it is detected that the client has completed the refresh operation of the second refresh count, the advertisement to be placed is displayed.

[0100] Among them, when the target operation gesture is the first operation gesture, the first display position of the advertisement to be placed in the information flow object is negatively correlated with the feedback parameter, and the display interval of the advertisement to be placed is negatively correlated with the feedback parameter;

[0101] When the target operation gesture is the second operation gesture, the first refresh count is negatively correlated with the feedback parameter, and the second refresh count is negatively correlated with the feedback parameter.

[0102] When the target operation gesture is the first operation gesture, that is, the target operation gesture of the user can be a swiping-up operation gesture. The first display position of the to-be-delivered advertisement in the information flow object is negatively correlated with the feedback parameter, indicating that if the value of the feedback parameter is high, the first display position of the to-be-delivered advertisement in the information flow object is set to be small; if the value of the feedback parameter is low, the first display position of the to-be-delivered advertisement in the information flow object is set to be large. At the same time, the display interval of the to-be-delivered advertisement is negatively correlated with the feedback parameter, indicating that if the value of the feedback parameter is high, the display interval of the to-be-delivered advertisement is set to be small; if the value of the feedback parameter is low, the display interval of the to-be-delivered advertisement is set to be large.

[0103] When the target operation gesture is the second operation gesture, that is, the target operation gesture of the user can be a swiping-down operation gesture. The first refresh times is negatively correlated with the feedback parameter, and the second refresh times is negatively correlated with the feedback parameter. It indicates that if the value of the feedback parameter is high, the first refresh times is set to be small and the second refresh times is small. Vice versa.

[0104] In another possible embodiment, step 240 includes:

[0105] Determine the delivery quantity of the to-be-delivered advertisement according to the delivery parameter;

[0106] Send the to-be-delivered advertisement with the delivery parameter and the delivery quantity to the client, so that the client can display the to-be-delivered advertisement according to the delivery parameter.

[0107] Specifically, the advertisement delivery quantity and the to-be-delivered advertisement with the delivery quantity can be calculated according to the delivery parameter; for one traffic request, the first quantity of the to-be-displayed content can be obtained, and the integer obtained by dividing the first quantity by the display interval is the delivery quantity.

[0108] Send the to-be-delivered advertisement with the delivery parameter and the delivery quantity to the client for the client to display the to-be-delivered advertisement according to the delivery parameter and perform the display of the advertisement position. For example, if the display interval is 5 and there are 16 pieces of content to be displayed in the information flow object, the delivery quantity is the result of taking the integer after dividing 16 by 5, that is, the delivery quantity is 3.

[0109] In summary, in the embodiments of the present invention, in response to a traffic request initiated by a client in an information flow object, the target operation gesture of the user corresponding to the client and the feedback parameter of the client for an advertisement are read, and a placement parameter negatively correlated with the feedback parameter is determined. The feedback parameter is used to describe the positive feedback degree of the user for the advertisement, that is, the reception degree of the user for the advertisement. The larger the feedback parameter, the higher the acceptance degree of the user for the advertisement. The feedback parameter is negatively correlated with the placement parameter, and the placement parameter is used to describe the number of information items browsed by the user in the information flow object when the to-be-placed advertisement is first displayed, and the display interval of the to-be-placed advertisement. Then, the larger the feedback parameter, the smaller the number of information items browsed by the user in the information flow object when the to-be-placed advertisement is first displayed, and the smaller the display interval of the to-be-placed advertisement, that is, the to-be-placed advertisement appears earlier in the process of the user using the information flow object, and the appearance frequency can also be relatively high. Finally, according to the placement parameter negatively correlated with the feedback parameter and the target operation gesture, the to-be-placed advertisement is placed, which can combine the user's feedback on the advertisement and the target operation gesture, and perform targeted advertisement placement, making the advertisement placement more flexible and personalized.

[0110] Based on the above Figure 2 advertising placement method shown, the embodiments of the present invention further provide an advertising placement device, as Figure 5 shown, the advertising placement device 500 may include:

[0111] A receiving module 510, configured to receive a traffic request initiated by a client in an information flow object.

[0112] A reading module 520, configured to read the target operation gesture of the user corresponding to the client and the feedback parameter of the client for the advertisement in response to the traffic request; the feedback parameter is used to describe the positive feedback degree of the user for the advertisement.

[0113] A determining module 530, configured to determine a placement parameter negatively correlated with the feedback parameter, where the placement parameter is used to describe the number of information items browsed by the user in the information flow object when the to-be-placed advertisement is first displayed, and the display interval of the to-be-placed advertisement.

[0114] A placement module 540, configured to place the to-be-placed advertisement according to the placement parameter and the target operation gesture.

[0115] In a possible embodiment of the reading module, the advertising placement device 500 may further include:

[0116] A first acquisition module, configured to acquire the operation data of the user for the advertisement in the information flow object, and the display duration of the advertisement.

[0117] A generation module, configured to generate a feedback parameter of the user for the advertisement according to the operation data and the display duration.

[0118] In a possible embodiment, the operation data includes: the number of times of input of the negative feedback identifier for the advertisement, the number of times of collection of the advertisement, the number of times of click on the advertisement, and the number of times of sharing of the advertisement. The generation module is specifically configured to: determine a first feedback parameter according to the display duration of the advertisement;

[0119] determine a second feedback parameter according to the operation data and the preset coefficient corresponding to each operation data respectively; the preset coefficient is related to the operation type of the operation data;

[0120] perform weighted calculation on the first feedback parameter and the second feedback parameter based on the preset weight to obtain the feedback parameter.

[0121] In a possible embodiment, the advertisement delivery device 500 may further include:

[0122] A second acquisition module, configured to acquire the number of operation gestures of the user on the information flow object within a preset time period. The operation gestures include a first operation gesture along a first direction and a second operation gesture along a second direction, and the first direction is opposite to the second direction.

[0123] The determination module 530 is further configured to determine the larger value between the number of first operation gestures and the number of second operation gestures.

[0124] The determination module 530 is further configured to determine the operation gesture corresponding to the larger value as the target operation gesture.

[0125] In a possible embodiment, there are multiple advertisements to be delivered. When the operation gesture is the first operation gesture, the delivery parameters include: the first display position of the advertisement to be delivered in the information flow object and the display interval of the advertisement to be delivered. The first display position includes the identification information of the page where the advertisement is first displayed and the position in the page where the advertisement is first displayed; the display interval is used to characterize the display interval of the advertisement to be delivered in the information flow object. The delivery module 540 is specifically configured to: deliver the advertisement to be delivered according to the first display position and the display interval. Or,

[0126] When the operation gesture is the second operation gesture, the delivery parameters include: the first refresh times and the second refresh times, which are used to first display the advertisement to be delivered when it is detected that the user refreshes the first refresh times, and which are used to display the advertisement to be delivered when it is detected that the user refreshes the second refresh times each time; the delivery module 540 is specifically configured to: deliver the advertisement to be delivered according to the first refresh times and the second refresh times.

[0127] In a possible embodiment, when the operation gesture is the first operation gesture, the first display position of the to-be-delivered advertisement in the information flow object is negatively correlated with the feedback parameter, and the display interval of the to-be-delivered advertisement is negatively correlated with the feedback parameter; when the operation gesture is the second operation gesture, the first refresh count is negatively correlated with the feedback parameter, and the second refresh count is negatively correlated with the feedback parameter.

[0128] In a possible embodiment, the determining module 530 is specifically configured to:

[0129] Input the feedback parameter of the advertisement by the client into a pre-trained delivery model to determine the delivery parameter.

[0130] In a possible embodiment, the advertisement delivery device 500 may further include:

[0131] An obtaining module, configured to obtain a plurality of training samples, each training sample including a sample feedback parameter of the advertisement by a sample user and a target delivery parameter negatively correlated with the sample feedback parameter.

[0132] An input module, configured to input the training samples into a preset model and output a predicted delivery parameter.

[0133] A training module, configured to train the preset model according to the predicted delivery parameter and the target delivery parameter until a training stop condition is met, to obtain a delivery model.

[0134] In summary, in the embodiments of the present invention, by responding to a traffic request initiated by the client in the information flow object, reading the target operation gesture of the user corresponding to the client and the feedback parameter of the advertisement by the client, the delivery parameter negatively correlated with the feedback parameter is determined. Among them, the feedback parameter is used to describe the positive feedback degree of the user on the advertisement, that is, the reception degree of the user for the advertisement. The larger the feedback parameter, the higher the acceptance degree of the user for the advertisement. The feedback parameter is negatively correlated with the delivery parameter, and the delivery parameter is used to describe the number of information browsed by the user in the information flow object when the to-be-delivered advertisement is first displayed, and the display interval of the to-be-delivered advertisement. Then, the larger the feedback parameter, the smaller the number of information browsed by the user in the information flow object when the to-be-delivered advertisement is first displayed, and the smaller the display interval of the to-be-delivered advertisement, that is, the to-be-delivered advertisement appears earlier in the process of the user using the information flow object, and the appearance frequency can also be relatively high. Finally, according to the delivery parameter negatively correlated with the feedback parameter and the target operation gesture, the to-be-delivered advertisement is delivered, which can combine the feedback situation of the user on the advertisement and the target operation gesture, and perform targeted advertisement delivery, making the advertisement delivery more flexible and personalized.

[0135] The embodiments of the present invention further provide an electronic device, such as Figure 6As shown in the figure, it includes a processor 601, a communication interface 602, a memory 603, and a communication bus 604. Among them, the processor 601, the communication interface 602, and the memory 603 complete their mutual communication through the communication bus 604.

[0136] The memory 603 is used to store computer programs.

[0137] When the processor 601 is used to execute the program stored in the memory 603, the following steps are implemented:

[0138] Receive the traffic request initiated by the client in the information flow object.

[0139] In response to the traffic request, read the target operation gesture of the user corresponding to the client and the feedback parameter of the client for the advertisement; the feedback parameter is used to describe the positive feedback degree of the user for the advertisement.

[0140] Determine the placement parameter that is negatively correlated with the feedback parameter. The placement parameter is used to describe the number of information browsed by the user in the information flow object when the to-be-placed advertisement is first displayed, and the display interval of the to-be-placed advertisement.

[0141] Place the to-be-placed advertisement according to the placement parameter and the target operation gesture.

[0142] The communication bus mentioned in the above terminal can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, only a thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0143] The communication interface is used for the communication between the above terminal and other devices.

[0144] The memory can include a Random Access Memory (RAM), and can also include a non-volatile memory, such as at least one disk memory. Optionally, the memory can also be at least one storage device located far from the aforementioned processor.

[0145] The above-mentioned processor may be a general-purpose processor, including a Central Processing Unit (CPU for short), a Network Processor (NP for short), etc.; it may also be a Digital Signal Processor (DSP for short), an Application Specific Integrated Circuit (ASIC for short), a Field-Programmable Gate Array (FPGA for short), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0146] In another embodiment provided by the present invention, there is also provided a computer-readable storage medium, in which instructions are stored. When it runs on a computer, it causes the computer to execute the advertisement placement method described in any one of the above embodiments.

[0147] In another embodiment provided by the present invention, there is also provided a computer program product containing instructions. When it runs on a computer, it causes the computer to execute the advertisement placement method described in any one of the above embodiments.

[0148] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present invention are generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wire (such as coaxial cable, optical fiber, Digital Subscriber Line (DSL)) or wirelessly (such as infrared, wireless, microwave, etc.). The computer-readable storage medium may be any available medium that the computer can access, or a data storage device such as a server or data center that includes one or more integrated available media. The available medium may be a magnetic medium (such as a floppy disk, hard disk, magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a Solid State Disk (SSD)).

[0149] It should be noted that in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprising", "including" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. Without more limitations, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the said element.

[0150] Each embodiment in this specification is described in a related manner. For the same or similar parts among the embodiments, reference can be made to each other, and the differences between each embodiment and other embodiments are emphasized. In particular, for system embodiments, since they are basically similar to method embodiments, the description is relatively simple, and reference can be made to the corresponding parts of the method embodiments for the relevant content.

[0151] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention are included within the protection scope of the present invention.

Claims

1. An advertising placement method, characterized in that, The method includes: Receiving a traffic request initiated by a client in an information flow object; In response to the traffic request, reading a target operation gesture of the user corresponding to the client and a feedback parameter of the client for an advertisement; the feedback parameter is used to describe the positive feedback degree of the user for the advertisement, and the target operation gesture is determined from a first operation gesture and a second operation gesture; Determining a delivery parameter negatively correlated with the feedback parameter, the delivery parameter being used to describe the number of pieces of information browsed by the user in the information flow object when the to-be-delivered advertisement is first displayed, and the display interval of the to-be-delivered advertisement, and the number of pieces of information browsed in the information flow object represents the number of pieces of information of any type other than advertisements; Delivering the to-be-delivered advertisement according to the delivery parameter and the target operation gesture; Wherein, when the target operation gesture is the first operation gesture, the delivery parameter includes: the first display position of the to-be-delivered advertisement in the information flow object and the display interval of the to-be-delivered advertisement; When the target operation gesture is the second operation gesture, the delivery parameter includes: a first refresh number and a second refresh number, which are used to first display the to-be-delivered advertisement when it is detected that the user refreshes the first refresh number, and are used to display the to-be-delivered advertisement when it is detected that the user refreshes the second refresh number each time.

2. The method according to claim 1, before the step of, in response to the traffic request, reading the target operation gesture of the user corresponding to the client and the feedback parameter of the client for the advertisement, the method further includes: Collecting operation data of the user for the advertisement in the information flow object and the display duration of the advertisement; Generating the feedback parameter of the user for the advertisement according to the operation data and the display duration.

3. The method according to claim 2, wherein the operation data includes: The number of input times of the negative feedback flag for the advertisement, the number of times of collecting the advertisement, the number of times of clicking on the advertisement, and the number of times of sharing the advertisement, the generating the feedback parameter of the user for the advertisement according to the operation data and the display duration includes: Determining a first feedback parameter according to the display duration of the advertisement; Determining a second feedback parameter according to the operation data and a preset coefficient corresponding to each piece of operation data respectively; the preset coefficient is related to the operation type of the operation data; Performing weighted calculation on the first feedback parameter and the second feedback parameter based on a preset weight to obtain the feedback parameter.

4. The method according to claim 1, before the step of, in response to the traffic request, reading the target operation gesture of the user corresponding to the client and the feedback parameter of the client for the advertisement, the method further includes: Collecting the number of operation gestures of the user for the information flow object within a preset time period, the operation gestures including a first operation gesture along a first direction and a second operation gesture along a second direction, and the first direction is opposite to the second direction; Determining the larger value between the number of the first operation gestures and the number of the second operation gestures; Determine the operation gesture corresponding to the larger value as the target operation gesture.

5. The method according to claim 4, wherein there are multiple advertisements to be delivered, and the delivering the advertisements to be delivered according to the delivery parameter and the target operation gesture includes: When the target operation gesture is the first operation gesture, the delivery parameter includes: the first display position of the advertisement to be delivered in the information flow object and the display interval of the advertisement to be delivered, where the first display position includes the identification information of the page where the advertisement is first displayed and the position in the page where the advertisement is first displayed; the display interval is used to characterize the display interval of the advertisement to be delivered in the information flow object; deliver the advertisement to be delivered according to the first display position and the display interval; or, When the target operation gesture is the second operation gesture, deliver the advertisement to be delivered according to the first refresh count and the second refresh count.

6. The method according to claim 1, wherein the determining the delivery parameter negatively correlated with the feedback parameter includes: Input the feedback parameter of the client for the advertisement into a pre-trained delivery model to determine the delivery parameter.

7. The method according to claim 6, before the inputting the feedback parameter of the client for the advertisement into a pre-trained delivery model to determine the delivery parameter, the method further includes: Obtain a plurality of training samples, each training sample including a sample feedback parameter of a sample user for an advertisement and a target delivery parameter negatively correlated with the sample feedback parameter; Input the training samples into a preset model to output a predicted delivery parameter; Train the preset model according to the predicted delivery parameter and the target delivery parameter until a training stop condition is met to obtain the delivery model.

8. An advertisement delivery device, characterized in that, The device includes: A receiving module, configured to receive a traffic request initiated by a client in an information flow object; A reading module, configured to, in response to the traffic request, read the target operation gesture of the user corresponding to the client and the feedback parameter of the client for the advertisement; the feedback parameter is used to describe the positive feedback degree of the user for the advertisement, and the target operation gesture is determined from a first operation gesture and a second operation gesture; A determining module, configured to determine a delivery parameter negatively correlated with the feedback parameter, where the delivery parameter is used to describe the number of pieces of information browsed by the user in the information flow object when the advertisement to be delivered is first displayed and the display interval of the advertisement to be delivered, and the number of pieces of information browsed in the information flow object represents the number of pieces of information of any type other than advertisements; A delivery module, configured to deliver the advertisement to be delivered according to the delivery parameter and the target operation gesture; Wherein, when the target operation gesture is the first operation gesture, the delivery parameter includes: the first display position of the advertisement to be delivered in the information flow object and the display interval of the advertisement to be delivered; When the target operation gesture is the second operation gesture, the placement parameters include: a first refresh count and a second refresh count, which are used to display the to-be-placed advertisement for the first time when it is detected that the user refreshes the first refresh count, and are used to display the to-be-placed advertisement when it is detected that the user refreshes the second refresh count each time.

9. An electronic device, characterized in that, It includes a processor, a communication interface, a memory, and a communication bus. Among them, the processor, the communication interface, and the memory complete mutual communication through the communication bus; The memory is used to store computer programs; The processor is used to implement the method steps described in any one of claims 1-7 when executing the program stored on the memory.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method described in any one of claims 1-7.

Images