Information delivery control method and device, electronic equipment and storage medium

Abstract

The invention relates to the technical field of computers, in particular to an information release control method and device, electronic equipment and a storage medium, which are used for improving the exposure of information and improving the resource utilization rate of information release. The method comprises the steps of receiving an information delivery request containing object attribute information of a to-be-delivered object and a target delivery time period, affiliating the to-be-delivered object to a target object set in a plurality of candidate object sets based on the object attribute information, and sending the to-be-delivered object to a plurality of candidate object sets based on the position of the target delivery time period in an affiliated information delivery period. Obtaining a target competition rate of the target object set according to historical competition rates of the plurality of candidate object sets and historical competition rates of the plurality of candidate object sets in a previous delivery time period of the target delivery time period; and obtaining a putting strategy of the target putting information based on the target competition rate. According to the method and the device, the information release for the to-be-released object is controlled based on the release time period and the historical competition rate of each candidate object set, so that the exposure can be improved, and the release resource utilization rate can be improved.

Description

Background Art

[0002] The development of new media technology has provided a large number of online exposure opportunities for various products. In order to increase revenue, more and more businesses choose to place multimedia information online for publicity. Due to the large amount of new media traffic and the limited budget of businesses, it is difficult to support participation in all exposure competitions. Therefore, in the process of multimedia information delivery, the participation rate is often set to control the consumption of the budget.

[0003] In the related art, when receiving a delivery request, the information delivery system will decide whether to participate in the exposure competition based on the competition rate preset by the business party.

[0004] However, in actual applications, the quality of traffic in different time periods varies greatly. Presetting a unified competition rate for traffic in all time periods will result in that in some time periods, even if the business party participates in the exposure competition and obtains exposure opportunities, it will not be able to achieve effective conversion of multimedia information into products, and will reduce the utilization rate of resources consumed by the business party in delivering multimedia information.

[0005] On the other hand, in some other time periods, the business party may not be able to obtain exposure opportunities smoothly due to the restriction of competition rate, resulting in low exposure of multimedia information, and then it is difficult for multimedia information to reach high-quality delivery targets, and it is also impossible to achieve effective conversion of multimedia information into products, so that the business party cannot obtain excellent conversion effects and the utilization rate of delivery resources is low. Summary of the invention

[0006] The embodiments of the present application provide an information delivery control method, device, electronic device and storage medium to increase the exposure of information and improve the resource utilization of information delivery.

[0007] An information delivery control method provided in an embodiment of the present application includes:

[0008] Receiving an information delivery request sent for target delivery information, the information delivery request including: object attribute information of the object to be delivered and a target delivery time period;

[0009] Based on the object attribute information, the to-be-delivered object is assigned to a target object set in a plurality of candidate object sets;

[0010] Based on the position of the target delivery time period in the information delivery cycle, and the historical competition rates of the plurality of candidate object sets in the previous delivery time period of the target delivery time period, a target competition rate of the target object set in the target delivery time period is obtained;

[0011] Based on the target competition participation rate, a delivery strategy for the target delivery information is obtained.

[0012] An information delivery control device provided in an embodiment of the present application includes:

[0013] A receiving unit, configured to receive an information delivery request sent for target delivery information, wherein the information delivery request includes: object attribute information of the object to be delivered and a target delivery time period;

[0014] an attribution unit, configured to attribute the to-be-delivered object to a target object set in a plurality of candidate object sets based on the object attribute information;

[0015] A processing unit, configured to obtain a target competition rate of the target object set in the target delivery time period based on the position of the target delivery time period in the information delivery cycle and the historical competition rates of each of the plurality of candidate object sets in a delivery time period before the target delivery time period;

[0016] A strategy unit is used to obtain a delivery strategy of the target delivery information based on the target competition participation rate.

[0017] Optionally, the processing unit is specifically used for:

[0018] When the target delivery time period is the first delivery time period in the information delivery cycle, the preset competition participation rate is used as the target competition participation rate;

[0019] When the target delivery time period is not the first delivery time period within the information delivery cycle, the target competition rate is obtained based on at least one reference resource consumption of the target delivery time period and various historical competition rates, wherein the reference resource consumption is: the resource consumption of the historical delivery time period within the information delivery cycle and located before the target delivery time period.

[0020] Optionally, the processing unit is specifically used for:

[0021] Obtaining an estimated resource input amount for the target delivery time period based on the at least one reference resource consumption, the planned resource input amount for each historical delivery time period, and the planned resource input amount for the target delivery time period;

[0022] Based on the resource difference between the expected resource input and the historical resource consumption in the previous historical delivery time period, the historical competition rates are adjusted in sequence according to a preset order to obtain the target competition rates of the multiple candidate object sets, wherein the preset order is determined based on the predicted feedback status of each of the multiple candidate object sets.

[0023] Optionally, the processing unit is specifically used for:

[0024] For a candidate object set, based on the current resource difference and the object resource consumption of the candidate object set in the previous delivery time period, the historical competition rate of the candidate object set is adjusted to obtain a corresponding target competition rate;

[0025] The current resource difference is determined based on the position of the candidate object set in the preset order.

[0026] Optionally, if the resource difference is greater than a preset threshold, the preset order is: the order of corresponding prediction feedback states from high to low;

[0027] If the resource difference is not greater than the preset threshold, the preset order is: the order of corresponding prediction feedback states from low to high.

[0028] Optionally, the processing unit is specifically configured to determine the current resource difference in the following manner:

[0029] When the location meets the preset location condition, the resource difference value determined based on the estimated resource input amount and the historical resource consumption amount is used as the current resource difference value;

[0030] When the position does not meet the preset position condition, adjusting the current resource difference corresponding to the intermediate object set based on the target competition rate, reference competition rate and object resource consumption of the intermediate object set to obtain the current resource difference;

[0031] Wherein, in the preset order, the position of the intermediate object set is before and adjacent to the position of one candidate object set.

[0032] Optionally, the objects belonging to the same candidate object set have the same predicted feedback status for the target delivery information.

[0033] Optionally, the predicted feedback state includes a predicted interest level and a predicted resource transfer amount; and the attribution unit is specifically configured to:

[0034] Based on the object attribute information, obtaining the predicted interest level and predicted resource transfer amount of the object to be delivered;

[0035] Based on the predicted interest level and the predicted resource transfer amount, the to-be-delivered object is assigned to a target object set in the plurality of candidate object sets.

[0036] Optionally, the device further includes an acquisition unit, configured to obtain the plurality of candidate object sets in the following manner:

[0037] Obtain multiple historical delivery objects of the target delivery information and their respective predicted feedback states;

[0038] Based on each prediction feedback state, a set boundary value of each of the plurality of candidate object sets is obtained.

[0039] An electronic device provided in an embodiment of the present application includes a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of any one of the above-mentioned information delivery control methods.

[0040] An embodiment of the present application provides a computer-readable storage medium, which includes a computer program. When the computer program is run on an electronic device, the computer program is used to enable the electronic device to execute the steps of any one of the above-mentioned information delivery control methods.

[0041] An embodiment of the present application provides a computer program product, which includes a computer program, and the computer program is stored in a computer-readable storage medium; when a processor of an electronic device reads the computer program from the computer-readable storage medium, the processor executes the computer program, so that the electronic device performs the steps of any one of the above-mentioned information delivery control methods.

[0042] The beneficial effects of this application are as follows:

[0043] The embodiments of the present application provide an information delivery control method, device, electronic device and storage medium. When controlling the delivery of target delivery information, first, based on object attribute information, the object to be delivered is assigned to a target object set in a plurality of candidate object sets, so that different delivery strategies can be set for different objects.

[0044] Then, the target competition rate of the target object set is obtained by combining the delivery time period and the historical competition rates of multiple candidate object sets, so that different competition rates can be set for different delivery times. In the same delivery time period, different competition rates can also be set for different object sets, fully considering the impact of delivery time and delivery objects on the information delivery effect.

[0045] Finally, the delivery strategy for the target objects is determined based on the target competition rate. Controlling information delivery based on the above method can ensure that the delivery information is accurately delivered to high-quality delivery objects while controlling the consumption of delivery resources, thereby improving the conversion rate of delivery information and further improving the utilization rate of delivery resources. The saved resources can be used to compete for more exposure opportunities, increase exposure, and further improve conversion effects.

[0046] Other features and advantages of the present application will be described in the following description, and partly become apparent from the description, or be understood by practicing the present application. The purpose and other advantages of the present application can be realized and obtained by the structures specifically pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0048] Figure 1A A schematic diagram of a method for controlling a competition rate in the related art;

[0049] Figure 1B An optional schematic diagram of an application scenario in an embodiment of the present application;

[0050] Figure 2 This is a flowchart of an implementation method of an information delivery control method in an embodiment of the present application;

[0051] Figure 3 A schematic diagram of a flow quality classification method in the related art;

[0052] Figure 4 A schematic diagram of a flow quality distribution in an embodiment of the present application;

[0053] Figure 5 A schematic diagram of a method for dividing a candidate object set in an embodiment of the present application;

[0054] Figure 6 A schematic diagram of a layered flow control method in an embodiment of the present application;

[0055] Figure 7 A schematic diagram of a flow fluctuation situation in an embodiment of the present application;

[0056] Figure 8 A schematic diagram of user stratification in an embodiment of the present application;

[0057] Fig. 9 A schematic diagram of a resource difference reallocation method in an embodiment of the present application;

[0058] Fig.10 This is an interface diagram of an information delivery system in an embodiment of the present application;

[0059] Fig.11 This is a schematic diagram of the operation flow of an information delivery system in an embodiment of the present application;

[0060] Fig.12 A logical diagram of the information delivery control method in an embodiment of the present application;

[0061] Fig.13 A schematic diagram of the structure of an information delivery control device in an embodiment of the present application;

[0062] Fig.14 A schematic diagram of a hardware structure of an electronic device to which an embodiment of the present application is applied;

[0063] Fig.15 The present invention is a schematic diagram of the hardware structure of another electronic device to which the embodiments of the present application are applied. DETAILED DESCRIPTION

[0064] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the technical solution of the present application, rather than all of the embodiments. Based on the embodiments recorded in the application documents, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the technical solution of the present application.

[0065] The following is an introduction to some concepts involved in the embodiments of the present application.

[0066] Delivery information: refers to information that is displayed to the target audience to achieve promotional effects for the corresponding products, such as advertisements, news, posters, music and other multimedia information.

[0067] Predicted feedback status: refers to the predicted feedback status of the target delivery object to the target delivery information, which may include the predicted click-through rate (CTR), conversion rate (CVR), click-througn & conversion rate (CTCVR), and user life cycle value (LTV) of the target delivery object to the target delivery information. Through the above information, it is possible to fully measure the benefits brought by the target delivery object to the product corresponding to the target delivery information, and then decide whether to deliver information to the target delivery object based on the predicted feedback status.

[0068] Competition rate: refers to the probability of a business party participating in the competition for exposure opportunities. Since the business party has a limited budget for information delivery, it hopes that the budget can be consumed smoothly throughout the day (Smooth delivery) and the life cycle of the plan is long enough to reach users at different times. The speed of budget consumption can be influenced by adjusting the competition rate. For example, faster consumption reduces the probability, while slower consumption increases the probability. Correctly setting the competition rate can enable the business party to obtain more exposure opportunities and achieve higher profits.

[0069] Reference resource consumption: refers to the resources actually consumed in the delivery of information within a certain delivery time period. For example, if the current time is 15 o'clock, the resources consumed by the delivery of information between 10 o'clock and 12 o'clock can be counted. The reference resource consumption can be used to timely adjust the resource input for subsequent delivery of information to obtain more exposure opportunities.

[0070] Planned resource investment: refers to the amount of resources planned to be invested in information delivery during a certain delivery period. For example, the planned resource investment from 1:00 to 2:00 can be set to 500, and the planned resource investment from 7:00 to 8:00 can be set to 5000.

[0071] The following is a brief introduction to the design concept of this application:

[0072] The development of new media technology has provided a large number of online exposure opportunities for various products. In order to increase revenue, more and more businesses choose to place multimedia information online for publicity. Due to the large amount of new media traffic and the limited budget of businesses, it is difficult to support participation in all exposure competitions. Therefore, in the process of multimedia information delivery, the participation rate is often set to control the consumption of the budget.

[0073] In the related art, when receiving a delivery request, the information delivery system will decide whether to participate in the current exposure competition based on the competition rate preset by the business party. Figure 1A As shown, when a delivery request is received, the global flow controller sets the global competition rate to decide whether to participate in the competition.

[0074] However, in actual applications, the quality of traffic in different time periods varies greatly. Presetting a unified competition rate for traffic in all time periods will result in that in some time periods, even if the business party participates in the exposure competition and obtains exposure opportunities, it will not be able to achieve effective conversion of multimedia information into products, and will reduce the utilization rate of resources consumed by the business party in delivering multimedia information.

[0075] On the other hand, in some other time periods, the business party may not be able to obtain exposure opportunities smoothly due to the restriction of competition rate, resulting in low exposure of multimedia information, and then it is difficult for multimedia information to reach high-quality delivery targets, and it is also impossible to achieve effective conversion of multimedia information into products, so that the business party cannot obtain excellent conversion effects and the utilization rate of delivery resources is low.

[0076] In view of this, the embodiments of the present application provide an information delivery control method, device, electronic device and storage medium. When controlling the delivery of target delivery information, first, based on object attribute information, the object to be delivered is assigned to a target object set in a plurality of candidate object sets, so that different delivery strategies can be set for different objects. Then, the target competition rate of the target object set is obtained by combining the delivery time period and the historical competition rates of the plurality of candidate object sets, so that different competition rates can be set for different delivery times. In the same delivery time period, different object sets can also be set with different competition rates, and the impact of the delivery time and delivery object on the information delivery effect is fully considered. Finally, the delivery strategy for the object to be delivered is determined based on the target competition rate. Controlling information delivery based on the above method can ensure that the delivery information is accurately delivered to high-quality delivery objects while controlling the delivery resource consumption, thereby improving the conversion rate of the delivery information, and further improving the utilization rate of the delivery resources. The saved resources can be used to compete for more exposure opportunities, increase the exposure, and further improve the conversion effect.

[0077] The preferred embodiments of the present application are described below in conjunction with the drawings in the specification. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present application, and are not used to limit the present application. In addition, the embodiments and features in the embodiments of the present application may be combined with each other if there is no conflict.

[0078] like Figure 1B As shown, it is a schematic diagram of an application scenario of an embodiment of the present application. The application scenario diagram includes two terminal devices 110 and a server 120.

[0079] In the embodiments of the present application, the terminal device includes but is not limited to mobile phones, tablet computers, laptop computers, desktop computers, e-book readers, intelligent voice interaction devices, smart home appliances, vehicle-mounted terminals and other devices; the terminal device may be installed with a client related to information delivery control, which may be software (such as a browser, information delivery software, etc.), or a web page, a small program, etc. The server is a background server corresponding to the software or web page, small program, etc., or a server specifically used for information delivery, which is not specifically limited in the present application. The server may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms.

[0080] It should be noted that the information delivery control method in the embodiment of the present application can be executed by an electronic device, and the electronic device can be a server or a terminal device, that is, the method can be executed by a server or a terminal device alone, or by a server and a terminal device together. For example, when executed by a server and a terminal device together, when the object to be delivered logs in to the client, the client sends an information delivery request, and the server attributes the object to be delivered to a target object set in a plurality of candidate object sets based on the user's object attribute information, and obtains the target competition rate of the target object set in the target delivery time period based on the position of the target delivery time period in the attributed information delivery cycle, and the respective historical competition rates of the plurality of candidate object sets in the previous delivery time period of the target delivery time period; based on the target competition rate, obtain the delivery strategy of the target delivery information.

[0081] In an optional implementation, the terminal device and the server may communicate via a communication network.

[0082] In an optional implementation, the communication network is a wired network or a wireless network.

[0083] It should be noted that Figure 1B The figure is only an example. In fact, the number of terminal devices and servers is not limited and is not specifically limited in the embodiments of the present application.

[0084] In the embodiment of the present application, when there are multiple servers, the multiple servers can form a blockchain, and the servers are nodes on the blockchain; such as the information delivery control method disclosed in the embodiment of the present application, the delivery information and historical delivery data involved therein can be saved on the blockchain, etc.

[0085] In addition, the embodiments of the present application can be applied to various scenarios, including not only information delivery control scenarios, but also including but not limited to cloud technology, artificial intelligence, smart transportation, assisted driving and other scenarios.

[0086] The following describes the information delivery control method provided by the exemplary embodiment of the present application in combination with the application scenarios described above and with reference to the accompanying drawings. It should be noted that the above application scenarios are only shown to facilitate understanding of the spirit and principles of the present application, and the implementation methods of the present application are not limited in this regard.

[0087] See also Figure 2 As shown, it is an implementation flow chart of an information delivery control method provided in an embodiment of the present application. Taking the execution subject as a server as an example, the specific implementation process of the method includes the following steps S201-S204:

[0088] S201: The server receives an information delivery request sent for target delivery information;

[0089] Among them, the sender of the information delivery request sends the information delivery request to the server when an exposure opportunity occurs, so that the server can determine whether to deliver the target delivery information. The exposure opportunity can appear when the user logs in to the client, the user opens a page on the website, etc. The sender can be the client, or the server corresponding to the client, as well as the website backend server, etc., without specific limitation here.

[0090] As described in the background technology of this application, the time period for information delivery has an important impact on the effect of information delivery, and the individual attributes of the object to be delivered also have an important impact on the effect of information delivery. If the object to be delivered is not interested in the target delivery information itself, even if the information is delivered, the corresponding effect cannot be achieved, and the delivery resources are wasted. Therefore, the information delivery request includes the object attribute information of the object to be delivered and the target delivery time period, so that the server can determine whether to deliver the information based on the above information.

[0091] S202: The server assigns the to-be-delivered object to a target object set in a plurality of candidate object sets based on the object attribute information;

[0092] Specifically, the object attribute information may include the object's age, gender, hobbies, and historical feedback behavior on the target delivery data. For example, if the object is 20 years old, there are candidate object set 1, candidate object set 2, and candidate object set 3. The age range of the objects in candidate object set 1 is less than 30 years old, the age range of the objects in candidate object set 2 is greater than 30 years old and less than 50 years old, and the age range of the objects in candidate object set 3 is greater than 50 years old. Then the object can be assigned to candidate object set 1, that is, candidate object set 1 is the target object set.

[0093] For another example, if the object's historical feedback behavior on the target delivery data is "clicked", the feedback behavior of the objects in candidate object set 4 is "not clicked", and the feedback behavior of the objects in candidate object set 5 is "clicked", then the object is assigned to candidate set 5.

[0094] The goal of information delivery is to get user feedback on the target delivery information. Therefore, before information delivery, the decision on whether to deliver information can be made by predicting the feedback status. The main goal of information delivery is to improve the return on investment (ROI). In other words, information delivery focuses on the user's conversion and payment behavior. Therefore, for the business side, the delivery objects can also be divided into high-conversion high-paying objects and low-conversion low-paying objects. The delivery objects can be classified based on the predicted feedback status. The objects belonging to the same candidate object set have the same predicted feedback status for the target delivery information. In this way, different delivery strategies can be implemented for objects in different object sets, and more delivery resources can be invested in high-value objects.

[0095] It is understandable that in the specific implementation of the present application, related data such as user information, such as object attribute information, is involved. When the above embodiments of the present application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.

[0096] Optionally, the predicted feedback state includes predicted interest and predicted resource transfer amount, and step S22 may be implemented as follows:

[0097] Based on the object attribute information, the predicted interest and predicted resource transfer amount of the object to be placed are obtained; based on the predicted interest and predicted resource transfer amount, the object to be placed is assigned to a target object set in a plurality of candidate object sets.

[0098] Specifically, the predicted interest level can measure the object's interest in the target delivery information, which can be CTR, CVR, CTCVR and other information. The predicted resource transfer volume can measure the resources that the object can invest in the product corresponding to the target delivery information, which can be specifically reflected by LTV. The above information can all be input into the object attribute information and obtained using the CTR model, CVR model, CTCVR model and LTV model.

[0099] For example, the estimated CTCVR value (pCTCVR) of the object to be placed is 51%, and the estimated LTV value (pLTV) is 100, the pCTCVR of candidate object set 4 is 0-30%, and the pLTV is 0-50, the pCTCVR of candidate object set 5 is 31%-50%, and the pLTV is 51-80, and the pCTCVR of candidate object set 6 is 51%-100%, and the pLTV is 80-150, then the object to be placed belongs to candidate object set 6.

[0100] Taking the predicted interest as pCTCVR and the predicted resource transfer volume as pLTV as an example, the CTCVR model and the LTV model are used to estimate the user's conversion and payment possibilities. Therefore, the model's estimated values ​​pCTCVR and pLTV measure the quality of online traffic to a certain extent. Traditional Internet advertising generally points out that a model p value threshold is set to filter low-quality traffic, and the dynamic regulation of traffic is achieved by dynamically adjusting the threshold value. Figure 3 As shown in the figure, the threshold value of pCTCVR is 50%, and the threshold value of pLTV is 100. Then users with pCTCVR greater than 50% and pLTV greater than 100 can be regarded as potential high-conversion and high-paying users. However, Figure 4 As shown in the figure, since the p-value distribution of the online traffic model is not uniform, the same threshold value changes in different p-value intervals will result in large differences in traffic changes, making it difficult to measure the impact on the budget.

[0101] According to the above content, reasonably setting the boundary values ​​of different candidate object sets plays an important role in information delivery control. Optionally, multiple historical delivery objects of the target delivery information and their respective predicted feedback states are obtained; based on each predicted feedback state, the set boundary values ​​of multiple candidate object sets are obtained.

[0102] Specifically, for the historical delivery request user, its predicted feedback status is determined, and the predicted feedback status is used to determine the set boundary values ​​of the candidate object sets. For example, among the 50 historical delivery objects, the estimated click rate of historical delivery objects 1-10 is 0.3, the estimated click rate of historical delivery objects 11-25 is 0.5, the estimated click rate of historical delivery objects 26-44 is 0.6, and the estimated click rate of historical delivery objects 45-50 is 0.7. Then, the set boundary values ​​of candidate object set 7 are 0.3 and 0.5, and the set boundary values ​​of candidate object set 8 are 0.6 and 0.7.

[0103] In order to achieve uniform division of online traffic, when determining the set boundary value, the historical delivery objects can also be stratified with equal frequency, and the boundary value of each layer can be used as the set boundary value. For example, when the predicted feedback status is pCTCVR and pLTV, Figure 5As shown in the figure, the object attribute information of the historical delivery objects is respectively input into the CTCVR model and the LTV model for prediction, and the distribution of pCTCVR and pLTV is represented by bar graphs. On the one hand, pCTCVR is stratified with equal frequency to obtain 3 layers, and the boundary values ​​of each layer are (0.2, 0.3) (0.4, 0.5) (0.5, 0.7). On the other hand, pLTV is stratified with equal frequency to obtain 3 layers, and the boundary values ​​of each layer are (20, 30) (40, 50) (50, 70). Cartesian product is performed on each layer to obtain 9 candidate object sets.

[0104] Based on the above method, we use the historical request users to calculate the equal frequency quantiles of pCTCVR and pLTV and store them in the remote dictionary service (redis); online, we divide the traffic into a certain value layer (candidate object set) according to the model p value of each traffic and the corresponding quantile. This achieves a uniform cutting of online traffic. Through the layered flow control algorithm, after the traffic is layered, we set a flow controller for each traffic layer to control the competition rate of the traffic in that layer. Figure 6 As shown in the figure, when an exposure opportunity occurs, each flow controller can set a different participation rate to decide whether to participate. By setting different participation rates for different layers, different flow control strategies for different mass flows are implemented. In practice, the flow can be divided into 1000 layers and 1000 flow controllers are set.

[0105] The biggest difficulty of hierarchical flow control is how to convert the budget into the competition rate of 1,000 flow controllers. It can be modeled as a scheduling optimization problem:

[0106]

[0107]

[0108]

[0109] Among them, P i represents the competition rate of the i-th layer, B t represents the budget at time t, f i Represents the mapping function from the i-th layer competition rate to consumption. There are two difficulties in solving this optimization problem:

[0110] Since the quality of traffic at each layer is different, the functional relationship of how the competition rate affects consumption is different. Even if we use historical data to learn these 1000 functions, the changes in daily quantiles and traffic will cause historical experience to become invalid. i It is known that under the above constraints, this problem also has infinite solutions.

[0111] (1) Strengthen the constraints on inter-layer competition rates;

[0112] In order to reduce the solution space, we further constrained the competition rate of each layer of traffic: each layer of traffic will only start to increase in volume after the previous layer of traffic is fully opened. In this way, we can get the transformed optimization problem:

[0113]

[0114] sP N =P N-1 = =P k+1 =1

[0115] P k-1 =P k-2 =…=P1=0

[0116] The solution space of this problem has only two dimensions, the minimum active layer K and the corresponding competition rate P of this layer k , thus reducing the 1000-dimensional solution space to 2 dimensions.

[0117] (2) Assumption of intraday flow continuity

[0118] Although the volatility of traffic makes it difficult to estimate a stable consumption-competition rate function, Figure 7 It can be seen that the traffic in an information delivery cycle has a certain continuity, that is, for the traffic in the same object set, the change difference in adjacent delivery time periods is not large. In other words, the historical competition rate of the candidate object set can be used to set the target competition rate of the target delivery time period.

[0119] S203: The server obtains a target competition rate of the target object set in the target delivery time period based on the position of the target delivery time period in the information delivery cycle and the historical competition rates of the multiple candidate object sets in the previous delivery time period of the target delivery time period;

[0120] Specifically, the information delivery cycle includes multiple delivery time periods, and the participation rates of different delivery time periods may be different. For example, a lower participation rate may be set from 5:00 to 6:00, and a higher participation rate may be set from 19:00 to 20:00. Usually, the information delivery cycle is set to one day, and the target delivery time period may be one or several hours in a day, or several minutes, which is not specifically limited here. Based on the above assumptions, the target participation rate in the target delivery time period may be obtained based on the historical participation rate of the candidate object set in the previous delivery time period. For example, the participation rate of candidate object set 1 from 5:00 to 6:00 is set to 50%, and the participation rate from 6:00 to 7:00 is set to 55%.

[0121] S204: The server obtains a delivery strategy for target delivery information based on the target competition rate.

[0122] Specifically, after obtaining the target competition participation rate, the server can determine whether to deliver the target delivery information based on the target competition participation rate. For example, if the target competition participation rate is 100%, then the information needs to be delivered this time. For another example, if the target competition participation rate is 50%, and the proportion of competition within the target delivery time period is 60%, then it is not necessary to participate in the competition this time, so that the competition rate is close to 50%.

[0123] In an embodiment of the present application, when controlling the delivery of target delivery information, first, based on the object attribute information, the object to be delivered is assigned to a target object set in a plurality of candidate object sets, so that different delivery strategies can be set for different objects. Then, the target competition rate of the target object set is obtained by combining the delivery time period and the historical competition rates of the plurality of candidate object sets, so that different competition rates can be set for different delivery times. In the same delivery time period, different object sets can also be set with different competition rates, which fully considers the impact of the delivery time and the delivery object on the information delivery effect. Finally, the delivery strategy for the object to be delivered is determined based on the target competition rate. Controlling information delivery based on the above method can ensure that the delivery information is accurately delivered to high-quality delivery objects while controlling the consumption of delivery resources, thereby improving the conversion rate of delivery information, and further improving the utilization rate of delivery resources. The saved resources can be used to compete for more exposure opportunities, increase the exposure, and further improve the conversion effect.

[0124] Optionally, in step S23, the target competition rate can be set in the following two cases according to the position of the target delivery time period:

[0125] Case 1: When the target delivery time period is the first delivery time period in the information delivery cycle, the preset competition rate is used as the target competition rate;

[0126] At this time, it is impossible to refer to the historical participation rates of the candidate object sets in other delivery time periods within the information delivery cycle, so the preset participation rate is used as the target participation rate. For example, the competition rate of candidate object set 1 is 70%, the competition rate of candidate object set 2 is 50%, the competition rate of candidate object set 3 is 30%, and the competition rate of candidate object set 4 is 10%. If the target object set is candidate object set 3, then the target participation rate is 30%.

[0127] Case 2: When the target delivery time period is not the first delivery time period in the information delivery cycle, the target competition rate is obtained based on at least one reference resource consumption in the target delivery time period and each historical competition rate.

[0128] The reference resource consumption is the resource consumption of the historical delivery time period before the target delivery time period within the information delivery cycle. For example, each delivery time period is 1 hour, and the target delivery time period is 2 o'clock to 3 o'clock. The historical delivery time period 1 is 0 o'clock to 1 o'clock, the planned consumption is 500, and the reference resource consumption is 500. The historical delivery time period 2 is 1 o'clock to 2 o'clock, the planned consumption is 600, and the reference resource consumption is 400. Therefore, there is a surplus in the planned consumption. Within 1 o'clock to 2 o'clock, the competition rate of candidate object set 1 is 40%, and the competition rate of candidate object set 2 is 50%. Then the competition rate within 1 o'clock to 2 o'clock can be increased. The target object set is candidate object set 2, and the target competition rate is 60%.

[0129] Optionally, in case 2, the target participation rate is obtained by the following steps:

[0130] S31: Obtaining an estimated resource input amount for a target delivery time period based on at least one reference resource consumption amount, the planned resource input amounts for each historical delivery time period, and the planned resource input amount for a target delivery time period;

[0131] S32: Based on the resource difference between the estimated resource input and the historical resource consumption in the previous historical delivery time period, adjust each historical competition rate in turn according to a preset order to obtain a target competition rate for each of the multiple candidate object sets.

[0132] Specifically, each information delivery cycle will pre-allocate planned resource inputs for each delivery time period. In actual applications, it is difficult to ensure that the resource consumption within the delivery time period is completely consistent with the planned resource input. Therefore, in order to reasonably control resource consumption, the planned resource input for the target delivery time period can be adjusted based on the difference between the reference resource consumption and the planned resource consumption. If the consumption is high, the resource input for the target delivery time period will be reduced, otherwise it will be increased to obtain the estimated resource input for the target delivery time period.

[0133] Furthermore, in the process of adjusting the historical competition rate, as shown above, different candidate object sets have different predicted feedback states. In order to ensure the rational use of resources, priority should be given to increasing the quantity of candidate object sets with high predicted feedback states, and priority should be given to reducing the quantity of candidate object sets with low predicted feedback states. Therefore, based on multiple candidate object sets and their respective predicted feedback states, a preset order can be determined, and the historical competition rate can be adjusted in sequence according to the preset order.

[0134] Optionally, if the resource difference is greater than the preset threshold, the preset order is: the corresponding predicted feedback state is in order from high to low; if the resource difference is not greater than the preset threshold, the preset order is: the corresponding predicted feedback state is in order from low to high.

[0135] For example, if the preset threshold is 0, then if the resource difference is greater than 0, the historical competition rate is increased in descending order of the predicted feedback status; if the resource difference is less than 0, the historical competition rate is decreased in descending order of the predicted feedback status.

[0136] In the process of adjusting the historical competition rate according to the preset order, since increasing or decreasing the competition rate of a candidate set will affect the amount of resources required to be invested, the resource difference will also change accordingly. Optionally, the current resource difference for each competition rate adjustment is determined in the following way:

[0137] When the location meets the preset location conditions, the resource difference determined based on the expected resource input and historical resource consumption will be used as the current resource difference; when the location does not meet the preset location conditions, the current resource difference corresponding to the intermediate object set will be adjusted based on the target competition rate, reference competition rate and object resource consumption of the intermediate object set to obtain the current resource difference.

[0138] Specifically, in the preset order, the position of the intermediate object set is before and adjacent to the position of a candidate object set. The preset position condition may be that the position in the preset order is the first, and for the candidate object sets after the first candidate object set, their current resource difference values ​​are all obtained based on the adjustment result of the previous candidate object set. For example, the preset order is candidate object set 1→candidate object set 2→candidate object set 3, and the resource difference value determined based on the expected resource input and historical resource consumption is 1000, then the current resource difference value corresponding to candidate object set 1 is 1000, and after the competition rate of candidate object set 1 is increased, the required resource input amount increases by 700, and the increased resource input amount needs to be subtracted from the initial resource difference value, therefore, the current resource difference value corresponding to candidate object set 2 is 300, and after the competition rate of candidate object set 2 is increased, the required resource input amount increases by 200, and the current resource difference value corresponding to candidate object set 3 is 100. According to the above content, the current resource difference value is determined based on the position of a candidate object set in the preset order.

[0139] For the same candidate set, the changes in adjacent adjustment periods are not very different, so we can introduce a daily traffic continuity assumption: the competition rate and consumption in adjacent adjustment periods are proportional. In other words, we can use the consumption C of the previous delivery period (t) i (Object resource consumption) and competition rate P (t) i (reference competition rate), estimate how much consumption will be caused by the competition rate in the current delivery time period. Therefore, after obtaining the target competition rate of the candidate set, the current resource difference △C can be adjusted by the following formula:

[0140]

[0141] Among them, △C 1 is the current resource difference corresponding to the candidate object set, P i (t) is the target participation rate, P i (t-1) is the historical participation rate, The resource consumption of the object.

[0142] Optionally, in step S32, for a candidate object set, a target competition rate is obtained by:

[0143] Based on the current resource difference and the object resource consumption of a candidate object set in the previous delivery time period, the historical competition rate of a candidate object set is adjusted to obtain a corresponding target competition rate.

[0144] Specifically, the target competition rate can be obtained by the following formula:

[0145]

[0146] In the above, by introducing the assumption of intraday traffic continuity, the target competition rate is calculated using the object resource consumption and competition rate in the previous delivery period and the estimated resource input in the target delivery period, thus bypassing the problem of learning the consumption-competition rate function. However, the introduction of the assumption of intraday traffic continuity also brings two new problems:

[0147] (1) If the candidate set in the previous delivery period has not been allocated resources, its consumption and competition rate are unknown, and it is impossible to calculate the appropriate competition rate to compensate the budget;

[0148] (2) The assumption of intraday flow continuity will inevitably introduce deviations, and such deviations will accumulate over time. How can we eliminate the impact of accumulated deviations on budget control?

[0149] For problem 1, a flexible exploration buffer mechanism is designed: each candidate object set is regarded as a layer, such as Figure 8As shown in the figure, according to the order of the predicted feedback status of each candidate object set from high to low, it is divided into an active layer, an exploration layer, and a closed layer. The participation rate of the active layer is greater than 0, the exploration layer participates in the competition at a very small participation rate (the impact on the overall consumption can be ignored), and the participation rate of the closed layer is 0. The role of the exploration layer is to serve as a buffer zone between the active layer and the closed layer. When it is necessary to increase the volume, the exploration layer will be opened first. The consumption and competition rate of the exploration layer during the exploration period are known, which is convenient for calculating the appropriate competition rate according to needs. After each adjustment, the new closed layer will be set as the exploration layer to ensure that there are always a certain number of exploration layers between the active layer and the closed layer. The number of exploration layers can be flexibly adjusted according to the actual daily consumption progress, so as to predict the strength of future scaling in advance. By establishing an elastic exploration buffer mechanism, user stratification can be based on model value.

[0150] Therefore, assuming that the exploration layer is preset to number n, when the historical competition rate of the candidate object set is not greater than 0, that is, it is a closed layer in the previous delivery time period, this candidate object set and the subsequent n-1 candidate object sets can be set as exploration layers, and compete with the preset competition rate of 0.001.

[0151] For problem 2, in order to eliminate the cumulative deviation introduced by inconsistent assumptions, at each budget control, according to the deviation between the planned resource input and the reference resource consumption in the historical delivery time period, a sequential quadratic programming problem is solved to reallocate the cumulative deviation to the future delivery time period. The form of the sequential quadratic programming problem is as follows:

[0152]

[0153]

[0154] Among them, C T With B T represents the consumption and budget in the Tth delivery period, and B represents the daily budget. The analytical solution to this problem is expressed as:

[0155]

[0156] The physical meaning of this solution is to reallocate the accumulated deviation between the daily historical budget and consumption to the subsequent delivery time period, such as Fig. 9 shown.

[0157] like Fig.10 As shown, the embodiment of the present application also provides an interface diagram of an information delivery system, and the object can set a corresponding delivery plan in the interface to control the information delivery.

[0158] like Fig.11As shown, it is a schematic diagram of the operation process of an information delivery system in an embodiment of the present application, which includes three parts: an offline process, a quasi-real-time process and an online process. In the offline process, based on the historical delivery data, the set boundary value of each candidate object set is obtained, and the resource input amount for each delivery time period is pre-allocated. In the quasi-real-time process, based on the real-time streaming data, the resource input amount for the future delivery time period is dynamically adjusted in real time, and then the competition rate is adjusted. In the online process, based on the object attribute information, the objects to be delivered are assigned to the target object set, and according to the competition rate of the target object set, it is decided whether to deliver the information.

[0159] The entire process can be likened to a reservoir: the flow stratification is likened to the water level, and the process of increasing and decreasing the volume is likened to the process of adding and releasing water. Each increase in volume will prioritize increasing the volume from the high layer to the low layer, and each decrease in volume will prioritize decreasing the volume from the low layer to the high layer. In this way, in the entire budget flow control process, high-value users can be identified and retained.

[0160] like Fig.12 As shown, it is a logical schematic diagram of an information delivery control method in an embodiment of the present application. For the object 1 to be delivered, the information delivery cycle is 1 day, and the target delivery time period is 4 o'clock to 5 o'clock. From 3 o'clock to 4 o'clock, the historical competition rate of candidate object set 1 is 30%, the historical competition rate of candidate object set 2 is 40%, and the historical competition rate of candidate object set 3 is 50%. The historical competition rates are adjusted, and the target competition rates of candidate object set 1, candidate object set 2, and candidate object set 3 are 35%, 45%, and 55%. According to the object attribute information, it is determined that the object 1 to be delivered belongs to the candidate object set 2, and then according to the competition rate of 45%, it is determined whether to deliver information to the delivery object.

[0161] Based on the information delivery control method in the embodiment of the present application, the intelligent layered flow control reduced the CPA within the delivery business by 20%, increased the ROI on the first day by about 500%, and significantly increased the daily exposure time of each duration and each core advertisement by about 100%, indicating that the flow control algorithm improves the time coverage span of the budget.

[0162] Based on the same inventive concept, the present application also provides an information delivery control device. Fig.13 As shown, it is a schematic diagram of the structure of the information delivery control device 1300, which may include:

[0163] The receiving unit 1301 is used to receive an information delivery request sent for target delivery information, the information delivery request including: object attribute information of the object to be delivered and a target delivery time period;

[0164] The attribution unit 1302 is used to attribute the to-be-delivered object to a target object set in a plurality of candidate object sets based on the object attribute information;

[0165] The processing unit 1303 is configured to obtain a target competition rate of the target object set in the target delivery time period based on the position of the target delivery time period in the information delivery cycle and the historical competition rates of the plurality of candidate object sets in the previous delivery time period of the target delivery time period;

[0166] The strategy unit 1304 is used to obtain a delivery strategy of target delivery information based on the target competition rate.

[0167] In an embodiment of the present application, when controlling the delivery of target delivery information, first, based on the object attribute information, the object to be delivered is assigned to a target object set in a plurality of candidate object sets, so that different delivery strategies can be set for different objects. Then, the target competition rate of the target object set is obtained by combining the delivery time period and the historical competition rates of the plurality of candidate object sets, so that different competition rates can be set for different delivery times. In the same delivery time period, different object sets can also be set with different competition rates, which fully considers the impact of the delivery time and the delivery object on the information delivery effect. Finally, the delivery strategy for the object to be delivered is determined based on the target competition rate. Controlling information delivery based on the above method can ensure that the delivery information is accurately delivered to high-quality delivery objects while controlling the consumption of delivery resources, thereby improving the conversion rate of delivery information, and further improving the utilization rate of delivery resources. The saved resources can be used to compete for more exposure opportunities, increase the exposure, and further improve the conversion effect.

[0168] Optionally, the processing unit 1303 is specifically configured to:

[0169] When the target delivery time period is the first delivery time period in the information delivery cycle, the preset competition participation rate is used as the target competition participation rate;

[0170] When the target delivery time period is not the first delivery time period in the information delivery cycle, the target competition rate is obtained based on at least one reference resource consumption of the target delivery time period and each historical competition rate, wherein the reference resource consumption is: the resource consumption of the historical delivery time period before the target delivery time period in the information delivery cycle.

[0171] Optionally, the processing unit 1303 is specifically configured to:

[0172] Obtaining an estimated resource input amount for the target delivery time period based on at least one reference resource consumption, the planned resource input amount for each historical delivery time period, and the planned resource input amount for the target delivery time period;

[0173] Based on the resource difference between the expected resource input and the historical resource consumption in the previous historical delivery time period, each historical competition rate is adjusted in sequence according to a preset order to obtain the target competition rate of each of the multiple candidate object sets, wherein the preset order is determined based on the predicted feedback status of each of the multiple candidate object sets.

[0174] Optionally, the processing unit 1303 is specifically configured to:

[0175] For a candidate object set, based on the current resource difference and the object resource consumption of the candidate object set in the previous delivery time period, the historical competition rate of the candidate object set is adjusted to obtain a corresponding target competition rate;

[0176] The current resource difference is determined based on the position of a candidate object set in a preset order.

[0177] Optionally, if the resource difference is greater than a preset threshold, the preset order is: the order of the corresponding prediction feedback states from high to low;

[0178] If the resource difference is not greater than the preset threshold, the preset order is: the order of the corresponding prediction feedback states from low to high.

[0179] Optionally, the processing unit 1303 is specifically configured to determine the current resource difference in the following manner:

[0180] When the location meets the preset location conditions, the resource difference determined based on the expected resource input and historical resource consumption is used as the current resource difference;

[0181] When the position does not meet the preset position condition, the current resource difference corresponding to the intermediate object set is adjusted based on the target competition rate, reference competition rate and object resource consumption of the intermediate object set to obtain the current resource difference;

[0182] In the preset order, the position of the intermediate object set is before the position of a candidate object set and is adjacent to the candidate object set.

[0183] Optionally, objects belonging to the same candidate object set have the same predicted feedback status for target delivery information.

[0184] Optionally, the predicted feedback state includes predicted interest and predicted resource transfer amount; the attribution unit 1302 is specifically configured to:

[0185] Based on the object attribute information, the predicted interest level and predicted resource transfer amount of the object to be placed are obtained;

[0186] Based on the predicted interest and the predicted resource transfer amount, the object to be delivered is assigned to a target object set in a plurality of candidate object sets.

[0187] Optionally, the device further includes an acquisition unit 1305, configured to obtain multiple candidate object sets in the following manner:

[0188] Get multiple historical delivery objects of target delivery information and their respective forecast feedback status;

[0189] Based on each prediction feedback state, a set boundary value of each of the plurality of candidate object sets is obtained.

[0190] For the convenience of description, the above parts are divided into modules (or units) according to their functions and described separately. Of course, when implementing this application, the functions of each module (or unit) can be implemented in the same or multiple software or hardware.

[0191] Those skilled in the art will appreciate that various aspects of the present application may be implemented as a system, method or program product. Therefore, various aspects of the present application may be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which may be collectively referred to as "circuit", "module" or "system" herein.

[0192] Based on the same inventive concept as the above method embodiment, an electronic device is also provided in the embodiment of the present application. In one embodiment, the electronic device may be a server, such as Figure 1B In this embodiment, the structure of the electronic device can be as follows: Fig.14 As shown, it includes a memory 1401 , a communication module 1403 and one or more processors 1402 .

[0193] The memory 1401 is used to store computer programs executed by the processor 1402. The memory 1401 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and programs required for running the instant messaging function, etc.; the data storage area may store various instant messaging information and operation instruction sets, etc.

[0194] The memory 1401 may be a volatile memory, such as a random-access memory (RAM); the memory 1401 may also be a non-volatile memory, such as a read-only memory, a flash memory, a hard disk drive (HDD) or a solid-state drive (SSD); or the memory 1401 may be any other medium that can be used to carry or store a desired computer program in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 1401 may be a combination of the above memories.

[0195] The processor 1402 may include one or more central processing units (CPU) or a digital processing unit, etc. The processor 1402 is used to implement the above-mentioned information delivery control method when calling the computer program stored in the memory 1401 .

[0196] The communication module 1403 is used to communicate with terminal devices and other servers.

[0197] The specific connection medium between the memory 1401, the communication module 1403 and the processor 1402 is not limited in the embodiment of the present application. Fig.14 In the embodiment, the memory 1401 and the processor 1402 are connected via a bus 1404. Fig.14 The connections between the other components are only for illustration and are not intended to be limiting. The bus 1404 can be divided into an address bus, a data bus, a control bus, etc. For ease of description, Fig.14 The diagram shows that only one thick line is used, but this does not mean that there is only one bus or only one type of bus.

[0198] The memory 1401 stores a computer storage medium, and the computer storage medium stores computer executable instructions, which are used to implement the information delivery control method of the embodiment of the present application. The processor 1402 is used to execute the above-mentioned information delivery control method, such as Figure 2 shown.

[0199] In another embodiment, the electronic device may also be other electronic devices, such as Figure 1B In this embodiment, the structure of the electronic device can be as follows: Fig.15As shown, it includes: a communication component 1510, a memory 1520, a display unit 1530, a camera 1540, a sensor 1550, an audio circuit 1560, a Bluetooth module 1570, a processor 1580 and other components.

[0200] The communication component 1510 is used to communicate with the server. In some embodiments, a wireless fidelity (WiFi) module may be included. The WiFi module belongs to a short-range wireless transmission technology. The electronic device can help the user to send and receive information through the WiFi module.

[0201] The memory 1520 can be used to store software programs and data. The processor 1580 executes various functions and data processing of the terminal device by running the software programs or data stored in the memory 1520. The memory 1520 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage device. The memory 1520 stores an operating system that enables the terminal device to run. In the present application, the memory 1520 can store an operating system and various application programs, and can also store a computer program for executing the information delivery control method of the embodiment of the present application.

[0202] The display unit 1530 can also be used to display information input by the user or information provided to the user and a graphical user interface (GUI) of various menus of the terminal device. Specifically, the display unit 1530 may include a display screen 1532 disposed on the front of the terminal device. The display screen 1532 may be configured in the form of a liquid crystal display, a light emitting diode, etc. The display unit 1530 may be used to display the information delivery control user interface in the embodiment of the present application, etc.

[0203] The display unit 1530 can also be used to receive input digital or character information and generate signal input related to user settings and function control of the terminal device. Specifically, the display unit 1530 may include a touch screen 1531 arranged on the front of the terminal device, which can collect user touch operations on or near it, such as clicking a button, dragging a scroll box, etc.

[0204] The touch screen 1531 can be covered on the display screen 1532, or the touch screen 1531 and the display screen 1532 can be integrated to realize the input and output functions of the terminal device, and the integrated display screen can be referred to as a touch display screen. In this application, the display unit 1530 can display the application program and the corresponding operation steps.

[0205] The camera 1540 can be used to capture still images, and the user can post comments on the images taken by the camera 1540 through the application. The camera 1540 can be one or more. The object generates an optical image through the lens and projects it onto the photosensitive element. The photosensitive element can be a charge coupled device (CCD) or a complementary metal-oxide-semiconductor (CMOS) phototransistor. The photosensitive element converts the optical signal into an electrical signal, and then passes the electrical signal to the processor 1580 to convert it into a digital image signal.

[0206] The terminal device may further include at least one sensor 1550, such as an acceleration sensor 1551, a distance sensor 1552, a fingerprint sensor 1553, and a temperature sensor 1554. The terminal device may also be configured with other sensors such as a gyroscope, a barometer, a hygrometer, a thermometer, an infrared sensor, a light sensor, and a motion sensor.

[0207] The audio circuit 1560, the speaker 1561, and the microphone 1562 can provide an audio interface between the user and the terminal device. The audio circuit 1560 can transmit the electrical signal converted from the received audio data to the speaker 1561, which is converted into a sound signal for output. The terminal device can also be equipped with a volume button for adjusting the volume of the sound signal. On the other hand, the microphone 1562 converts the collected sound signal into an electrical signal, which is received by the audio circuit 1560 and converted into audio data, and then the audio data is output to the communication component 1510 to be sent to, for example, another terminal device, or the audio data is output to the memory 1520 for further processing.

[0208] The Bluetooth module 1570 is used to exchange information with other Bluetooth devices having Bluetooth modules through the Bluetooth protocol. For example, the terminal device can establish a Bluetooth connection with a wearable electronic device (such as a smart watch) that also has a Bluetooth module through the Bluetooth module 1570 to exchange data.

[0209] The processor 1580 is the control center of the terminal device. It uses various interfaces and lines to connect various parts of the entire terminal. It executes various functions of the terminal device and processes data by running or executing software programs stored in the memory 1520 and calling data stored in the memory 1520. In some embodiments, the processor 1580 may include one or more processing units; the processor 1580 may also integrate an application processor and a baseband processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the baseband processor mainly processes wireless communications. It is understandable that the above-mentioned baseband processor may not be integrated into the processor 1580. In the present application, the processor 1580 can run the operating system, application programs, user interface display and touch response, as well as the information delivery control method of the embodiment of the present application. In addition, the processor 1580 is coupled to the display unit 1530.

[0210] In some possible implementations, various aspects of the information delivery control method provided by the present application may also be implemented in the form of a program product, which includes a computer program. When the program product is run on an electronic device, the computer program is used to enable the electronic device to execute the steps of the information delivery control method according to various exemplary implementations of the present application described above in this specification. For example, the electronic device may execute the following steps: Figure 2 Follow the steps shown in .

[0211] The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0212] The program product of the embodiment of the present application may adopt a portable compact disk read-only memory (CD-ROM) and include a computer program, and can be run on an electronic device. However, the program product of the present application is not limited thereto, and in this document, a readable storage medium may be any tangible medium containing or storing a program, which can be used by or in combination with a command execution system, apparatus, or device.

[0213] A readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, wherein a readable computer program is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. A readable signal medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with a command execution system, apparatus, or device.

[0214] The computer program embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0215] The computer program for performing the operation of the present application can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and also conventional procedural programming languages ​​such as "C" language or similar programming languages. The computer program can be executed entirely on the user electronic device, partially on the user device, as a separate software package, partially on the user electronic device and partially on a remote electronic device, or entirely on a remote electronic device or server. In the case of a remote electronic device, the remote electronic device can be connected to the user electronic device through any type of network including a local area network (LAN) or a wide area network (WAN), or can be connected to an external electronic device (for example, using an Internet service provider to connect through the Internet).

[0216] It should be noted that, although several units or subunits of the device are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more units described above can be embodied in one unit. Conversely, the features and functions of one unit described above can be further divided into multiple units to be embodied.

[0217] In addition, although the operations of the method of the present application are described in a specific order in the drawings, this does not require or imply that the operations must be performed in this specific order, or that all the operations shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps.

[0218] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain a computer-usable computer program.

[0219] The present application is described with reference to the flowchart and / or block diagram of the method, device (system) and computer program product according to the embodiment of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, and the combination of the process and / or box in the flowchart and / or block diagram can be realized by computer program commands. These computer program commands can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the command executed by the processor of the computer or other programmable data processing device produces a device for realizing the function specified in one process or multiple processes in the flowchart and / or one box or multiple boxes in the block diagram.

[0220] These computer program commands may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the commands stored in the computer-readable memory produce a manufactured product including a command device that implements the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0221] These computer program commands can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, whereby the commands executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0222] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0223] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A method for controlling information delivery, characterized in that: The method comprises: Receiving an information delivery request sent for target delivery information, the information delivery request including: object attribute information of the object to be delivered and a target delivery time period; Based on the object attribute information, the to-be-delivered object is assigned to a target object set in a plurality of candidate object sets; Based on the position of the target delivery time period in the information delivery cycle, and the historical competition rates of the plurality of candidate object sets in the previous delivery time period of the target delivery time period, a target competition rate of the target object set in the target delivery time period is obtained; Based on the target competition participation rate, a delivery strategy for the target delivery information is obtained.

2. The method according to claim 1, characterized in that The obtaining, based on the position of the target delivery time period in the information delivery cycle to which the target delivery time period belongs, a target competition rate of the target object set in the target delivery time period includes: When the target delivery time period is the first delivery time period in the information delivery cycle, the preset competition participation rate is used as the target competition participation rate; When the target delivery time period is not the first delivery time period within the information delivery cycle, the target competition rate is obtained based on at least one reference resource consumption of the target delivery time period and various historical competition rates, wherein the reference resource consumption is: the resource consumption of the historical delivery time period within the information delivery cycle and located before the target delivery time period.

3. The method according to claim 2, characterized in that The step of obtaining the target competition rate based on at least one reference resource consumption in the target delivery time period and each historical competition rate includes: Obtaining an estimated resource input amount for the target delivery time period based on the at least one reference resource consumption, the planned resource input amount for each historical delivery time period, and the planned resource input amount for the target delivery time period; Based on the resource difference between the expected resource input and the historical resource consumption in the previous historical delivery time period, the historical competition rates are adjusted in sequence according to a preset order to obtain the target competition rates of the multiple candidate object sets, wherein the preset order is determined based on the predicted feedback status of each of the multiple candidate object sets.

4. The method according to claim 3, characterized in that The method of adjusting the historical competition rates in sequence according to a preset order based on the resource difference between the estimated resource input amount and the historical resource consumption amount in the previous historical delivery time period of the target delivery time period to obtain the target competition rates of the plurality of candidate object sets includes: For a candidate object set, based on the current resource difference and the object resource consumption of the candidate object set in the previous delivery time period, the historical competition rate of the candidate object set is adjusted to obtain a corresponding target competition rate; The current resource difference is determined based on the position of the candidate object set in the preset order.

5. The method according to claim 3, characterized in that If the resource difference is greater than a preset threshold, the preset order is: the order of the corresponding prediction feedback states from high to low; If the resource difference is not greater than the preset threshold, the preset order is: the order of corresponding prediction feedback states from low to high.

6. The method according to claim 4, characterized in that The current resource difference is determined by: When the location meets the preset location condition, the resource difference value determined based on the estimated resource input amount and the historical resource consumption amount is used as the current resource difference value; When the position does not meet the preset position condition, adjusting the current resource difference corresponding to the intermediate object set based on the target competition rate, reference competition rate and object resource consumption of the intermediate object set to obtain the current resource difference; Wherein, in the preset order, the position of the intermediate object set is before and adjacent to the position of one candidate object set.

7. The method according to any one of claims 1 to 6, characterized in that: The objects belonging to the same candidate object set have the same predicted feedback status for the target delivery information.

8. The method according to claim 7, characterized in that The predicted feedback status includes predicted interest and predicted resource transfer amount; Then, based on the object attribute information, the object to be delivered is assigned to a target object set in a plurality of candidate object sets, including: Based on the object attribute information, obtaining the predicted interest level and predicted resource transfer amount of the object to be delivered; Based on the predicted interest level and the predicted resource transfer amount, the to-be-delivered object is assigned to a target object set in the plurality of candidate object sets.

9. The method according to any one of claims 1 to 6, characterized in that: The multiple candidate object sets are obtained by: Obtain multiple historical delivery objects of the target delivery information and their respective predicted feedback states; Based on each prediction feedback state, a set boundary value of each of the plurality of candidate object sets is obtained.

10. An information delivery control device, characterized in that: include: A receiving unit, configured to receive an information delivery request sent for target delivery information, wherein the information delivery request includes: object attribute information of the object to be delivered and a target delivery time period; an attribution unit, configured to attribute the to-be-delivered object to a target object set in a plurality of candidate object sets based on the object attribute information; A processing unit, configured to obtain a target competition rate of the target object set in the target delivery time period based on the position of the target delivery time period in the information delivery cycle and the historical competition rates of the plurality of candidate object sets in the previous delivery time period of the target delivery time period; A strategy unit is used to obtain a delivery strategy of the target delivery information based on the target competition participation rate.

11. An electronic device, characterized in that: It comprises a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of any one of the methods of claims 1 to 9.

12. A computer-readable storage medium, characterized in that: It comprises a computer program. When the computer program is run on an electronic device, the computer program is used to enable the electronic device to execute the steps of any method described in claims 1 to 9.

13. A computer program product, characterized in that The method comprises a computer program stored in a computer-readable storage medium; when a processor of an electronic device reads the computer program from the computer-readable storage medium, the processor executes the computer program, so that the electronic device executes the steps of any one of the methods described in claims 1 to 9.

Images