Advertisement delivery method, device and equipment, and storage medium

Abstract

The application provides an advertisement putting method, device, equipment and storage medium, the method comprises the following steps: obtaining the putting geographical position of the to-be-put advertisement, and determining the to-be-put area according to the putting geographical position; determining the environment perception data of the to-be-put area according to the position of the target personnel in the to-be-put area; the environment perception data comprises at least one of personnel density data, personnel flow data, personnel portrait data and area heat data of the target personnel; and the putting geographical position is put according to the historical operation data of the target personnel for the advertisement and the environment perception data. The application can comprehensively use the historical operation data and real-time environment perception data to put the advertisement, effectively improving the accuracy and putting effect of the advertisement putting.

Description

Technical Field

[0001] This application relates to the field of advertising technology, and in particular to an advertising delivery method, apparatus, device, and storage medium. Background Technology

[0002] Currently, advertising campaigns typically rely on pre-built static user profiles. However, since static user profiles are based on historical data, they cannot reflect the user's current situation and changing environment in real time. Therefore, ads based on static user profiles lack real-time performance and adapt poorly to the user's actual scenario, resulting in poor advertising effectiveness. Summary of the Invention

[0003] The main objective of this invention is to provide an advertising delivery method, apparatus, device, and storage medium to solve the problems of insufficient real-time performance and poor scenario adaptability in existing advertising delivery methods, which rely on pre-built static user profiles and thus affect the effectiveness of advertising delivery.

[0004] Firstly, it provides an advertising placement method, including: Obtain the geographic location of the advertisement to be placed, and determine the target area based on the geographic location; Based on the location of the target personnel in the area to be targeted, determine the environmental perception data of the area to be targeted; the environmental perception data includes at least one of the following: personnel density data, personnel flow data, personnel profile data, and area heat data. Based on the target audience's historical data on advertising and environmental perception data, ads are targeted to specific geographic locations.

[0005] In conjunction with the first aspect, in certain implementations of the first aspect, the geographic location of the advertisement to be delivered is obtained, including: The geographical location of the advertisement to be placed is obtained based on the BeiDou satellite positioning system.

[0006] In conjunction with the first aspect, in some implementations of the first aspect, the environmental sensing data includes personnel thermal data, which includes at least one of the following: personnel density data, personnel flow data, and regional heat data of the target personnel. Based on the location of the target personnel in the area to be targeted, determine the environmental perception data for the area, including: Obtain the location of the target personnel in the area to be targeted; The location of the target personnel is transmitted to a pre-deployed edge computing node via a 5G network, and the edge computing node sends personnel thermal data; the personnel thermal data is obtained by the edge computing node after performing thermal analysis on the location of the target personnel. Based on human thermal data, determine the environmental perception data for the area to be deployed.

[0007] In conjunction with the first aspect, in some implementations of the first aspect, the computing power allocated to the edge computing node is determined based on the edge computing node's load, available computing power, and the preset task processing priority corresponding to the thermal analysis.

[0008] In conjunction with the first aspect, in some implementations of the first aspect, environmental perception data includes personnel profile data; based on the location of the target personnel in the area to be targeted, the environmental perception data of the area to be targeted is determined, including: Obtain the location of the target personnel in the area to be targeted; Based on the location of the target person, the corresponding preset image acquisition device is invoked to acquire the image of the target person and obtain the target person's facial data. Based on the facial data of the target person, obtain the target person's historical location from the collected historical location database; Based on the target personnel's historical location, determine the target personnel's profile data; Based on personnel profile data, determine the environmental perception data for the area to be deployed.

[0009] In conjunction with the first aspect, in some implementations of the first aspect, advertising is targeted to specific geographic locations based on the target audience's historical operational data regarding the advertisement, as well as environmental awareness data, including: Based on historical operational data, environmental perception data, and a pre-trained intelligent decision-making model, an advertising placement strategy is determined. The advertising placement strategy includes at least one of the following: the content to be placed, the placement time, and the placement frequency. The intelligent decision-making model is trained using a deep reinforcement learning algorithm with the optimization objectives of advertising conversion rate and user dwell time. Based on the advertising strategy, ads are targeted to specific geographic locations.

[0010] Secondly, an advertising delivery device is provided, including: The acquisition module is used to obtain the geographic location of the advertisement to be delivered, and determine the delivery area based on the geographic location; The determination module is used to determine the environmental perception data of the area to be targeted based on the location of the target personnel in the area to be targeted. The environmental perception data includes at least one of the following: personnel density data, personnel flow data, personnel profile data, and area heat data. The ad delivery module is used to deliver ads to geographic locations based on the target audience's historical action data and environmental perception data.

[0011] Thirdly, an advertising delivery device is provided, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the method of any one of the first aspects.

[0012] Fourthly, a computer-readable storage medium is provided for storing computer-executable instructions that, when executed by a processor, implement the steps of the method of any one of the first aspects.

[0013] Fifthly, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the steps of the method of any one of the first aspects are implemented.

[0014] Compared with the prior art, the embodiments of this application have the following advantages: In this embodiment, firstly, the specific target area is determined by acquiring the geographic location of the advertisement to be placed, providing a location basis for advertisement placement. Then, based on the real-time location information of target users in the target area, environmental perception data is generated. This environmental perception data includes dynamic indicators such as population density, population flow, user profiles, and regional heat, enabling real-time perception of the current scene. Finally, by combining the target users' historical advertising operation data with the environmental perception data, dynamic decisions are made and advertisement placement is executed to ensure that the advertisement content matches the real-time scene and user behavior.

[0015] This application embodiment integrates real-time environmental perception data and historical operation data for ad delivery, which can effectively improve the timeliness and scene adaptability of ad delivery. It enables the delivered ads to dynamically respond to environmental changes, thereby effectively solving the problems of insufficient real-time performance and poor scene adaptability caused by relying on static user profiles, improving ad conversion rate and user dwell time, and reducing ineffective delivery. Attached Figure Description

[0016] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 This is a schematic diagram of an advertising delivery method provided in one embodiment of this application; Figure 2 This is a schematic diagram of the module composition of an advertising delivery device 200 provided in one embodiment of this application; Figure 3 This is a schematic diagram of the hardware structure of an electronic device provided in one embodiment of this application. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0018] The technical solutions in this application will now be described with reference to the accompanying drawings.

[0019] Please see Figure 1 , Figure 1 This is a flowchart illustrating an advertising delivery method provided in one embodiment of this application, as shown below. Figure 1 As shown, the method includes the following steps: S101, obtain the geographic location of the advertisement to be placed, and determine the area to be placed based on the geographic location.

[0020] S102, Based on the location of the target personnel in the area to be deployed, determine the environmental perception data of the area to be deployed; the environmental perception data includes at least one of the following: personnel density data, personnel flow data, personnel profile data, and area heat data.

[0021] S103, based on the target personnel's historical operation data regarding the advertisement and environmental perception data, the advertisement is delivered to the geographical location.

[0022] In one embodiment of this application, firstly, the geographic location of the advertisement to be placed can be obtained, and the area to be placed can be determined based on the obtained geographic location.

[0023] In one implementation, such as Figure 1 In the method shown, when obtaining the geographic location of the advertisement to be placed, the geographic location can be obtained based on Beidou satellite positioning, thereby improving the accuracy and reliability of geographic location information and providing high-precision basic data support for the subsequent division of the placement area.

[0024] The positioning accuracy of BeiDou satellites is:

[0025] Among them, positioning accuracy (RMS), short for "root mean square error", is the core indicator for measuring the accuracy of positioning results. The smaller the value, the more accurate the positioning. GDOP is the geometric precision factor, which reflects the impact of the geometric distribution of satellites in the sky on positioning accuracy. The more uniform the distribution of satellites, the smaller the GDOP value, and the higher the positioning accuracy. This represents the standard deviation of satellite orbit error. Deviations in satellite orbit calculations directly lead to shifts in positioning results. This represents the standard deviation of the error between the satellite clock and the receiver clock. Satellite positioning relies on "time difference to calculate distance," and clock errors can significantly affect the accuracy of distance measurements. This represents the standard deviation of the error in the propagation delay of satellite signals caused by the ionosphere. Changes in the electron density of the ionosphere will alter the signal propagation speed and produce delay errors. This represents the standard deviation of the error in the propagation delay of satellite signals in the troposphere. Changes in the atmospheric environment of the troposphere (such as pressure, temperature, and humidity) can interfere with signal propagation. The standard deviation of errors such as multipath effects on the signal propagation path. Multipath refers to the multiple paths a signal takes to reach the receiver after reflection / scattering, causing interference errors. This represents the standard deviation of the receiver's own measurement error, including errors caused by internal factors such as hardware noise and circuit precision.

[0026] It should be noted that the parameters involved in the above positioning accuracy determination formula, such as GDOP, , All of these can be obtained based on existing technologies, therefore, the embodiments in this application will not be described in detail.

[0027] In this embodiment of the application, the reliability of location data can be determined by calculating the positioning accuracy of Beidou satellites in real time: when the accuracy meets the requirements, such as RMS≤3 meters, the location data can be determined to be reliable and can be used to generate heat maps and user trajectory analysis; when the accuracy is too low, such as RMS>5 meters, the data can be ignored or downgraded to avoid deployment based on incorrect location information.

[0028] In this embodiment, after determining the geographic location, the area within a preset distance from the geographic location can be designated as the advertising area. For example, a circular area can be defined with the geographic location as the center and the preset distance as the radius, and this circular area can be designated as the advertising area. Subsequently, when advertising is placed, the advertisement can be displayed on devices capable of displaying advertisements, such as screens, within this advertising area.

[0029] In one embodiment of this application, in such Figure 1 In the method shown, after determining the delivery area based on the delivery location, the location of the target personnel in the delivery area can be obtained, and the environmental perception data of the delivery area can be determined based on the location of the target personnel.

[0030] In one example, environmental perception data may include personnel thermal data, which may specifically include at least one of the following: personnel density data, personnel flow data, and area heat data. When determining the environmental perception data for a delivery area based on the location of target personnel, the location of the target personnel can be obtained first and transmitted via a 5G network to a pre-deployed edge computing node. The edge computing node then receives the personnel thermal data, which is obtained by performing thermal analysis on the target personnel's location. Based on this thermal data, the environmental perception data for the delivery area is determined, thereby achieving low-latency data transmission via the 5G network, improving the processing efficiency of the edge computing node, and making the environmental perception data more real-time and accurate.

[0031] In this example, the transmission latency of the 5G network can be:

[0032] in, It is the total transmission delay, which is the total time it takes for data to travel from the sending end to the receiving end, and is measured in seconds. It is transmission delay. The data length is typically determined by the amount of raw data collected by the sensor, and is measured in bits. Transmission bandwidth, measured in bits per second, represents the time it takes for data to be transmitted over the link. It is the propagation delay. The unit of measurement for transmission distance is meters, and At the speed of light, Let be the refractive index of the transmission medium, where 5G signals in air... This represents the propagation time of a signal in physical space; Processing latency refers to the time it takes for equipment, such as base stations and receivers, to encode, decode, and verify data. Queuing delay refers to the time that data waits to be transmitted in the network node's cache, and is usually related to the degree of network congestion.

[0033] The processing efficiency of edge computing nodes is:

[0034] in, It is the effective utilization rate of computing power (or data processing), which can be quantified in terms of the comprehensive utilization of time, data validity, and processing speed. The value ranges from 0 to 1, and the closer it is to 1, the higher the utilization efficiency. It is the actual time used for effective data processing, that is, the time spent actually performing calculations and analyses on the effective data; It is the total time to complete the task, including all time spent on effective processing, waiting, scheduling, data transmission, etc. This refers to the amount of invalid or erroneous data in the input data, such as noisy data, incorrectly formatted data, redundant or invalid data, etc. It is the total amount of input data; It is the actual processing rate, that is, the amount of effective data actually processed per unit time. It is the peak processing rate, the maximum processing capacity that can be achieved, determined by the hardware configuration of the edge computing node.

[0035] Human body heatmaps can be generated by fusing multi-source sensor data from cameras, Wi-Fi probes, and Bluetooth beacons to create a real-time crowd density distribution map. The accuracy of the generated crowd density distribution map can be improved through a weighting algorithm. The formula for calculating the crowd density heatmap is: (Gaussian kernel density algorithm) in, express population density This represents the weight of the i-th data point. In one example, N=3; then when i=1 (camera), it can represent the real-time number of people counted by the camera through AI algorithms (e.g., there are currently 50 people in a certain area); when i=2 (Wi-Fi probe), it can represent the number of active devices detected by the Wi-Fi access point (e.g., there are 30 mobile phones connected to or searching for Wi-Fi signals in a certain area); when i=3 (Bluetooth beacon), it can represent the number of pedestrians carrying Bluetooth devices detected by the Bluetooth beacon (e.g., there are 20 devices responding to Bluetooth signals in a certain area).

[0036] In one example, the computing power allocated to an edge computing node can be determined based on the edge computing node's load, available computing power, and the preset task processing priority corresponding to the thermal analysis, thereby realizing dynamic scheduling and reasonable allocation of computing resources and improving overall operating efficiency and response speed.

[0037] The formula for calculating the allocation of computing resources is as follows:

[0038] in, This represents the resource allocation suitability of the i-th task on the j-th edge computing node. The higher the value, the better the suitability of the task on that node, and the higher the priority of resource allocation. It is the weighting coefficient for task priority (manually configured, usually...) ,like Adjust the degree to which task priority affects fit; It represents the priority of the i-th task (the higher the value, the more important the task, such as the priority of the advertising delivery task being higher than that of the data storage task). It represents the resource availability of the j-th edge computing node (e.g., the current idle computing power percentage of the node, with a value ranging from 0 to 1, where the closer to 1, the more abundant the resources). It is the weighting factor of node load (manually configured, usually...) ,and ,like This is used to adjust the impact of node load on adaptability. It is the current load rate of the j-th edge computing node (e.g., the percentage of computing power used by the node, with a value between 0 and 1, the closer to 1, the heavier the load).

[0039] In the above steps of this application embodiment, the low-latency transmission mechanism of the 5G network is first used to achieve rapid transmission of location data to ensure the real-time nature of data transmission. Then, the efficient processing capabilities of edge computing nodes are used to perform real-time thermal analysis on the transmitted location data. During the real-time thermal analysis, the processing efficiency is quantified using a corresponding quantization formula. Based on this, a weighted fusion algorithm is used to integrate multi-source sensor data, and a high-precision crowd density distribution map is generated based on a Gaussian kernel density estimation algorithm. Through low-latency data transmission, real-time thermal analysis at edge nodes, and multi-source data fusion processing, environmental perception data that meets the requirements of real-time performance, accuracy, and stability can be generated. In addition, this application embodiment also proposes a dynamic computing resource scheduling strategy, which can intelligently allocate computing resources based on real-time task priorities and the load status of each node. This strategy optimizes the scheduling of computing tasks through a resource allocation suitability formula, ensuring the stable and efficient execution of the above analysis process in high-concurrency scenarios, and further ensuring the reliability of the environmental perception data generation process.

[0040] In one embodiment of this application, the environmental perception data may include personnel profile data. When determining the environmental perception data of the target area based on the location of the target personnel, the location of the target personnel in the target area can be obtained first. Then, based on the target personnel's location, a corresponding preset image acquisition device can be invoked to acquire images of the target personnel, obtaining their facial data. Next, based on the target personnel's facial data, the target personnel's historical location can be obtained from a historical location database, and their personnel profile data can be determined based on their historical location. The environmental perception data of the target area can then be determined based on the determined personnel profile data. Thus, through image acquisition and historical data analysis, a more complete user profile can be constructed, improving the accuracy of advertising delivery.

[0041] In this embodiment, based on the real-time location of the target person within the determined target area, a pre-deployed image acquisition device, such as a high-definition camera, can be invoked to acquire image data containing facial features. Then, facial recognition technology can be used to extract facial data representing facial features from the acquired images. This extracted facial data is used as a key identifier and retrieved and matched in a database storing the correspondence between historical location information and facial data to obtain the target person's location data over a historical period. This historical location data is then subjected to in-depth analysis. For example, by analyzing the types of places the person frequently visits, such as gyms, cafes, and high-end shopping malls, their interests and spending power can be inferred; by analyzing their activity patterns, such as commuting time and weekend activity range, their lifestyle can be inferred, ultimately generating user profile data. Because this approach combines the user's long-term interests and behavioral habits, subsequent advertising can better meet the user's needs.

[0042] In one embodiment of this application, such as Figure 1 In the method shown, after determining the environmental perception data of the area to be targeted, the advertising can be targeted to the geographical location based on the target personnel's historical operation data of the advertisement and the environmental perception data.

[0043] In one example, when targeting ads to specific geographic locations, an ad delivery strategy can be determined first based on historical operational data, environmental awareness data, and a pre-trained intelligent decision-making model. This strategy can include at least one of the following: ad content to be delivered, delivery time, and delivery frequency. The intelligent decision-making model can be trained using a deep reinforcement learning algorithm, with ad conversion rate and user dwell time as optimization objectives. Then, ads can be delivered to specific geographic locations according to the ad delivery strategy. This example, by introducing a deep reinforcement learning algorithm, enables the ad delivery strategy to dynamically adapt to environmental changes and user behavior, significantly improving ad effectiveness and resource utilization efficiency.

[0044] The optimization objective of the intelligent decision-making model can be:

[0045] in, It is about finding the optimal strategy. (i.e., the decision-making rules for advertising placement); In strategy The mathematical expectation is used to measure the long-term average performance of the strategy; It represents the cumulative discount reward; T is the upper limit of the time step. It is a discount factor that emphasizes the importance of near-term returns and avoids overemphasis on uncertain long-term returns. Specifically, in setting... When the value is , for promotional ads that aim for immediate conversion, You can set a smaller value to allow the model to focus on short-term clicks and purchase behavior; while for ads aimed at building brand image and cultivating long-term user awareness, Larger values ​​can be set to encourage the model to consider long-term user engagement and brand favorability; It is a state Take action below Instant rewards; It is a variance penalty term. This is a penalty coefficient, used to balance "high expected return" with "low strategy stability," preventing the strategy from becoming overly risky. (In setting...) When the value is [value], different [values] can be observed through offline simulation. To find a variance in the strategy returns under the given conditions. A value that allows the strategy's variance to be significantly reduced within an acceptable range of cumulative return decline (e.g., a decline of no more than 5%). It is a reward The variance.

[0046] Core objective function Decomposed into:

[0047] in, This is the weighting coefficient for conversion rewards; the higher the business priority, the higher the weighting coefficient. The larger the value, the higher the value should be, if the advertiser prioritizes conversion. ; It is an action The number of conversions generated by (such as the placement of an advertisement), for example, when a user clicks on it and completes a purchase / reservation. It is an action The number of times an ad is seen, such as the total number of times the ad is seen by users; It is the advertising conversion rate, which is the core performance indicator; This is the weighting coefficient for dwell time rewards; the longer the user stays, the more important it is. The larger the value, the greater the potential impact; for example, if the brand advertisement emphasizes the depth of user viewing, then increase the value. ; It is a state Next user action The average dwell time, such as the viewing time of video ads and the browsing time of image and text ads; It involves performing a logarithmic transformation on the dwell time to smooth out numerical growth and prevent extreme values ​​from dominating the reward. It is a weighting coefficient for energy consumption penalties; the more sensitive it is to energy consumption, the higher the weighting coefficient becomes. The larger the value, for example, if the power cost of edge nodes is high, then the value should be increased. ; It is an action Energy consumption vectors, such as the power consumption of devices playing advertisements and the computing power consumption of edge computing nodes; It is the L2 norm, which can be used to quantify the overall size of energy consumption and avoid extreme values ​​in a single dimension.

[0048] In the steps described above in this application embodiment, a multi-objective optimization function with ad conversion rate, user dwell time, and system energy consumption as core objectives is first constructed, and the constructed function is used to quantitatively evaluate the intelligent decision-making model. Then, the model is trained using a deep reinforcement learning algorithm, and a discount factor is introduced to dynamically adjust the attention weights of short-term and long-term returns in the model, achieving adaptive optimization for different ad type strategies. Based on this, the volatility of the strategy output is controlled by configuring a variance penalty coefficient to ensure the stability of the delivery effect. Simultaneously, conversion weight, dwell time weight, and energy consumption weight are set to adapt to diverse ad delivery needs. Through the above multi-objective optimization, adaptive training, and stability control mechanisms, an intelligent ad delivery strategy that balances immediate effects, long-term value, and operational efficiency can be generated. This strategy can dynamically adjust ad content, delivery timing, and frequency based on the real-time environment and user status, thereby significantly improving ad conversion rate, user engagement, and overall resource utilization efficiency.

[0049] In this embodiment, firstly, the specific target area is determined by acquiring the geographic location of the advertisement to be placed, providing a location basis for advertisement placement. Then, based on the real-time location information of target users in the target area, environmental perception data is generated. This environmental perception data includes dynamic indicators such as population density, population flow, user profiles, and regional heat, enabling real-time perception of the current scene. Finally, by combining the target users' historical advertising operation data with the environmental perception data, dynamic decisions are made and advertisement placement is executed to ensure that the advertisement content matches the real-time scene and user behavior.

[0050] This application embodiment integrates real-time environmental perception data and historical operation data for ad delivery, which can effectively improve the timeliness and scene adaptability of ad delivery. It enables the delivered ads to dynamically respond to environmental changes, thereby effectively solving the problems of insufficient real-time performance and poor scene adaptability caused by relying on static user profiles, improving ad conversion rate and user dwell time, and reducing ineffective delivery.

[0051] Figure 2 The advertising delivery device 200 shown can achieve Figure 1 The method described in the embodiment achieves the same technical effect, and can be specifically referred to in the above description. Figure 1 The description of the advertising delivery method in the illustrated embodiment will not be repeated here. The advertising delivery device 200 includes:

[0052] The acquisition module 201 is used to acquire the geographic location of the advertisement to be delivered, and determine the delivery area based on the geographic location. The determination module 202 is used to determine the environmental perception data of the area to be deployed based on the location of the target personnel in the area to be deployed; the environmental perception data includes at least one of the following: personnel density data, personnel flow data, personnel profile data, and area heat data of the target personnel. The delivery module 203 is used to deliver advertisements to geographical locations based on the target audience's historical operation data for advertisements and environmental perception data.

[0053] Optionally, the acquisition module 201 is used for: The geographical location of the advertisement to be placed is obtained based on the BeiDou satellite positioning system.

[0054] Optionally, the environmental sensing data includes personnel thermal data, which includes at least one of the target personnel's personnel density data, personnel flow data, and regional heat data; the determining module 202 is used for: Obtain the location of the target personnel in the area to be deployed; The location of the target person is transmitted to a pre-deployed edge computing node via a 5G network, and the edge computing node sends personnel thermal data; the personnel thermal data is obtained by the edge computing node after performing thermal analysis on the location of the target person. Based on the personnel thermal data, the environmental perception data of the area to be deployed is determined.

[0055] Optionally, the computing power allocated to the edge computing node is determined based on the edge computing node's load, available computing power, and the preset task processing priority corresponding to the thermal analysis.

[0056] Optionally, the environmental perception data includes personnel profile data; the determining module 202 is used for: Obtain the location of the target personnel in the area to be deployed; Based on the location of the target person, the corresponding preset image acquisition device is invoked to acquire the image of the target person and obtain the facial data of the target person. Based on the facial data of the target person, the historical location of the target person is obtained from the collected historical location database; Based on the target personnel's historical location, determine the target personnel's profile data; Based on the personnel profile data, the environmental perception data of the area to be deployed is determined.

[0057] Optionally, the delivery module 203 is used for: Based on the historical operation data, the environmental perception data, and the pre-trained intelligent decision-making model, an advertising delivery strategy is determined; the advertising delivery strategy includes at least one of the advertising content to be delivered, the delivery time, and the delivery frequency; the intelligent decision-making model is trained using a deep reinforcement learning algorithm with advertising conversion rate and user dwell time as optimization objectives. According to the advertising strategy, ads are delivered to the specified geographic locations.

[0058] In this embodiment, firstly, the specific target area is determined by acquiring the geographic location of the advertisement to be placed, providing a location basis for advertisement placement. Then, based on the real-time location information of target users in the target area, environmental perception data is generated. This environmental perception data includes dynamic indicators such as population density, population flow, user profiles, and regional heat, enabling real-time perception of the current scene. Finally, by combining the target users' historical advertising operation data with the environmental perception data, dynamic decisions are made and advertisement placement is executed to ensure that the advertisement content matches the real-time scene and user behavior.

[0059] This application embodiment integrates real-time environmental perception data and historical operation data for ad delivery, which can effectively improve the timeliness and scene adaptability of ad delivery. It enables the delivered ads to dynamically respond to environmental changes, thereby effectively solving the problems of insufficient real-time performance and poor scene adaptability caused by relying on static user profiles, improving ad conversion rate and user dwell time, and reducing ineffective delivery.

[0060] Figure 3 This is a schematic diagram of the structure of an electronic device provided in one embodiment of this application. Please refer to it. Figure 3 At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and memory. The memory may include main memory, such as high-speed random-access memory (RAM), or non-volatile memory, such as at least one disk drive. Of course, the electronic device may also include other hardware required for other business operations.

[0061] The processor, network interface, and memory can be interconnected via an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 3 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0062] Memory is used to store programs. Specifically, programs may include program code, which includes computer operation instructions. Memory may include main memory and non-volatile memory, and provides instructions and data to the processor.

[0063] The processor reads the corresponding computer program from non-volatile memory into main memory and then executes it, forming a non-contiguous transfer configuration at the logical level. The processor executes the program stored in memory and specifically performs the following operations: Obtain the geographic location of the advertisement to be placed, and determine the area to be placed based on the geographic location; Based on the location of the target personnel in the area to be targeted, environmental perception data of the area to be targeted is determined; the environmental perception data includes at least one of the following: personnel density data, personnel flow data, personnel profile data, and area heat data of the target personnel. Based on the target personnel's historical operational data regarding the advertisement, and the environmental perception data, the advertisement is delivered to the geographical location.

[0064] The above is as stated in this application. Figure 1The advertising delivery method disclosed in the embodiments described above can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in one or more embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in one or more embodiments of this application can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software module can reside in a mature storage medium in the field, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method.

[0065] The electronic device can also perform Figure 1 The advertising placement method described herein will not be elaborated further in this application.

[0066] This application also proposes a computer-readable storage medium that stores one or more programs, the programs including instructions that, when executed by a portable electronic device including multiple applications, enable the portable electronic device to perform... Figure 1 The methods of the embodiments shown are not described in detail here.

[0067] This application also proposes a computer program product, which is stored in a storage medium and executed by at least one processor to implement... Figure 1 The methods of the embodiments shown are not described in detail here.

[0068] Of course, in addition to software implementation, the electronic device of this application does not exclude other implementation methods, such as logic devices or a combination of hardware and software, etc. In other words, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0069] In summary, the above description is merely a preferred embodiment of this application and is not intended to limit the scope of protection of this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of one or more embodiments of this application should be included within the scope of protection of one or more embodiments of this application.

[0070] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0071] Computer-readable media, including both permanent and non-permanent, removable and non-removable media, can store information using any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined in the embodiments of this application, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0072] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0073] The various embodiments in this application are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

Claims

1. An advertising placement method, characterized in that, The method includes: Obtain the geographic location of the advertisement to be placed, and determine the area to be placed based on the geographic location; Based on the location of the target personnel in the area to be targeted, environmental perception data of the area to be targeted is determined; the environmental perception data includes at least one of the following: personnel density data, personnel flow data, personnel profile data, and area heat data of the target personnel. Based on the target personnel's historical operational data regarding the advertisement, and the environmental perception data, the advertisement is delivered to the geographical location.

2. The advertising placement method according to claim 1, characterized in that, The process of obtaining the geographic location of the advertisement to be delivered includes: The geographical location of the advertisement to be placed is obtained based on the BeiDou satellite positioning system.

3. The advertising placement method according to claim 1, characterized in that, The environmental sensing data includes personnel thermal data, which includes at least one of the target personnel's personnel density data, personnel flow data, and regional heat data. The step of determining the environmental perception data of the area to be deployed based on the location of the target personnel in the area to be deployed includes: Obtain the location of the target personnel in the area to be deployed; The location of the target person is transmitted to a pre-deployed edge computing node via a 5G network, and the edge computing node sends personnel thermal data; the personnel thermal data is obtained by the edge computing node after performing thermal analysis on the location of the target person. Based on the personnel thermal data, the environmental perception data of the area to be deployed is determined.

4. The advertising placement method according to claim 3, characterized in that, The computing power allocated to the edge computing node is determined based on the edge computing node's load, available computing power, and the preset task processing priority corresponding to the thermal analysis.

5. The advertising placement method according to claim 1, characterized in that, The environmental perception data includes personnel profile data; determining the environmental perception data of the area to be deployed based on the location of the target personnel in the area to be deployed includes: Obtain the location of the target personnel in the area to be deployed; Based on the location of the target person, the corresponding preset image acquisition device is invoked to acquire the image of the target person and obtain the facial data of the target person. Based on the facial data of the target person, the historical location of the target person is obtained from the collected historical location database; Based on the target personnel's historical location, determine the target personnel's profile data; Based on the personnel profile data, the environmental perception data of the area to be deployed is determined.

6. The advertising placement method according to claim 1, characterized in that, The step of targeting ads to specific geographic locations based on the target user's historical interaction data with the ads and the environmental awareness data includes: Based on the historical operation data, the environmental perception data, and the pre-trained intelligent decision-making model, an advertising delivery strategy is determined; the advertising delivery strategy includes at least one of the advertising content to be delivered, the delivery time, and the delivery frequency; the intelligent decision-making model is trained using a deep reinforcement learning algorithm with advertising conversion rate and user dwell time as optimization objectives. According to the advertising strategy, ads are delivered to the specified geographic locations.

7. An advertising delivery device, characterized in that, The device includes: The acquisition module is used to acquire the geographic location of the advertisement to be delivered, and determine the delivery area based on the geographic location. The determination module is used to determine the environmental perception data of the area to be deployed based on the location of the target personnel in the area to be deployed; the environmental perception data includes at least one of the target personnel's personnel density data, personnel flow data, personnel profile data, and area heat data; The ad delivery module is used to deliver ads to the target geographic location based on the target user's historical operation data for the ads and the environmental perception data.

8. An advertising delivery device, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store computer-executable instructions that, when executed by a processor, implement the steps of the method described in any one of claims 1 to 6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the steps of the method described in any one of claims 1 to 6.

Images