Advertisement distribution method, medium and equipment

Abstract

The invention relates to an advertisement distribution method, a medium and equipment. The advertisement distribution method comprises the following steps: acquiring putting portraits of candidate advertisements and calling position information and calling time information of a calling party; the delivery portrait comprises any one or more of an industry category, a delivery range and time of a faint season and a peak season; according to the putting portrait, the calling position information and the calling time information, determining a region weight, a time weight and a putting weight of each candidate advertisement; weighting the basic score of each candidate advertisement according to the region weight, the time weight and the putting weight to obtain a matching score of each candidate advertisement; and taking the candidate advertisement corresponding to the highest matching score as a target advertisement, and distributing the target advertisement to a calling party. The problem that in the prior art, accurate matching and playing of advertisements cannot be achieved in the call waiting stage is solved.

Description

Technical Field

[0001] This invention relates to the field of electronic communication technology, and in particular to an advertising distribution method, medium, and device. Background Technology

[0002] With the deep integration of mobile communication and Internet technologies, voice and video calls have become the mainstream means of daily communication for the public. Existing technical solutions mainly fall into two categories: First, based on traditional telecom operators' circuit-switched or VoLTE / VoNR calls, a ringback tone is played during the ringback phase before the call is connected; second, OTT applications, represented by social software (such as WeChat, QQ, etc.), initiate voice or video calls through data channels and complete the ringback notification with a fixed prompt tone pushed locally or by the server before the called party answers.

[0003] In the context of telecom operators, ringback tone technology has evolved into "custom ringback tone" services, allowing users to customize audio content. However, default ringback tones still dominate. Because default ringback tones are monotonous, short in duration, and loop repeatedly, callers are highly focused while waiting for the call to be answered, yet lack effective information input, resulting in a wasted "window" of user time and platform bandwidth resources. Some operators have attempted to embed audio advertisements into ringback tones, but commercialization has been limited by issues such as narrow circuit-switched signaling channel bandwidth, uncontrollable playback duration, coarse user profiling granularity, and the inability to achieve closed-loop statistical analysis of advertising effectiveness.

[0004] In social media scenarios, OTT call ringback tones are entirely controlled by the application layer. Currently, they typically use short, pre-set "beep" or "ding" sounds, or very short clips sent by the server, serving only as reminders and without any content management during the waiting period. Because the ringback tone is extremely short and cannot be extended repeatedly, platforms neither offer personalized ringback settings nor allow third-party content integration, leaving the content and commercial value of the call waiting phase largely untapped. Furthermore, while social applications possess rich user profiles and real-time contextual data, current technical solutions have not yet integrated this advantage with the call waiting scenario, failing to achieve accurate matching and playback of advertisements or personalized content.

[0005] Therefore, how to solve the problem that existing technologies cannot achieve accurate matching and playback of advertisements during the call waiting stage is an urgent technical problem to be solved in this field. Summary of the Invention

[0006] Based on this, the purpose of this application is to provide an advertising distribution method, medium, and device to solve at least one of the technical problems mentioned in the background art.

[0007] Firstly, this application provides an advertising distribution method, including: Obtain the targeting profile of each candidate advertisement, as well as the caller's call location information and call time information; the targeting profile includes any one or more of the following: industry category, targeting scope, peak and off-peak seasons; Based on the target audience profile, call location information, and call time information, determine the geographic weight, time weight, and target audience weight of each candidate advertisement; The matching score of each candidate ad is obtained by weighting the base score of each candidate ad according to the aforementioned regional weight, time weight, and delivery weight. The candidate ad with the highest matching score is selected as the target ad, and the target ad is distributed to the caller.

[0008] Furthermore, the steps of determining the geographic weight, time weight, and delivery weight of each candidate advertisement based on the aforementioned target profile, call location information, and call time information include: The caller's location is determined based on the call location information. If the caller is within the target area of ​​each candidate advertisement, the first regional weight is applied; otherwise, the second regional weight is applied. The first regional weight is higher than the second regional weight. Based on the call time information, determine whether the current time is in the off-season or peak season of each candidate advertisement. If it is in the peak season, it is the first time weight; if it is in the off-season, it is the second time weight. The first time weight is higher than the second time weight. Obtain the average spending per person in each industry category, sort the industry categories according to the average spending per person, and determine the placement weight of each candidate advertisement based on the ranking results; the higher the average spending per person, the higher the placement weight.

[0009] Furthermore, before weighting the base scores of each candidate advertisement according to the aforementioned geographic weight, time weight, and placement weight, the process also includes: Obtain the bids for each candidate ad and perform segmented mapping to determine the base score for each candidate ad.

[0010] Furthermore, after obtaining the matching score for each candidate ad, the following is also included: Obtain the current power consumption of each software on the calling party, and calculate the industry category to which each software belongs, to obtain the total power consumption of the software included in each industry category; The industry categories are sorted according to the total power consumption. Based on the sorting results and the industry category to which each candidate advertisement belongs, the software usage habit weight of each candidate advertisement is determined. The matching scores of each candidate ad are weighted according to the software usage habit weight to obtain the optimized matching score of each candidate ad.

[0011] Furthermore, the step of selecting the candidate ad corresponding to the highest matching score as the target ad includes: Candidate ads are categorized into video candidate ads and audio candidate ads; The video candidate ad and the audio candidate ad corresponding to the highest matching score are obtained respectively, which are the target video ad and the target audio ad.

[0012] Furthermore, the step of distributing the targeted advertisement to the caller includes: Based on the call location information and call time information, the caller's movement speed is obtained, and it is determined whether the movement speed is greater than a set speed threshold. If not, the target video advertisement is distributed to the caller; if so, the target audio advertisement is distributed to the caller.

[0013] Alternatively, the distance between the mobile phone and the human body can be obtained, and it can be determined whether it is greater than a set threshold. If not, the target audio advertisement can be distributed to the caller; if so, the target video advertisement can be distributed to the caller.

[0014] Furthermore, the step of distributing the target video advertisement to the caller also includes: Obtain the device density within a set range centered on the caller, and determine whether the device density is greater than a set density threshold. If yes, play the target video advertisement at a first volume; otherwise, play the target video advertisement at a second volume. The first volume is less than the second volume.

[0015] Furthermore, the step of distributing the target video advertisement to the caller also includes: The system identifies the orientation of the calling terminal. When the terminal is in landscape mode, the target video advertisement is played in landscape mode; when the terminal is in portrait mode, the target video advertisement is played in portrait mode.

[0016] Secondly, this application also provides a computer storage medium storing executable program code; the executable program code is used to execute the advertising distribution method described in any one of the first aspects.

[0017] Thirdly, this application also provides a terminal device, including a memory and a processor; the memory stores program code executable by the processor; the program code is used to execute the advertising distribution method described in any one of the first aspects.

[0018] This invention provides an advertising distribution method, medium, and device. It acquires the placement profile of each candidate advertisement, as well as the caller's location and time information. The placement profile includes any one or more of industry category, placement range, and peak / off-peak season. By simultaneously acquiring multi-dimensional information from both the advertiser and the caller, it provides a rich data foundation for subsequent steps, avoiding the limitations caused by single-dimensional information. Then, based on the placement profile, call location information, and call time information, it determines the geographic weight, time weight, and placement weight of each candidate advertisement. The multi-dimensional information is converted into quantifiable indicator data for horizontal comparison. The basic scores of each candidate advertisement are then weighted according to the geographic weight, time weight, and placement weight to obtain a matching score for each candidate advertisement. By dynamically weighting and correcting the basic scores of candidate advertisements, it avoids single-factor determination, balances regional timeliness and commercial value, and finally selects the candidate advertisement with the highest matching score as the target advertisement, distributing the target advertisement to the caller to complete the advertising delivery and effectively improve the advertising conversion rate. This solves the problem that existing technologies cannot achieve accurate advertising matching and playback during the call waiting stage. Attached Figure Description

[0019] Figure 1 This is a flowchart of an advertising distribution method according to an embodiment of the present invention. Detailed Implementation

[0020] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0021] It should be noted that if the embodiments of the present invention involve directional indications, such as up, down, left, right, front, back, etc., these directional indications are only used to explain the relative positional relationships and movement of the components in a specific posture. If the specific posture changes, the directional indications will also change accordingly. Furthermore, if the embodiments of the present invention involve descriptions such as "first," "second," "S1," "S2," "step one," "step two," etc., these descriptions are for descriptive purposes only and should not be construed as indicating or implying their relative importance, or implicitly indicating the number of technical features indicated or the order of method execution. Those skilled in the art will understand that anything that does not violate the inventive concept and is within the scope of the present invention should be included in the protection scope of the present invention.

[0022] like Figure 1 As shown, the present invention provides an advertising distribution method: S1: Obtain the placement profile of each candidate advertisement, as well as the caller's call location information and call time information; the placement profile includes any one or more of the following: industry category, placement scope, peak and off-peak seasons; Specifically, candidate ads are the advertising content that advertisers determine to continue running. Optionally, but not limited to, before the advertiser runs ads, it involves obtaining a profile of each candidate ad, including industry category, target audience, peak and off-peak seasons, etc., and obtaining the caller's location and call time information from the base station connected to the caller's device via a communication server, providing a data foundation for subsequent steps. Preferably, since users may have set personalized services such as custom ringback tones, before obtaining the profiles of each candidate ad and the caller's location and call time information, it is optional to determine whether the user has set personalized services; if so, subsequent steps are stopped.

[0023] S2: Based on the target audience profile, call location information, and call time information, determine the geographic weight, time weight, and target audience weight of each candidate advertisement; Specifically, but not limited to, the matching degree between each candidate ad and the caller's location and time information can be determined based on information such as industry category, target area, peak and off-peak season. This determines the geographic weight, time weight, and placement weight of each candidate ad. By adjusting the weights, the different focuses of each candidate ad can be given more attention when calculating the matching degree, thereby improving customer conversion efficiency.

[0024] For example, when user A calls user B, user A's call information is sent to the base station. The base station contacts the communication server. While searching for the called user, the server determines whether the called user has customized a personalized ringtone. If the called user has not set a personalized ringtone, the communication server uses the information it can obtain, such as the caller's base station information, regional characteristics, current weather information, and time information, to match the corresponding advertising information. The higher the degree of matching, the higher the weight.

[0025] Suppose a called user has not set a personalized ringtone, and the advertisers are: G1: Food and Beverage Industry; G2: Tourism industry; G3: Education industry; G4: Retail industry; G5: Brand owners.

[0026] After a caller makes a call, the communication server obtains the caller's relevant information. If it's peak season for restaurants, G1 content will be prioritized; if it's peak season for tourism, G2 content will be prioritized; if it's near summer or winter vacation, or other peak season for education, G3 content will be prioritized; if the caller is within the advertising area of ​​a shopping mall or other advertiser, G4 content will be prioritized; if none of these conditions are met, G5 content will be pushed, and so on. As the number of advertisers increases, the content pushed will become more precise and diversified.

[0027] Preferably, the step of determining the geographic weight, time weight, and delivery weight of each candidate advertisement based on the target audience profile, call location information, and call time information includes: S21: Determine whether the caller is within the delivery range of each candidate advertisement based on the call location information. If yes, it is the first regional weight; if no, it is the second regional weight. The first regional weight is higher than the second regional weight. Specifically, since the service range of advertisers is limited—for example, a restaurant in Changsha cannot serve customers in Beijing—advertisers will select a target area before placing an ad to ensure that users who receive the ad can enjoy the advertiser's services. Therefore, it is possible to determine whether the caller is within the target area of ​​each candidate ad based on the caller's location information. If so, it means that the caller can use the advertiser's services promptly if they have the intention to consume after receiving the ad, and the regional weight is the first regional weight. If not, it means that even if the caller has the intention to consume after receiving the ad, they cannot immediately use the advertiser's services, resulting in a significant decrease in advertising effectiveness. However, considering groups such as tourists, it is possible to place a small number of ads outside the target area as well, and the regional weight is the second regional weight. The first regional weight is higher than the second regional weight.

[0028] S22: Determine whether the current time is in the off-season or peak season of each candidate advertisement based on the call time information. If it is in the peak season, it is the first time weight; if it is in the off-season, it is the second time weight. The first time weight is higher than the second time weight. Specifically, because some industries have significant off-seasons or peak seasons, such as tourism and tutoring, and the timing of off-seasons or peak seasons may differ or even be opposite across industries, advertisers will select their off-season and peak season periods before placing an ad. Then, based on the call time information, they will determine whether the current time falls within the off-season or peak season of each candidate ad. If it is the peak season, it means that most users have a strong willingness to consume from the advertiser at this time, and the time weight is the first time weight. If it is the off-season, it means that most users have a low willingness to consume from the advertiser at this time, and the time weight is the second time weight. The first time weight is higher than the second time weight.

[0029] S23: Obtain the average spending per person in each industry category, sort the industry categories according to the average spending per person, and determine the placement weight of each candidate advertisement based on the sorting results; the higher the average spending per person, the higher the placement weight.

[0030] Specifically, since the average spending per person varies across different industries, and a higher average spending per person means a greater profit from a single transaction, prioritizing exposure to industries with high average order values ​​can maximize the expected return on each exposure / call, especially when call volume is limited. Furthermore, advertisers' bid ceilings for leads are significantly higher than those for industries with low average order values. Therefore, it is advisable to obtain the average spending per person for each industry category and rank these categories accordingly. The ranking results determine the placement weight of each candidate ad; the higher the average spending per person, the higher the placement weight, thus maximizing advertising revenue.

[0031] S3: The base scores of each candidate ad are weighted according to the aforementioned regional weight, time weight, and delivery weight to obtain the matching score of each candidate ad; Specifically, the basic scores of each candidate advertisement can be weighted according to the geographical weight, time weight, and placement weight to obtain the matching score of each candidate advertisement, providing a data basis for subsequent determination of target advertisements; the basic scores can be arbitrarily set by those skilled in the art.

[0032] Preferably, the bids of each candidate ad can be obtained and segmented for mapping to determine the base score of each candidate ad, thereby prioritizing the distribution of ads with higher bids to increase ad revenue. For example, the candidate ads can be ranked according to their bids, with the top 10% of candidate ads having a base score of 10, the bottom 10% having a base score of 1, and so on, to obtain the base score of all candidate ads.

[0033] Preferably, after obtaining the matching score of each candidate advertisement, the process also includes: S31: Obtain the current power consumption of each software of the calling party, and count the industry category to which each software belongs, to obtain the total power consumption of the software included in each industry category; S32: Sort the industry categories according to the total power consumption, and determine the software usage habit weight of each candidate advertisement based on the sorting results and the industry category to which each candidate advertisement belongs; S33: The matching scores of each candidate advertisement are weighted according to the software usage habit weight to obtain the optimized matching score of each candidate advertisement.

[0034] Specifically, to improve ad conversion rates, it's possible to obtain users' app usage time to identify their most frequently used apps. However, since apps like Ele.me and Meituan have similar functions but different user preferences lead to varying usage times, it's advisable to categorize each app by industry category to obtain the total power consumption of apps within each category. Then, the industry categories are ranked based on this total power consumption. The higher the total power consumption of apps within each industry category, the higher the user's willingness to spend. Based on the ranking results and the industry category of each candidate ad, the app usage habit weight of each candidate ad is determined. Finally, the matching score of each candidate ad is weighted according to the app usage habit weight to obtain an optimized matching score for each candidate ad, thereby improving user conversion efficiency.

[0035] S4: Select the candidate ad corresponding to the highest matching score as the target ad and distribute the target ad to the caller.

[0036] Specifically, when a candidate ad has the highest matching score, it means that the ad has the highest conversion probability for the caller. Therefore, the candidate ad with the highest matching score can be selected as the target ad and the target ad can be distributed to the caller.

[0037] Preferably, the step of selecting the candidate ad corresponding to the highest matching score as the target ad includes: S41: Divide candidate ads into video candidate ads and audio candidate ads; S42: Obtain the video candidate ad and the audio candidate ad corresponding to the highest matching score respectively, and set them as the target video ad and the target audio ad; Specifically, due to the existence of several different usage scenarios, such as running, walking, and riding in a car, the types of advertisements applicable to each scenario are also different. For example, in the walking scenario, the movement speed is relatively low, so the caller may be staring at the phone screen and waiting for the callee to respond. In this case, video advertisements are more suitable. In the running scenario, the movement speed is relatively fast, and the user needs to pay attention to changes in the surrounding environment at all times, so their attention is distracted. Therefore, audio advertisements can be selected as the main distribution form to adapt to the usage scenario. The video candidate advertisement and the audio candidate advertisement corresponding to the highest matching score can be selected respectively as the target video advertisement and the target audio advertisement.

[0038] Preferably, the step of distributing the target advertisement to the caller includes: S43: Based on the call location information and call time information, obtain the caller's movement speed and determine whether the movement speed is greater than a set speed threshold. If not, distribute the target video advertisement to the caller; if so, distribute the target audio advertisement to the caller.

[0039] Specifically, the caller's movement speed can be obtained based on the call location information and call time information, and it can be determined whether the movement speed is greater than a set speed threshold. If not, it means that the caller is in a relatively safe and slow-changing environment. At this time, the caller's attention is more focused on the mobile terminal. Therefore, the target video advertisement can be distributed to the caller. If yes, it means that the caller may be in a fast-moving scenario such as running or riding in a car. The caller's attention needs to be dispersed in a constantly changing environment. If the caller focuses on the video advertisement on the mobile terminal, it may pose a security risk. Therefore, the target audio advertisement can be distributed to the caller to adapt to the usage scenario.

[0040] S44: Alternatively, obtain the distance between the mobile phone and the human body, determine whether it is greater than a set threshold, if not, distribute the target audio advertisement to the caller, if so, distribute the target video advertisement to the caller; Specifically, due to different calling habits, the calling party's behavior during a call also varies. Some calling parties prefer to stare intently at the screen while waiting for the called party to respond, while others prefer to hold the device to their ear. When the calling party stares intently at the screen, the conversion rate of video ads is much higher than that of audio ads. When the calling party holds the device to their ear, the conversion rate of audio ads is much higher than that of video ads. Therefore, it is possible to obtain the distance between the mobile phone and the human body and determine whether it is greater than a set threshold. If not, it means that the current device is close to the human body. Since the calling party needs to pay attention to whether the called party responds at all times, it is likely that the device is held to the ear. In this case, the target audio ad can be distributed to the calling party to improve the conversion rate. If the device is far from the human body, since the calling party needs to pay attention to whether the called party responds at all times, and the audio cannot be obtained, the device is likely within the calling party's line of sight. In this case, the target video ad can be distributed to the calling party to improve the conversion rate.

[0041] Preferably, the step of distributing the target video advertisement to the caller further includes: S45: Obtain the device density within a set range centered on the caller, determine whether the device density is greater than a set density threshold, if yes, play the target video advertisement at a first volume, if no, play the target video advertisement at a second volume; the first volume is less than the second volume.

[0042] Specifically, since video ads also contain audio content, when confirming the distribution of video ads, the device density within a set range centered on the caller can be obtained. It can be determined whether the device density exceeds a set density threshold. If it does, it indicates the caller is in a public place. In this case, if the ad volume is too loud, it may easily cause a reaction from people outside. If people outside react to the ad volume, it will further lead to the caller's aversion to the ad, or even cause them to actively close the ad, thereby reducing conversion efficiency. Therefore, the target video ad can be played at a first volume. If not, it indicates the caller is in a relatively private place or the surrounding environment is relatively open. In this case, a louder ad volume can actually strengthen the caller's impression of the advertiser. Therefore, the target video ad can be played at a second volume. The first volume is less than the second volume, and the first and second volumes can be arbitrarily set by those skilled in the art.

[0043] Preferably, the step of playing the target video advertisement further includes: S46: Identify the orientation of the calling terminal. When the terminal is in landscape mode, play the target video advertisement in landscape mode; when the terminal is in portrait mode, play the target video advertisement in portrait mode.

[0044] Specifically, due to different usage habits of callers, the hand orientation of the terminal device varies during a call. Optionally, data from devices such as a mobile phone level indicator can be read to identify the caller's terminal orientation. When the terminal is in landscape mode, the target video advertisement is played in landscape mode; when the terminal is in portrait mode, the target video advertisement is played in portrait mode, thus optimizing the caller's viewing experience and improving conversion efficiency.

[0045] For example, after the same advertisement video is edited, different export formats such as 16:9 or 9:16 may be selected during export, resulting in corresponding horizontal and vertical target video advertisements. The appropriate video advertisement format can be selected based on the current orientation of the terminal.

[0046] For example, when a video ad only exists in one export format, you can optionally change the video interface by scaling down, rotating, or other steps to ensure that the video ad is aligned with the current terminal orientation.

[0047] This embodiment presents an advertising distribution method of the present invention. It obtains the placement profile of each candidate advertisement, as well as the caller's location and time information. The placement profile includes any one or more of industry category, placement range, and peak / off-peak season. By simultaneously acquiring multi-dimensional information from both the advertiser and the caller, a rich data foundation is provided for subsequent steps, avoiding the limitations caused by single-dimensional information. Then, based on the placement profile, call location information, and call time information, the geographical weight, time weight, and placement weight of each candidate advertisement are determined. The multi-dimensional information is converted into quantifiable indicator data for horizontal comparison. The basic scores of each candidate advertisement are then weighted according to the geographical weight, time weight, and placement weight to obtain the matching score of each candidate advertisement. By dynamically weighting and correcting the basic scores of candidate advertisements, a single factor is avoided, balancing regional timeliness and commercial value. Finally, the candidate advertisement with the highest matching score is selected as the target advertisement, and the target advertisement is distributed to the caller, completing the advertising placement and effectively improving the advertising conversion rate. This solves the problem that existing technologies cannot achieve accurate matching and playback of advertisements during the call waiting stage.

[0048] On the other hand, the present invention also provides a computer storage medium storing executable program code; the executable program code is used to execute any of the above-described advertising distribution methods.

[0049] On the other hand, the present invention also provides a terminal device, including a memory and a processor; the memory stores program code that can be executed by the processor; the program code is used to execute any of the above-described advertising distribution methods.

[0050] For example, the program code can be divided into one or more modules / units, which are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units can be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the program code in the terminal device.

[0051] The terminal device can be a desktop computer, laptop, handheld computer, or cloud server, etc. The terminal device may include, but is not limited to, a processor and memory. Those skilled in the art will understand that the terminal device may also include input / output devices, network access devices, buses, etc.

[0052] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor.

[0053] The memory can be an internal storage unit of the terminal device, such as a hard drive or RAM. The memory can also be an external storage device of the terminal device, such as a plug-in hard drive, SmartMedia Card (SMC), Secure Digital (SD) card, or Flash Card. Furthermore, the memory can include both internal and external storage units of the terminal device. The memory is used to store the program code and other programs and data required by the terminal device. The memory can also be used to temporarily store data that has been output or will be output.

[0054] The computer storage medium and terminal device described above are created based on the advertising distribution method described above. Their technical functions and beneficial effects will not be elaborated here. The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0055] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these all fall within the protection scope of the present invention. Therefore, the protection scope of this invention patent should be determined by the appended claims.

Claims

1. An advertising distribution method, characterized in that, include: Obtain the target audience profile for each candidate ad, as well as the caller's location and time information; The target profile includes any one or more of the following: industry category, target scope, and peak / off-peak season. Based on the target audience profile, call location information, and call time information, determine the geographic weight, time weight, and target audience weight of each candidate advertisement; The matching score of each candidate ad is obtained by weighting the base score of each candidate ad according to the aforementioned regional weight, time weight, and delivery weight. The candidate ad with the highest matching score is selected as the target ad, and the target ad is distributed to the caller.

2. The method according to claim 1, characterized in that, The steps for determining the geographic weight, time weight, and delivery weight of each candidate advertisement based on the aforementioned target audience profile, call location information, and call time information include: The caller's location is determined based on the call location information. If the caller is within the target area of ​​each candidate advertisement, the first regional weight is applied; otherwise, the second regional weight is applied. The first regional weight is higher than the second regional weight. Based on the call time information, determine whether the current time is in the off-season or peak season of each candidate advertisement. If it is in the peak season, it is the first time weight; if it is in the off-season, it is the second time weight. The first time weight is higher than the second time weight. Obtain the average spending per person in each industry category, sort the industry categories according to the average spending per person, and determine the placement weight of each candidate advertisement based on the ranking results; the higher the average spending per person, the higher the placement weight.

3. The method according to claim 1, characterized in that, Before weighting the base scores of each candidate ad based on the aforementioned geographic weight, time weight, and placement weight, the following is also included: Obtain the bids for each candidate ad and perform segmented mapping to determine the base score for each candidate ad.

4. The method according to claim 1, characterized in that, After obtaining the matching score for each candidate ad, the following is also included: Obtain the current power consumption of each software on the calling party, and calculate the industry category to which each software belongs, to obtain the total power consumption of the software included in each industry category; The industry categories are sorted according to the total power consumption. Based on the sorting results and the industry category to which each candidate advertisement belongs, the software usage habit weight of each candidate advertisement is determined. The matching scores of each candidate ad are weighted according to the software usage habit weight to obtain the optimized matching score of each candidate ad.

5. The method according to claim 1, characterized in that, The steps for selecting the candidate ad with the highest matching score as the target ad include: Candidate ads are categorized into video candidate ads and audio candidate ads; The video candidate ad and the audio candidate ad corresponding to the highest matching score are obtained respectively, which are the target video ad and the target audio ad.

6. The method according to claim 5, characterized in that, The steps of distributing the targeted advertisement to the caller include: Based on the call location information and call time information, the caller's movement speed is obtained, and it is determined whether the movement speed is greater than a set speed threshold. If not, the target video advertisement is distributed to the caller; if so, the target audio advertisement is distributed to the caller. Alternatively, the distance between the mobile phone and the human body can be obtained, and it can be determined whether it is greater than a set threshold. If not, the target audio advertisement can be distributed to the caller; if so, the target video advertisement can be distributed to the caller.

7. The method according to claim 6, characterized in that, The step of distributing the target video advertisement to the caller further includes: Obtain the device density within a set range centered on the caller, and determine whether the device density is greater than a set density threshold. If yes, play the target video advertisement at a first volume; otherwise, play the target video advertisement at a second volume. The first volume is less than the second volume.

8. The method according to claim 7, characterized in that, The step of distributing the target video advertisement to the caller further includes: The system identifies the orientation of the calling terminal. When the terminal is in landscape mode, the target video advertisement is played in landscape mode; when the terminal is in portrait mode, the target video advertisement is played in portrait mode.

9. A computer storage medium, characterized in that, It stores executable program code; the executable program code is used to perform the advertising distribution method according to any one of claims 1 to 8.

10. A terminal device, characterized in that, It includes a memory and a processor; the memory stores program code that can be executed by the processor; the program code is used to perform the advertising distribution method according to any one of claims 1 to 8.

Images