A resource scheduling method and device for sharing a screen and a medium

Abstract

This application discloses a resource scheduling method, device, and medium for shared screens, relating to the fields of multimedia playback and public display technology. The method includes: receiving attribute data of at least one shared screen; discretizing the shared screen into at least one time resource unit according to a preset time granularity, and constructing a screen resource library based on the time resource units and attribute data; using a time-series gap detection algorithm to identify fragmented time resource units with different value levels; responding to a transaction request initiated for a target fragmented time resource unit, executing a differentiated transaction process corresponding to the value level of the target fragmented time resource unit; conducting a compliance review of the submitted target content; updating the status information of the target fragmented time resource unit to indicate that it is occupied; and controlling the target shared screen to play the target content in response to the review being approved and the playback period arriving. This can improve the resource utilization rate of shared screens and meet the needs of more users.

Description

Technical Field

[0001] This application relates to the field of multimedia playback and public display technology, and in particular to a resource scheduling method, device and medium for sharing a screen. Background Technology

[0002] With the acceleration of urbanization, various display screens (hereinafter referred to as "shared screens") have been widely deployed in outdoor and public places, including shopping mall advertising screens, subway signage screens, park information screens, and community announcement screens. However, existing shared screens have the following core problems: 1. Extremely low resource utilization: Most screens are centrally managed by a single organization (such as certain advertising operators or property management companies), and only play fixed advertisements or announcements. A large number of time slots (such as fragmented time slots between advertisements by large companies) are idle, failing to fully realize the value of public resources. 2. Centralized usage rights, failing to meet the needs of SMEs: The right to use the screens is monopolized by large advertisers, who adopt a coarse-grained placement model of "large-amount package deals." SMEs, due to limited funds, cannot afford the high costs and find it difficult to obtain advertising exposure opportunities on public screens. Summary of the Invention

[0003] This application provides a resource scheduling method, device, and medium for shared screens to solve the following technical problem: how to improve the resource utilization of shared screens and meet the needs of more users.

[0004] In a first aspect, embodiments of this application provide a resource scheduling method for a shared screen. The method includes: receiving attribute data of at least one shared screen; discretizing the available time interval of the shared screen into at least one time resource unit according to a preset time granularity, and constructing a screen resource library based on the time resource units and the attribute data; using a time-series gap detection algorithm to analyze the occupied time resource units in the screen resource library to identify fragmented time resource units of different value levels, wherein the fragmented time resource units are time resource units in an idle state; responding to a transaction request initiated by a first user for a target fragmented time resource unit of a target shared screen, executing a differentiated transaction process corresponding to the value level of the target fragmented time resource unit; receiving target content submitted by the first user and associated with the target fragmented time resource unit, and performing a compliance review on the target content; updating the status information of the target fragmented time resource unit to "occupied" upon completion of the differentiated transaction process; and controlling the target shared screen to play the target content upon approval and the arrival of the playback period.

[0005] Secondly, embodiments of this application also provide a resource scheduling device for a shared screen, the device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform a resource scheduling method for a shared screen as described in the first aspect above.

[0006] Thirdly, embodiments of this application also provide a computer storage medium storing computer-executable instructions, which, when executed, implement a resource scheduling method for a shared screen as described in the first aspect above.

[0007] The resource scheduling method, device, and medium for shared screens provided in this application have the following beneficial effects: In this embodiment, at least one shared screen's attribute data can be received. Then, the available time interval of the shared screen is discretized into at least one time resource unit according to a preset time granularity, and a screen resource library is created based on the time resource units and attribute data. A time-series gap detection algorithm is used to determine fragmented time resource units. In response to a transaction request initiated by a first user for a target fragmented time resource unit of a target shared screen, a differentiated transaction process corresponding to the value level of the target fragmented time resource unit is executed. Target content submitted by the first user and associated with the target fragmented time resource unit is received, and the target content undergoes compliance review. Upon completion of the differentiated transaction process, the status information of the target fragmented time resource unit is updated to indicate that it is occupied. Finally, in response to approval and the arrival of the playback period, the target shared screen is controlled to play the target content. Through this method, the value of fragmented time periods can be activated, the utilization rate of shared screens can be improved, the needs of more users can be met, and user satisfaction can be increased. Attached Figure Description

[0008] 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 A flowchart illustrating a resource scheduling method for a shared screen, provided as an embodiment of this application; Figure 2 A schematic diagram of a resource scheduling architecture for a shared screen provided in an embodiment of this application; Figure 3 A flowchart illustrating another resource scheduling method for shared screens provided in an embodiment of this application; Figure 4A flowchart illustrating another resource scheduling method for shared screens provided in this application embodiment; Figure 5 A flowchart illustrating another resource scheduling method for shared screens provided in this application embodiment; Figure 6 This is a schematic diagram of the internal structure of a resource scheduling device for a shared screen, provided in an embodiment of this application. Detailed Implementation

[0009] 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.

[0010] This application provides a resource scheduling scheme for shared screens. The technical solution proposed in this application will be described in detail below with reference to the accompanying drawings.

[0011] Figure 1 This document provides a flowchart of a resource scheduling method for shared screens, as illustrated in an embodiment of this application. This method can be applied to commercial operating platforms, such as… Figure 1 As shown in the figure, the resource scheduling method for a shared screen provided in this application embodiment specifically includes the following steps: Step 101: Receive attribute data for at least one shared screen.

[0012] In practical applications, shared screens can be any type of display screen that is widely deployed in outdoor and public places, including shopping mall advertising screens, subway signage screens, park information screens, community announcement screens, etc., without specific limitations. The attribute data of a shared screen can include its identity and capability information.

[0013] Shared screens can be broadly categorized into three types. The first type is a regular screen, which is a traditional display device without intelligent processing capabilities. It can achieve network connectivity and identity verification by adding a "network adaptation module + identity recognition module" (such as a network card with a built-in MAC address), and support receiving advertising playback instructions from the operating platform. The second type is a smart screen, which is a terminal with independent network connectivity and data processing capabilities. It has a built-in identity identifier (such as a unique device ID) and supports direct communication with the operating platform, enabling functions such as advertising content caching, playback status feedback, and e-commerce page display. The third type is a smart screen with a camera. It can add an AI visual recognition module and an interactive sensing module (such as a gesture recognizer) to the smart screen, supporting facial / human feature recognition and gesture operation, thereby triggering functions such as "targeted advertising playback" and "interactive product selection".

[0014] Step 102: Discretize the available time interval of the shared screen into at least one time resource unit according to a preset time granularity, and construct a screen resource library based on the time resource unit and the attribute data.

[0015] In practical applications, shared screens are generally not used 24 / 7. For example, shared screens in shopping malls are only used during the mall's business hours. In this embodiment, the available time interval of each shared screen can be discretized into multiple time resource units with a unified format according to a preset time granularity, and a screen resource library can be constructed based on the time resource units and attribute data. In this way, discretization converts continuous time intervals into discrete units, significantly reducing data storage volume. Moreover, the screen resource library constructed based on time resource units can support multi-dimensional retrieval by time, shared screen, etc., improving resource search efficiency and resource management efficiency. Furthermore, this allows for rapid updates to the availability status of screen resources, which is helpful for screen resource management.

[0016] In practical applications, when constructing a screen resource library based on time resource units and attribute data, a corresponding resource record can be built for each time resource unit. This resource record can include the attribute data of the shared screen corresponding to that time resource unit and the status information of that time resource unit. In this way, multiple resource records can be used to construct a screen resource library. Other methods can also be used, and there are no specific restrictions.

[0017] Step 103: Use the time gap detection algorithm to analyze the occupied time resource units in the screen resource library in order to discover fragmented time resource units with different value levels.

[0018] The fragmented time resource unit is a time resource unit that is in an idle state.

[0019] In practical applications, the reason for not directly querying idle time is that a direct query yields a raw, undifferentiated dataset, but the value of different time periods varies. It's impossible to automatically assess the inherent commercial value differences between different idle periods, leading to difficulties in subsequent pricing. Furthermore, it cannot automatically match differentiated sales strategies (such as fixed prices versus bidding) to different resources; the entire transaction process relies on manual decision-making, making scalable and programmatic trading impossible.

[0020] In this embodiment, a time gap detection algorithm can be used to analyze the occupied time resource units in the aforementioned screen resource library to identify fragmented time resource units. By using the time gap detection algorithm, fragmented resources with different value levels (such as high-value fragments and low-value fragments) can be identified and classified. This enables automated routing and decision-making in the transaction process, improving transaction efficiency and resource utilization.

[0021] For example, gaps in large enterprise package orders (such as important customer A package until 24:00 on Sunday, important customer B package starting from 1:00 on Monday, with the 0:00-1:00 interval being a fragmented period) can be identified and determined to be high-value fragments.

[0022] Step 104: In response to a transaction request initiated by the first user for a target fragmented time resource unit of the target shared screen, execute a differentiated transaction process corresponding to the value level of the target fragmented time resource unit.

[0023] In practical applications, different fragmented time resource units correspond to different value levels. For example, the value level of a certain time slot in a shopping mall at noon is different from the value level of a certain time slot on a community bulletin board at noon. Different value levels of fragmented time resource units correspond to different application processes. For instance, some fragmented time resource units with lower value levels can be applied for directly by the first user (e.g., small and medium-sized merchants or ordinary users), while some fragmented time resource units with higher value levels can be acquired by the first user (e.g., small and medium-sized merchants or ordinary users) through bidding. In this way, a differentiated transaction process can be executed according to the value level of the fragmented time resource unit requested by the first user, which can fully utilize the value of shared screens and improve user satisfaction.

[0024] Step 105: Receive the target content submitted by the first user that is associated with the target fragmented time resource unit, and conduct a compliance review on the target content.

[0025] In this embodiment, the system can receive target content submitted by a first user that is associated with the aforementioned target fragmented time resource unit, and conduct a compliance review of the target content. Through this compliance review, it can automatically or manually detect whether the target content contains sensitive information, preventing the spread of illegal content on shared screens, protecting user rights and platform reputation, meeting industry regulatory requirements, and conveying the platform's emphasis on content security to users through a rigorous review process, thereby enhancing user trust in the platform and promoting long-term cooperation.

[0026] In practical applications, upon receiving an application, a multi-layered content review process can be initiated. Automated review can begin, using image recognition (e.g., filtering inappropriate images), text recognition (e.g., detecting sensitive words and false advertising terms), and audio recognition (e.g., screening for inappropriate audio) technologies to identify non-compliant content. Automated review typically completes within 10 seconds. Questionable content is then transferred to manual review; for content questioned by automated review (e.g., blurry images, ambiguous statements), reviewers complete a secondary confirmation within 5 minutes. Industry compliance databases can also be accessed, containing built-in advertising compliance rules for various industries (e.g., the food industry cannot advertise "medicinal effects"), allowing for targeted review of specific content. Upon approval, a "approved" notification can be sent to the first user. If the review fails, the reason for the violation can be provided (e.g., "contains false advertising terms"). A violation application log is also recorded for regulatory authorities and operators to access. This ensures the legality and compliance of advertising content while balancing review efficiency and commercial timeliness.

[0027] Step 106: Upon completion of the differentiated transaction process, update the status information of the target fragmented time resource unit to indicate that it has been occupied.

[0028] In this embodiment of the application, once the differentiated transaction process is completed, the status information of the target fragmented time resource unit can be updated to indicate that it has been occupied. This avoids secondary transactions and ensures the service quality for the first user.

[0029] Step 107: In response to the approval and the arrival of the playback period, control the target shared screen to play the target content.

[0030] In practical applications, ad playback instructions (including content address, playback duration, mode, etc.) can be sent to the target shared screen to ensure timely and accurate ad delivery. If the first user uploads the video themselves, the video can be packaged and sent to the target shared screen. In this way, once the target content is approved and the playback time arrives, the target shared screen can be controlled to play the target content, ensuring that user needs are met and delivery is completed.

[0031] In this embodiment, at least one shared screen's attribute data can be received. Then, the available time interval of the shared screen is discretized into at least one time resource unit according to a preset time granularity, and a screen resource library is created based on the time resource units and attribute data. A time-series gap detection algorithm is used to determine fragmented time resource units. In response to a transaction request initiated by a first user for a target fragmented time resource unit of a target shared screen, a differentiated transaction process corresponding to the value level of the target fragmented time resource unit is executed. Target content submitted by the first user and associated with the target fragmented time resource unit is received, and the target content undergoes compliance review. Upon completion of the differentiated transaction process, the status information of the target fragmented time resource unit is updated to indicate that it is occupied. Finally, in response to approval and the arrival of the playback period, the target shared screen is controlled to play the target content. Through this method, the value of fragmented time periods can be activated, the utilization rate of shared screens can be improved, the needs of more users can be met, and user satisfaction can be increased.

[0032] In one possible implementation, the use of a time gap detection algorithm to analyze the occupied time resource units in the screen resource library to identify fragmented time resource units of different value levels includes: Using a time gap detection algorithm, fragmented time resource units between adjacent occupied time resource units in the screen resource library are identified; For each fragmented time resource unit, a value score is calculated based on the length of the fragmented time resource unit, the attribute data of adjacent time resource units and the corresponding shared screen. The value level of the fragmented time resource unit is determined based on the range in which the value score falls.

[0033] In practical applications, when using a time gap detection algorithm to identify fragmented time resource units between adjacent occupied time resource units in the aforementioned screen resource library, the time range of all occupied time resource units can be obtained, sorted chronologically, and then fragmented time resource units can be identified one by one. When calculating the value score of fragmented time resource units, a formula can be used. For example, the calculation formula can be: S=α*F duration(D) +β*F timing(T) +γ*F neighbor(N_prev,N_next) +δ*F screen(P) +ε*F dynamic(C) Where S is the final value score; F duration(D)The length factor is determined based on the length D of the aforementioned fragmented time resource unit (the value is assigned based on the length of the fragmented time resource unit; generally, if it is too long or too short, the value is low); F timing(T) The time factor is determined based on the starting time T (higher values ​​correspond to morning and evening peak hours); F neighbor(N_prev, N_next) The neighbor value factor is determined based on the tenant value levels (N_prev and N_next) of adjacent time resource units; F screen(P) F is the location-level attribute factor determined based on the location P of the shared screen (shared screens in better locations have higher values); dynamic(C) The environmental factors are determined based on the predicted environment (the environment can be weather or pedestrian traffic; higher pedestrian traffic results in larger values); α, β, γ, δ, and ε are the weight coefficients corresponding to each factor, and α+β+γ+δ+ε=1.

[0034] In practical applications, when calculating the value score of fragmented time resource units, a scoring model (a machine learning model) can also be used. This model collects fragmented time resource units that have been sold in historical transactions, along with their corresponding feature data and transaction price data, as training samples. The goal is to minimize the error between the predicted price and the actual transaction price. The parameters of the scoring model are then trained to obtain a well-trained model. Finally, the length of the fragmented time resource unit, the attribute data of adjacent time resource units, and the corresponding shared screen are input into the scoring model to obtain the value score.

[0035] Both of these methods eliminate the need for manual scoring of fragmented time resource units, saving time. After obtaining a value score, the value level of the fragmented time resource unit can be determined based on the range in which the score falls. The mapping relationship between the range and the value level can be determined according to the actual situation. This allows for a more accurate determination of the value level of fragmented time resource units.

[0036] In one possible implementation, the step of executing a differentiated transaction process based on the value level corresponding to the target fragmented time resource unit includes: If the value level is higher than or equal to the bidding threshold, a bidding process based on the starting price is initiated for the target fragmented time resource unit. If the value level is lower than the bidding threshold, a fixed price is provided for the target fragmented time resource unit for the first user to purchase directly.

[0037] In practical applications, a value level higher than or equal to the bidding threshold indicates that the target fragmented time resource unit has high value, and a bidding process can be initiated to obtain greater benefits. Conversely, a value level lower than the bidding threshold indicates that the target fragmented time resource unit has average value, and a fixed price can be offered. These starting and fixed prices can be set by the operator or obtained through a pricing model. Thus, by providing corresponding application processes for target fragmented time resource units with different value levels, users can optimize their advertising budget allocation, reduce customer acquisition costs, and ultimately improve user satisfaction.

[0038] In one possible implementation, the starting price is obtained in the following way: The value level, duration, tenant value level of adjacent time resource units, and attribute data of the target shared screen are input into the starting price pricing model to obtain the starting price of the target fragmented time resource unit output by the pricing model. The bidding process includes: Obtain the bidding request from the first user, wherein the bidding request carries a price higher than the starting price; In response to the end of the bidding period and the first user being the highest bidder, a funding instruction is issued to the first user, wherein the funding instruction is used to instruct the first user to pay funds; A review instruction is issued to the first user, wherein the review instruction is used to instruct the first user to upload target content.

[0039] In the above embodiments, the starting price of the target fragmented time resource unit can be obtained through a starting price pricing model. In practical applications, pricing can also be set by enterprises, without specific restrictions. Simultaneously, a bidding process can be provided to the first user based on the aforementioned starting price.

[0040] In practical applications, the value level and duration of the target fragmented time resource unit, the tenant value level of adjacent time resource units, and the attribute data of the target shared screen can be input into a fixed-price pricing model to obtain a fixed price corresponding to the target fragmented time resource unit. This method yields a more reasonable price, helps stimulate users' purchasing desire, and avoids excessively high pricing that could reduce user willingness to buy.

[0041] In practical applications, users can be provided with a variety of modes to choose from, such as full-screen playback, interstitial playback, loop playback, and playback frequency (e.g., interstitial playback every 10 minutes), which can better meet the needs of users.

[0042] In a possible implementation, after controlling the target shared screen to play the target content in response to successful review and arrival of the playback period, the method further includes: Obtain product information sent by an e-commerce platform; Display interaction elements associated with the product information on the shared screen; In response to a second user scanning the interaction element via a mobile terminal or selecting the interaction element via a gesture, guide the second user to a transaction page related to the product information.

[0043] In practical applications, in addition to meeting the needs of users who want to share content via a shared screen, the needs of users passing by the shared screen can also be met. For example, cooperation can be carried out with an e-commerce platform to display product information on the e-commerce platform during the idle period of the shared screen so that passing users can directly conduct transactions via the shared screen, which can not only improve the utilization rate of the shared screen but also meet the needs of this part of users. In the above embodiments, docking can be performed with mainstream e-commerce platforms (such as food delivery platforms and local life platforms) and the enterprise's own e-commerce system to synchronize product information (such as food and beverage packages and daily necessities); at the same time, e-commerce scenarios can be customized for screens in different venues (such as pushing outdoor supplies on park screens, pushing food and beverage packages on screens at the entrance of restaurants, and pushing travel services on subway station screens); after the user completes the transaction, the order information is synchronized to the commercial operation platform in real time to provide a basis for commission settlement. In this way, additional revenue can also be generated for the operator.

[0044] In practical applications, when customizing e-commerce scenarios for screens in different venues, the geographical location information of the shared screen can be obtained, and based on the geographical location information, a preset scenario classification database is queried to map the above shared screen to at least one predefined venue scenario category, and the venue scenario category at least includes a park leisure scenario, a food and beverage consumption scenario, and a transportation scenario.

[0045] Then, in response to the shared screen being mapped to a specific venue scenario category, a set of candidate products with a high degree of association with the above specific venue scenario category is screened out from the e-commerce product library; if the venue scenario category is a park leisure scenario, at least one of outdoor sports supplies, picnic utensils, children's toys, and beverages is screened out; if the venue scenario category is a food and beverage consumption scenario, at least one of food and beverage packages, vouchers, and food delivery services is screened out; if the venue scenario category is a transportation scenario, at least one of taxi coupons, shared bicycle services, travel tickets, and convenience store products is screened out.

[0046] Subsequently, the available fragmented time resource units of the shared screen can be identified; then, at least one candidate product from the candidate product set is bound to the available fragmented time resource unit to generate a delivery task; finally, during the playback period corresponding to the fragmented time resource unit, the shared screen is controlled to play the advertising content corresponding to the candidate product, and interactive elements to guide users to complete the transaction are displayed in the advertising content. This allows for more precise delivery of e-commerce content.

[0047] In one possible implementation, the method further includes: The screen resource library is analyzed, and multiple different fragmented time resource units are clustered and combined into at least one spatiotemporal combination based on geographical proximity and temporal proximity. By analyzing the value of the spatiotemporal combination, the combination price of the spatiotemporal combination is determined; Based on the first user's historical targeting preferences and search behavior, a target spatiotemporal combination is recommended to the first user.

[0048] In practical applications, the screen resource library can be automatically analyzed to intelligently package fragmented resources from the same area, different screens, and adjacent time periods (e.g., "screens A, B, and C in a shopping mall, during the 7:00-7:15 time slot tonight"), forming a spatiotemporal combination with wider coverage and longer duration. It should be noted that the combined price of the spatiotemporal combination is not simply the sum of the prices of the fragmented time resource units, but requires comprehensive consideration of multiple factors. In the above embodiment, the value of the spatiotemporal combination can be analyzed to obtain its combined price. For example, the additional coverage increase and brand exposure synergy brought by packaging can be analyzed, and a preferential package price can be calculated using a pricing model to stimulate user purchases. Alternatively, based on the value of each fragmented time resource unit, a weight can be assigned to each fragmented time resource unit, and then a combined price can be calculated by adding the product of the prices of each fragmented time resource unit and its weight; no specific restrictions apply. Finally, based on the first user's historical targeting preferences (such as location, time of day, and target audience) and search behavior, we can proactively push target time and space combinations to the first user, i.e. packages that the first user is likely to be interested in. This can improve the first user's satisfaction.

[0049] In one possible implementation, after the differentiated transaction process is completed and the status information of the target fragmented time resource unit is updated to indicate that it is occupied, the method further includes: Monitor the status of the target time resource unit that is about to reach its playback period; If the target time resource unit becomes idle within a first preset time period before the start of the playback period, a fast bidding process with a duration of a second preset time is initiated, wherein the second preset time is shorter than the first preset time. Once the process is complete, a playback command is sent to the target shared screen via the edge node network.

[0050] In practical applications, within a confirmed playback schedule, a very short "sudden idle time" may occur before the start of the broadcast due to last-minute cancellations by clients or content failures in the review process. For example, if a user wants to propose using a target time slot, but encounters unforeseen problems (such as sudden heavy rain) that prevent the scheduled event from proceeding, the order is typically cancelled, leaving the target time slot idle. In this case, a rapid bidding process can be initiated for the target time slot. For instance, if screen A becomes idle N minutes (e.g., 30 minutes) before the start of playback, an emergency auction can be held. The bidding period is short (e.g., 5 minutes), content review is extremely simple (only comparing pre-reviewed materials or using templates), and payment locks the slot. After winning the bid, the playback instructions and content are sent directly to the screen via the edge network to ensure on-time broadcast.

[0051] In practical applications, some users may want to advertise on shared screens, such as a restaurant owner who wants to promote their business, but they may not have specific ideas about the screen location or time of day and their willingness to purchase is not strong. In this case, targeted recommendations can be made to these users to improve the utilization rate of shared screens and meet the needs of more users.

[0052] In one possible implementation, prior to responding to a transaction request initiated by a first user for a target fragmented time resource unit of the target shared screen, the method further includes: Obtain the first user's advertising needs information, wherein the advertising needs information includes the target geographic area, target audience attributes, marketing objectives, and budget constraints; Based on the target geographical region, candidate fragmented time resource units located within the target geographical region are selected from the screen resource library; Based on the target audience attributes, candidate fragmented time resource units with a potential audience distribution matching degree greater than a preset threshold are selected from the candidate fragmented time resource units. The potential audience distribution is predicted by the scene audience model based on the shared screen of the candidate fragmented time resource units and the time information of the candidate fragmented time resource units. Based on the aforementioned marketing objectives, at least one of the following should be selected as the optimization objective: maximizing exposure, maximizing audience matching, and minimizing cost. Based on the optimization objective, an objective function is constructed, and with the budget constraint as the constraint condition, at least one recommended fragmented time resource unit is selected from the candidate fragmented time resource units to construct a set of recommended solutions. The recommended scheme set is pushed to the first user.

[0053] In the above embodiments, to address the issue of unclear user goals, a set of recommended solutions can be pushed to the user based on their advertising needs information, allowing the user to choose from them. At this point, the advertising needs information of the first user can be obtained, enabling targeted recommendations.

[0054] Next, candidate fragmented time resource units located within the target geographical area are selected from the screen resource library. It should be noted that these candidate fragmented time resource units must be in an idle state. In practical applications, offline content delivery, especially advertising for small and medium-sized businesses, is essentially regional marketing. Users require advertising in specific areas, making geographical location the primary and rigid constraint. The aforementioned target geographical area can be selected through administrative regions, map selection, or input of a center point and radius, etc., with no specific restrictions. During the selection process, the location information of the shared screens associated with each fragmented time resource unit in the screen resource library can be compared with the aforementioned target geographical area. Those located within the target geographical area are selected as candidate fragmented time resource units.

[0055] If the first user does not explicitly specify a target geographic area, at least one alternative geographic area can be recommended to the first user based on at least one of the following: their industry, historical campaign data, target audience attributes, and marketing objectives, so that the first user can choose a target geographic area. During the filtering process, the scope can be further narrowed based on marketing objectives. For example, if the marketing objective is exposure, shared screens near landmark buildings can be prioritized; if the marketing objective is promotion and traffic generation, shared screens at the entrances of shopping malls or supermarkets can be prioritized.

[0056] In the above embodiments, candidate fragmented time resource units with a potential audience distribution matching degree greater than a preset threshold can be selected from the candidate fragmented time resource units based on the target audience attributes. The essence of the above scene audience model is that, given a specific shared screen and time period, the scene audience model can output the probability of the population profile that may see the target content, i.e., the potential audience distribution. For example, the first user sets the target audience attributes (such as "office worker"). The scene audience model M can be called on the candidate fragmented time resource units Ri (corresponding to shared screen Si and time Ti) obtained through the target geographical location selection to obtain the predicted potential audience distribution (audience distribution vector Di=M(Si,Ti)). For example, Di={"office worker":0.7, "student":0.1,...}. Then, the matching degree Scorei between the target audience attribute vector T (such as {"office worker":1}) corresponding to the target audience attribute and each predicted distribution Di is calculated. A simple method is to take the probability value of the target audience category in Di (such as the probability value of 0.7 for the "office worker" category in the above example, which can be used as the matching degree). Alternatively, the cosine similarity between the target audience attribute vector and the potential audience distribution vector can be calculated and used as the matching degree; there are no specific restrictions.

[0057] Then, based on marketing objectives, at least one of the following can be selected as an optimization goal: maximizing exposure, maximizing audience relevance, and minimizing cost. Subsequently, an objective function is constructed based on these optimization goals, and with the aforementioned budget constraint as a condition, at least one recommended fragmented time resource unit is selected from the candidate fragmented time resource units to construct a recommendation scheme set. Finally, the recommendation scheme set is pushed to the first user. Through this method, precise recommendations can be made according to the user's advertising needs, making it easier for the user to choose. This not only helps improve the utilization rate of shared screens but also increases user satisfaction.

[0058] In practical applications, the aforementioned recommendation scheme set, in addition to information on each recommended fragmented time resource unit (associated shared screens, time periods, etc.), can also include traffic flow data obtained from traffic flow prediction for each recommended fragmented time resource unit. For example, various data from the recommended fragmented time resource unit can be input into a traffic flow prediction model to obtain predicted traffic flow data. Alternatively, historical traffic flow data can be included. This helps users understand approximately how many people will see the content delivered in that recommended fragmented time resource unit, aiding in decision-making.

[0059] To provide a more detailed explanation of the resource scheduling of the shared screen in the embodiments of this application, the following supplementary descriptions are also provided in the embodiments of this application: Figure 2This application provides an architecture for executing the resource scheduling method for shared screens in one application scenario. This architecture is clearly divided into a terminal layer and a platform layer. The terminal layer includes: shared screen terminals, further subdivided into: ordinary screens, smart screens, and smart screens with cameras; user terminals; monitoring terminals; and an e-commerce platform. The platform layer, namely the business operation management platform, is specifically subdivided into seven core functional modules, corresponding to the technical solution. These modules include: an identification and registration module; an SME advertising application module; a multi-layer content review module; a time-slot bidding module; an intelligent playback control module; an interactive e-commerce module; and a fine-grained billing and commission module. The shared screen terminals connect to the platform via network communication; user terminals access the platform services via QR code scanning / APP access; monitoring terminals access the platform through compliance supervision; and the e-commerce platform connects to the targeted interactive e-commerce module via an interface, resulting in more precise logic.

[0060] In practical applications, the identification and registration module can be responsible for the identity identification and unified registration of shared screens. It supports multiple identification methods and provides a precise positioning foundation for commercial scenarios. These methods can be visual identification: displaying a unique QR code on the screen (including device ID, location, and commercial value level); location identification: integrating a Beidou / GPS positioning module to obtain the screen's physical coordinates and supporting filtering by region; or hardware identification: reading the screen's MAC address, unique device ID, and other hardware identifiers. Registration information can include the screen type, location, region, network information, available time period (including fragmented time periods after large enterprises have booked segments), hardware capabilities, and commercial value level (e.g., S-level for a core area, C-level for a residential community entrance), forming a "screen resource library" that can be accessed by small and medium-sized enterprises.

[0061] Meanwhile, the SME advertising application module provides SMEs with a granular and personalized advertising application portal; the multi-layered content review module ensures the legality and compliance of advertising content, balancing review efficiency with commercial timeliness; the time-slot bidding module can build a bidding mechanism for fragmented time slots of high-value screens (such as one hour of free time after a large enterprise has booked a segment), maximizing value; the intelligent playback control module enables precise push of advertising content and playback status management, adapting to the needs of commercial scenarios. This module can send advertising playback instructions (including content address, playback duration, and mode) to the target shared screen, ensuring timely and accurate delivery; it can also receive the playback status of the target shared screen in real time (such as whether it is online, playback completion rate, and whether it is blocked), generating an "ad placement report" to provide feedback to enterprise users; and it can support automatic switching between "ad playback - default recovery" (after use, the screen reverts to the original large enterprise advertisement or public service announcement); the interactive e-commerce module can help upgrade shared screens from "information display" to "transaction conversion," generating revenue for operators; and the granular billing and commission module enables diversified commercial monetization, protecting the interests of operators and partners.

[0062] In practical applications, the above-mentioned fine-grained billing and commission module can be used for advertising billing. Advertising billing includes basic billing (priced according to the commercial value level of the screen, usage time, and playback mode (e.g., 500 yuan for 10 minutes of full-screen playback on an S-level screen, and 50 yuan for 10 minutes of interstitial playback on a C-level screen)) and auction billing, which is settled according to the transaction price, with the operator taking a fixed percentage service fee (e.g., 10%).

[0063] The aforementioned granular billing and commission module also allows for e-commerce commission payments, distributing commissions to operators based on a pre-agreed percentage of the transaction amount (e.g., 5% for restaurant orders, 3% for daily necessities orders), with support for customizable commission rates. Payment methods include corporate bank transfers and corporate payments, as well as prepaid and monthly packages (e.g., a "1000 RMB monthly advertising package for SMEs"). This module also manages billing, generating detailed invoices (including ad placement periods, screen information, cost details, and commission amounts) for reconciliation between enterprise users and operators. Furthermore, the module facilitates revenue sharing settlements: periodically settling accounts with e-commerce platforms and screen owners, automatically generating settlement reports.

[0064] It should be noted that the above-mentioned structure of the business operation management platform is only an example. In actual application, the specific structure can be determined according to the actual situation.

[0065] In practical applications, SMEs can access the shared screen via computer web pages and mobile apps / mini-programs. Functions include: querying screen resources, submitting advertising applications, uploading customized content, participating in time-slot bidding, paying fees, viewing campaign reports, and reconciling accounts. Consumers can interact with the shared screen by scanning a QR code with their mobile phones to perform operations such as product inquiries, order placement and payment, and receiving coupons.

[0066] In practical applications, the monitoring terminal is a dedicated interface that government regulatory departments, street offices, and other agencies can access to view the advertising content, playback history, and transaction data of shared screens within their jurisdiction in real time. They can also initiate emergency removal orders (such as forcibly stopping playback when illegal advertisements are discovered). E-commerce platforms can connect to the business operation management platform via API interfaces to provide services such as product information, order management, and payment settlement, sharing e-commerce revenue with operators. Shared screens can communicate with the business operation platform through existing networks (such as operator 4G / 5G, LAN, and WiFi), without the need for additional dedicated network deployment; and advertising content and e-commerce pages are pre-cached locally on the screen to avoid network interruptions affecting playback and transactions.

[0067] Figure 3 This is a flowchart illustrating a resource scheduling method for shared screens in an application scenario provided by an embodiment of this application. Figure 3 As shown, the resource scheduling method for shared screens in this application embodiment, in the context of fine-grained advertising placement for small and medium-sized enterprises, may include the following steps: Step 301: Small and medium-sized enterprise users log in to the platform to query resources.

[0068] Step 302: Filter the target screen time period pattern.

[0069] Step 303: Upload ad content or use a template.

[0070] Step 304: Submit the application and pay the fees.

[0071] Step 305: Automatically review whether the application is approved.

[0072] If the application passes, step 3061 can be performed to manually review the questionable content.

[0073] If approved, step 3062 can be executed to provide feedback on the reason for the violation and refund the fee.

[0074] Step 307: Verify whether the application passes.

[0075] If successful, proceed to step 308 to lock the screen and issue a command.

[0076] If the above steps fail, step 3062 can be performed.

[0077] Step 309: Target screen sharing to play advertisements.

[0078] Step 310: Real-time feedback on playback status.

[0079] Step 311: Generate a report and send it to the enterprise.

[0080] To illustrate the above steps in more detail, the following example demonstrates a fine-grained advertising campaign for small and medium-sized enterprises (SMEs). A small restaurant (SME user) wants to advertise a "20% off lunch" promotion on a regular screen at the entrance of an office building elevator, with a budget of 500 yuan. The user can search for "XX office building elevator screen" through the app, filter for the available time slot (30 minutes) from 11:00 AM to 12:00 PM today, with a commercial value level of B, and a price of 200 yuan / 30 minutes. The user can choose the "interlude mode" (interlude once every 10 minutes, 30 seconds each time), use the platform template to generate a promotional ad image, submit an application and pay 200 yuan. The system automatically reviews the ad content (no violations) and approves it within 10 seconds. From 11:00 AM to 12:00 PM, the screen plays the promotional ad according to the set mode. After the playback ends, the user receives a "Platform Report": 6 plays, reaching approximately 500 people, 30 coupons claimed. The operator pays a share to the screen owner, retains the service fee, and realizes profit.

[0081] Figure 4 This is a flowchart illustrating a resource scheduling method for shared screens in an application scenario provided by an embodiment of this application. Figure 4 As shown, the resource scheduling method for shared screens in this application embodiment, in a bidding scenario for fragmented high-value screen time periods, may include the following steps: Step 401: Automatically identify fragmented time periods after large enterprises have taken over a segment.

[0082] Step 402: Mark the bidding period and set the starting price / bidding cycle.

[0083] Step 403: Small and medium-sized enterprises focus on the target time period and participate in the bidding.

[0084] Step 404: The system updates the bidding status in real time and processes bid requests in parallel.

[0085] Step 405: Has the bidding period ended?

[0086] If the bidding period ends, step 406 can be executed to determine the highest bidder and lock the time period.

[0087] Step 406: Determine the highest bidder and lock in the time period.

[0088] Step 407: Notify the successful bidder to pay the final payment.

[0089] Step 408: The company uploads the advertising content and submits it for review.

[0090] Step 409: Multi-layered content review.

[0091] Step 410: Check if the review is approved.

[0092] If the review is approved, step 4111 can be executed to issue a playback command, and the bidding advertisement will be played on the screen.

[0093] If the review fails, step 4112 can be executed to cancel the transaction qualification and refund the deposit.

[0094] After step 4111, step 412 can be executed, playback ends, and a bidding report is generated.

[0095] Step 413: The platform deducts a service fee and settles with the operator.

[0096] To illustrate the above steps in more detail, the following example illustrates a high-value screen fragmented time slot bidding scenario. An operator leases a Class S smart screen at the entrance of a park to large company A, with playback time from Sunday 00:00 to 24:00. Large company B leases the screen from Monday 1:00 to 24:00, with the 0:00-1:00 period considered a fragmented time slot. This time slot is marked as a "bidding period," with a starting bid of 10 yuan / minute (600 yuan / hour in total). A small-to-medium-sized cosmetics company (targeting young women) notices this time slot, participates in the bidding, and ultimately wins the bid at 1500 yuan / hour. The system approves the beauty advertisement uploaded by the company, and it plays in full screen from Sunday 0:00 to 1:00. After the playback ends, the system can push a report to the company and settle the service fee with the operator, increasing the operator's revenue by 1500 yuan compared to the idle time slot.

[0097] Figure 5 This is a flowchart illustrating a resource scheduling method for shared screens in an application scenario provided by an embodiment of this application. Figure 5 As shown, the resource scheduling method for shared screens in this application embodiment, in a large-screen interactive e-commerce scenario, may include the following steps: Step 501: The business operations management platform connects with the e-commerce platform to synchronize product information.

[0098] Step 502: Share the screen to display product advertisements and interactive entry points.

[0099] Step 503: Consumers select products by scanning a code or using gestures.

[0100] Step 504: Does the shared screen support intelligent interaction?

[0101] If supported, you can proceed to step 5051, where you can select gestures to add scanning a QR code to place an order.

[0102] If not supported, you can proceed to step 5052 to scan the QR code and be redirected to the e-commerce platform to place an order.

[0103] Step 506: Synchronize the completed payment order information to the business operations management platform.

[0104] Step 507: The e-commerce platform fulfills the order by delivering or verifying the goods.

[0105] Step 508: The platform calculates e-commerce commission based on transaction amount.

[0106] Step 509: Settle commissions with the operator and generate a transaction report.

[0107] To explain the above steps in more detail, the following example illustrates a scenario of a large-screen interactive e-commerce platform. A user, while enjoying a visit to a park, becomes thirsty and wants to buy bottled water. They see a smart screen with a camera in the park; the screen displays an advertisement for a local bottled water brand, with the options "Scan to buy, 30-minute delivery" or "Gesture to select flavor" below. The user selects "mineral water" using gestures, scans the QR code on the screen to be redirected to a food delivery platform to complete the payment; the order information is synchronized to the business operation platform, which records the transaction data and settles accounts with the operator at a 5% commission rate; 30 minutes later, the user receives the delivered bottled water, and the operator earns additional revenue through e-commerce commissions.

[0108] The above are embodiments of the method proposed in this application. Based on the same inventive concept, embodiments of this application also provide a resource scheduling device for sharing a screen, the structure of which is as follows: Figure 6 As shown.

[0109] Figure 6 This is a schematic diagram of the internal structure of a resource scheduling device for a shared screen, provided as an embodiment of this application. Figure 6 As shown, the device includes: At least one processor 601; And a memory 602 that is communicatively connected to at least one processor; The memory 602 stores instructions that can be executed by at least one processor, which are executed by at least one processor 601 to enable at least one processor 601 to: execute the resource scheduling method for the shared screen described above.

[0110] In one possible implementation, the processor 601 is capable of receiving attribute data from at least one shared screen; discretizing the available time interval of the shared screen into at least one time resource unit according to a preset time granularity, and constructing a screen resource library based on the time resource units and the attribute data; using a time gap detection algorithm to analyze the occupied time resource units in the screen resource library to mine fragmented time resource units of different value levels, wherein the fragmented time resource units are time resource units in an idle state; responding to a transaction request initiated by a first user for a target fragmented time resource unit of a target shared screen, executing a differentiated transaction process corresponding to the value level of the target fragmented time resource unit; receiving target content submitted by the first user and associated with the target fragmented time resource unit, and performing compliance review on the target content; updating the status information of the target fragmented time resource unit to be occupied when the differentiated transaction process is completed; and controlling the target shared screen to play the target content in response to the approval and the arrival of the playback period.

[0111] Some embodiments of this application provide corresponding to Figure 1 A non-volatile computer storage medium stores computer-executable instructions, which are configured to execute the resource scheduling method for the shared screen described above.

[0112] In one possible implementation, the computer-executable instructions are configured to: receive attribute data of at least one shared screen; discretize the available time interval of the shared screen into at least one time resource unit according to a preset time granularity, and construct a screen resource library based on the time resource unit and the attribute data; use a time gap detection algorithm to analyze the occupied time resource units in the screen resource library to mine fragmented time resource units of different value levels, wherein the fragmented time resource units are time resource units in an idle state; respond to a transaction request initiated by a first user for a target fragmented time resource unit of a target shared screen, execute a differentiated transaction process corresponding to the value level of the target fragmented time resource unit; receive target content submitted by the first user and associated with the target fragmented time resource unit, and conduct a compliance review of the target content; when the differentiated transaction process is completed, update the status information of the target fragmented time resource unit to be occupied; and respond to the review being passed and the playback period arriving, control the target shared screen to play the target content.

[0113] 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 embodiments for IoT devices and media 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.

[0114] The systems, media, and methods provided in this application are one-to-one correspondences. Therefore, the systems and media also have similar beneficial technical effects as their corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the systems and media will not be repeated here.

[0115] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0116] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0117] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0118] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0119] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0120] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0121] Computer-readable media include both permanent and non-permanent, removable and non-removable media that can store information by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, 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 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 herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0122] 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.

[0123] The above description is merely an embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of this application should be included within the scope of the claims of this application.

Claims

1. A resource scheduling method for shared screens, characterized in that, The method includes: Receive attribute data for at least one shared screen; The available time interval of the shared screen is discretized into at least one time resource unit according to a preset time granularity, and a screen resource library is constructed based on the time resource unit and the attribute data. The time gap detection algorithm is used to analyze the occupied time resource units in the screen resource library in order to discover fragmented time resource units with different value levels, wherein the fragmented time resource units are time resource units in an idle state. In response to a transaction request initiated by a first user for a target fragmented time resource unit of a target shared screen, a differentiated transaction process corresponding to the value level of the target fragmented time resource unit is executed. Receive the target content submitted by the first user and associated with the target fragmented time resource unit, and conduct a compliance review of the target content; Upon completion of the differentiated transaction process, the status information of the target fragmented time resource unit will be updated to indicate that it has been occupied. In response to approval and the arrival of the playback period, control the target shared screen to play the target content.

2. The method according to claim 1, characterized in that, The time gap detection algorithm is used to analyze the occupied time resource units in the screen resource library to identify fragmented time resource units of different value levels, including: Using a time gap detection algorithm, fragmented time resource units between adjacent occupied time resource units in the screen resource library are identified; For each fragmented time resource unit, a value score is calculated based on the length of the fragmented time resource unit, the attribute data of adjacent time resource units and the corresponding shared screen. The value level of the fragmented time resource unit is determined based on the range in which the value score falls.

3. The method according to claim 2, characterized in that, The step of executing a differentiated transaction process based on the value level corresponding to the target fragmented time resource unit includes: If the value level is higher than or equal to the bidding threshold, a bidding process based on the starting price is initiated for the target fragmented time resource unit. If the value level is lower than the bidding threshold, a fixed price is provided for the target fragmented time resource unit for the first user to purchase directly.

4. The method according to claim 3, characterized in that, The starting bid price is obtained through the following methods: The value level, duration, tenant value level of adjacent time resource units, and attribute data of the target shared screen are input into the starting price pricing model to obtain the starting price of the target fragmented time resource unit output by the pricing model. The bidding process includes: Obtain the bidding request from the first user, wherein the bidding request carries a price higher than the starting price; In response to the end of the bidding period and the first user being the highest bidder, a funding instruction is issued to the first user, wherein the funding instruction is used to instruct the first user to pay funds; A review instruction is issued to the first user, wherein the review instruction is used to instruct the first user to upload target content.

5. The method according to claim 1, characterized in that, After controlling the target shared screen to play the target content in response to approval and the arrival of the playback period, the method further includes: Obtain product information sent by e-commerce platforms; Interactive elements associated with product information are displayed on the shared screen; In response to a second user scanning or selecting the interactive element via a mobile terminal, the second user is directed to a transaction page related to the product information.

6. The method according to claim 1, characterized in that, Prior to responding to a transaction request initiated by a first user for a target fragmented time resource unit of the target shared screen, the method further includes: The screen resource library is analyzed, and multiple different fragmented time resource units are clustered and combined into at least one spatiotemporal combination based on geographical proximity and temporal proximity. By analyzing the value of the spatiotemporal combination, the combination price of the spatiotemporal combination is determined; Based on the first user's historical targeting preferences and search behavior, a target spatiotemporal combination is recommended to the first user.

7. The method according to claim 1, characterized in that, After the differentiated transaction process is completed, and the status information of the target fragmented time resource unit is updated to indicate that it is occupied, the method further includes: Monitor the status of the target time resource unit that is about to reach its playback period; If the target time resource unit becomes idle within a first preset time period before the start of the playback period, a fast bidding process with a duration of a second preset time is initiated, wherein the second preset time is shorter than the first preset time. Once the rapid bidding process is completed, a playback command is sent to the target shared screen via the edge node network.

8. The method according to claim 1, characterized in that, Prior to responding to a transaction request initiated by a first user for a target fragmented time resource unit of the target shared screen, the method further includes: Obtain the first user's advertising needs information, wherein the advertising needs information includes the target geographic area, target audience attributes, marketing objectives, and budget constraints; Based on the target geographical region, candidate fragmented time resource units located within the target geographical region are selected from the screen resource library; Based on the target audience attributes, candidate fragmented time resource units with a potential audience distribution matching degree greater than a preset threshold are selected from the candidate fragmented time resource units. The potential audience distribution is predicted by the scene audience model based on the shared screen of the candidate fragmented time resource units and the time information of the candidate fragmented time resource units. Based on the aforementioned marketing objectives, at least one of the following should be selected as the optimization objective: maximizing exposure, maximizing audience matching, and minimizing cost. Based on the optimization objective, an objective function is constructed, and with the budget constraint as the constraint condition, at least one recommended fragmented time resource unit is selected from the candidate fragmented time resource units to construct a set of recommended solutions. The recommended scheme set is pushed to the first user.

9. A resource scheduling device for a shared screen, characterized in that, The device includes: At least one processor; And, a memory communicatively connected to the at least one processor; The memory stores instructions that can be executed by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform a shared screen resource scheduling method as described in any one of claims 1-8.

10. A computer storage medium storing computer-executable instructions, characterized in that, When the computer-executable instructions are executed, a resource scheduling method for a shared screen as described in any one of claims 1-8 is implemented.

Images