CN116894698A

CN116894698A - Content delivery method and device, electronic device and storage medium

Info

Publication number: CN116894698A
Application number: CN202310787924.XA
Authority: CN
Inventors: 刘欣; 陈双喜; 管皓
Original assignee: Samsung Electronics China R&D Center; Samsung Electronics Co Ltd
Current assignee: Samsung Electronics China R&D Center; Samsung Electronics Co Ltd
Priority date: 2023-06-29
Filing date: 2023-06-29
Publication date: 2023-10-17

Abstract

The disclosure provides a content delivery method and device, electronic equipment and a storage medium, so that a user can intelligently deliver content according to requirements. The content delivery method comprises the following steps: receiving user input including content delivery requirements; responding to the user input, and determining release information and release content by using a release recommendation model according to the content release requirement; and delivering the delivery content according to the delivery information.

Description

Content delivery method and device, electronic device and storage medium

Technical Field

The present disclosure relates to the field of electronics technologies, and in particular, to a content delivery method and apparatus, an electronic device, and a storage medium.

Background

Digital Signage (Digital Signage) generally refers to a multimedia professional audiovisual system that distributes business, financial and entertainment information and the like through a large-screen terminal display device, and distributes and processes information in a media manner by means of integration of network technology, multimedia technology and the like, so as to be capable of timely interacting with feedback information of clients. Therefore, the digital signage as a brand new media concept has been widely used in mass shops, supermarkets, hotel lobbies, restaurants, cinema and other public places where people flow converges.

However, the existing content delivery for digital signage has a plurality of defects, for example, a user can determine the content for delivering to the digital signage only under the condition of mastering professional skills (such as material selection, page layout, tone collocation, etc.), the user needs to manually configure specific delivery information and upload the delivered content, the existing content template cannot meet the personalized requirements of the user, and the use of the existing digital signage requires the user to have hardware devices supporting specific delivery functions, etc. How to deliver content efficiently enables the content to reach customers accurately, so that improving marketing conversion rate is a continuous problem in the industry.

Disclosure of Invention

The embodiment of the disclosure provides a content delivery method and device, electronic equipment and a storage medium, so that a user can intelligently deliver content according to requirements.

According to a first aspect of embodiments of the present disclosure, a content delivery method is provided. The content delivery method comprises the following steps: receiving user input including content delivery requirements; responding to the user input, and determining release information and release content by using a release recommendation model according to the content release requirement; and delivering the delivery content according to the delivery information.

Optionally, the delivery recommendation model includes a delivery device recommendation model and/or a delivery period recommendation model, where the step of determining the delivery information using the delivery recommendation model according to the content delivery requirement includes: determining a plurality of alternative devices according to the requirement of a delivery area included in the content delivery requirement, acquiring first statistical data of all the alternative devices, and determining a delivery device for delivering the content among the plurality of alternative devices by using a delivery device recommendation model according to the acquired first statistical data; and/or determining a plurality of alternative time periods according to the delivery time requirements included in the content delivery requirements, acquiring second statistical data of all delivery devices, and determining a delivery time period for delivering the content among the plurality of alternative time periods by using a delivery time period recommendation model according to the acquired second statistical data.

Optionally, the step of determining, according to the obtained first statistical data, a delivery device for delivering the delivered content from among a plurality of candidate devices using a delivery device recommendation model includes: calculating a first device recommendation score for each candidate device according to the content type included in the put content demand and the environment data of each candidate device included in the first statistical data, wherein the first device recommendation score indicates the matching degree of the environment near the put device and the content type; calculating a second device recommendation score for each candidate device according to the device delivery frequency included in the first statistics, wherein the second device recommendation score indicates the frequency with which the delivery device was previously used to deliver content; determining a device recommendation score for each candidate device according to a weighted sum of the calculated first device recommendation score and the calculated second device recommendation score; and determining a delivery device for delivering the delivery content among the plurality of alternative devices according to the determined device recommendation score.

Optionally, the step of determining, according to the acquired second statistical data, a delivery period for delivering the delivered content among a plurality of alternative periods using a delivery period recommendation model includes: calculating a time period recommendation score for each alternative time period from the person flow data for each alternative time period included in the second statistical data and the maximum person flow data within one time period in the second statistical data; and determining a delivery period for delivering the delivery content among the plurality of alternative periods according to the determined period recommendation score.

Optionally, the step of determining the delivery information by using a delivery recommendation model according to the content delivery requirement further comprises: calculating the equipment recommendation score of each piece of alternative equipment according to the acquired first statistical data; calculating a time period recommendation score of each alternative time period according to the acquired second statistical score; determining a delivery device and a delivery period for delivering the delivery content from among the plurality of candidate devices and the plurality of candidate periods according to a weighted sum of the device recommendation score of each candidate device and the period recommendation score of each candidate period.

Optionally, the content delivery requirement includes a delivery area, and the step of determining the delivered content by using a delivery recommendation model according to the content delivery requirement includes: and generating the delivery content matched with the personnel characteristics indicated by the peripheral personnel characteristic data by using an artificial intelligent model according to the peripheral personnel characteristic data of at least one delivery device included in the delivery area and the content delivery requirement.

According to a second aspect of embodiments of the present disclosure, there is provided a content delivery apparatus including: a communication module configured to: receiving user input including content delivery requirements; a processing module configured to: responding to the user input, and determining release information and release content by using a release recommendation model according to the content release requirement; a launch module configured to: and delivering the delivery content according to the delivery information.

Optionally, the delivery recommendation model includes a delivery device recommendation model and/or a delivery period recommendation model, wherein the processing module is configured to determine the delivery information using the delivery recommendation model according to the content delivery demand by: determining a plurality of alternative devices according to the requirement of a delivery area included in the content delivery requirement, acquiring first statistical data of all the alternative devices, and determining a delivery device for delivering the content among the plurality of alternative devices by using a delivery device recommendation model according to the acquired first statistical data; and/or determining a plurality of alternative time periods according to the delivery time requirements included in the content delivery requirements, acquiring second statistical data of all delivery devices, and determining a delivery time period for delivering the content among the plurality of alternative time periods by using a delivery time period recommendation model according to the acquired second statistical data.

Optionally, the processing module is configured to determine a delivery device for delivering the delivery content among the plurality of candidate devices using a delivery device recommendation model according to the acquired first statistical data by: calculating a first device recommendation score for each candidate device according to the content type included in the put content demand and the environment data of each candidate device included in the first statistical data, wherein the first device recommendation score indicates the matching degree of the environment near the put device and the content type; calculating a second device recommendation score for each candidate device according to the device delivery frequency included in the first statistics, wherein the second device recommendation score indicates the frequency with which the delivery device was previously used to deliver content; determining a device recommendation score for each candidate device according to a weighted sum of the calculated first device recommendation score and the calculated second device recommendation score; and determining a delivery device for delivering the delivery content among the plurality of alternative devices according to the determined device recommendation score.

Optionally, the processing module is configured to determine a delivery period for delivering the delivery content from the acquired second statistical data using a delivery period recommendation model among a plurality of alternative periods by: calculating a time period recommendation score for each alternative time period from the person flow data for each alternative time period included in the second statistical data and the maximum person flow data within one time period in the second statistical data; and determining a delivery period for delivering the delivery content among the plurality of alternative periods according to the determined period recommendation score.

Optionally, the processing module is configured to determine the delivery information using a delivery recommendation model according to the content delivery requirements by: calculating the equipment recommendation score of each piece of alternative equipment according to the acquired first statistical data; calculating a time period recommendation score of each alternative time period according to the acquired second statistical score; determining a delivery device and a delivery period for delivering the delivery content from among the plurality of candidate devices and the plurality of candidate periods according to a weighted sum of the device recommendation score of each candidate device and the period recommendation score of each candidate period.

Optionally, the content delivery requirement includes a delivery area, wherein the processing module is configured to determine the delivered content using a delivery recommendation model according to the content delivery requirement by: and generating the delivery content matched with the personnel characteristics indicated by the peripheral personnel characteristic data by using an artificial intelligent model according to the peripheral personnel characteristic data of at least one delivery device included in the delivery area and the content delivery requirement.

According to a third aspect of embodiments of the present disclosure, there is provided an electronic device comprising: at least one processor; at least one memory storing computer-executable instructions, wherein the computer-executable instructions, when executed by the at least one processor, cause the at least one processor to perform the content delivery method as described above.

According to a fourth aspect of embodiments of the present disclosure, there is provided a computer-readable storage medium, wherein instructions in the computer-readable storage medium, when executed by at least one processor, cause the at least one processor to perform the content delivery method as described above.

According to the embodiment of the disclosure, the user can be helped to adaptively select the optimal throwing device in consideration of the user demands and the environmental data of the throwing device, and the user does not need to conduct excessive investigation on the regional characteristics of the throwing region, so that the time and the labor cost are saved. According to the embodiment of the disclosure, the user can be helped to adaptively select the optimal throwing period by considering the user demands and the personnel flow data near the throwing equipment, and the user is not required to study the personnel flow characteristics of the throwing target group, so that the time is effectively saved and the labor cost is reduced. According to the embodiment of the disclosure, through the fusion use of the equipment recommendation and the time period recommendation, the optimal throwing equipment and throwing time which are adaptive to the environment and mutually adaptive to each other can be determined, so that resource throwing is performed by an intelligently generated throwing strategy, and the marketing conversion rate is improved. According to the embodiment of the disclosure, personalized release content can be automatically generated for display according to the user requirements, the application scene of the current digital signage device can be expanded, and the possibility of content release expanded to the meta-universe virtual display screen is provided.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure and do not constitute an undue limitation on the disclosure.

Fig. 1 is a diagram illustrating an example of product types covered by a CMS solution.

Fig. 2 is a flowchart illustrating a content delivery method according to an embodiment of the present disclosure.

Fig. 3 is a diagram illustrating an example of input user input according to an embodiment of the present disclosure.

Fig. 4 is a sequence diagram illustrating a content delivery method according to an embodiment of the present disclosure.

Fig. 5 is a diagram illustrating a process of classifying person features according to an embodiment of the present disclosure.

Fig. 6 is a flowchart illustrating a process of determining a launch device according to an embodiment of the present disclosure.

Fig. 7 is a flowchart illustrating a process of determining a delivery period according to an embodiment of the present disclosure.

Fig. 8 is a diagram illustrating an example of generating impression content according to an embodiment of the present disclosure.

Fig. 9 is a diagram illustrating an example of a scenario in which a content delivery method according to an embodiment of the present disclosure is applied.

Fig. 10 is a block diagram illustrating a content delivery device according to an embodiment of the present disclosure.

Detailed Description

In order to enable those skilled in the art to better understand the technical solutions of the present disclosure, the technical solutions of the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.

It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the foregoing figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the disclosure described herein may be capable of operation in sequences other than those illustrated or described herein. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present disclosure as detailed in the accompanying claims.

It should be noted that, in this disclosure, "at least one of the items" refers to a case where three types of juxtaposition including "any one of the items", "a combination of any of the items", "an entirety of the items" are included. For example, "including at least one of a and B" includes three cases side by side as follows: (1) comprises A; (2) comprising B; (3) includes A and B. For example, "at least one of the first and second steps is executed", that is, three cases are juxtaposed as follows: (1) performing step one; (2) executing the second step; (3) executing the first step and the second step.

Recently, new business models continue to emerge as the popularity and usage of the concept of the meta-universe increases. By means of various interactive technologies, various scenes in the virtual world are greatly increased, more super-realistic life landscapes from the real world are expanded, and meanwhile, the limitation that real advertising media are influenced by space time, quantity and quality can be broken through. Perhaps in the future, a tile in the meta-universe, each guideboard, each device may become a "container" for advertising. Thus, the frequency of application of content delivery to electronic devices like digital signage has also increased substantially.

Hereinafter, the "electronic device" used to deliver content according to the embodiments of the present disclosure may also be referred to as a "delivery device" or "delivery electronic device".

As an example, the delivery device may include various types of electronic devices. The electronic device may include, for example, a portable communication device (e.g., a smart phone), a computer device, a portable multimedia device, a portable medical device, a camera, a wearable device, or a household appliance. According to the embodiments of the present disclosure, the electronic devices are not limited to those described above.

Hereinafter, "content" may include various types of resources for delivery for information presentation. Forms of content include, but are not limited to, video, still images, moving images, text, virtual Reality (VR) content, augmented Reality (AR) content. Information presentation means of contents include, but are not limited to, presentation means of various forms of contents as described above, for example, presentation of contents by projection, and the like.

As used herein, the term "module" may include units implemented in hardware, software, or firmware, and may be used interchangeably with other terms (e.g., "logic," "logic blocks," "portions," or "circuitry"). A module may be a single integrated component adapted to perform one or more functions or a minimal unit or portion of the single integrated component. For example, according to an embodiment, a module may be implemented in the form of an Application Specific Integrated Circuit (ASIC).

In the related art, in order to enable the delivery content to realize the characteristic of playing advertisement information for a specific crowd in a specific physical place and a specific time period, a user is often required to purchase corresponding hardware equipment for delivery first, which causes a large cost. It is also required that the user creates contents for information presentation using expertise (such as material selection, page layout, tone collocation, etc.) or generates contents using a preset content template, which causes inconvenience to the user in using a delivery function. Eventually, the user is also required to manually configure various delivery information for delivering the content, which requires the user to have a marketing means capable of determining a specific delivery strategy according to the needs. Therefore, the content delivery method and device in the related art often require a user to have a certain experience or skill and require a targeted delivery device, and have high requirements on the user and the delivery device.

In this regard, the disclosure proposes a content delivery method and device, an electronic device, and a storage medium, so that a user can intelligently deliver content according to requirements. Exemplary embodiments according to the present disclosure will be described below with reference to fig. 1 to 10.

Fig. 1 is a diagram illustrating an example of product types covered by a new generation Content Management Server (CMS) solution. Referring to fig. 1, an application scenario is shown that may be applied to in accordance with an embodiment of the present disclosure, specifically including Hotel televisions (Hotel TVs), stand alone large screen displays (LFDs), flip-flop LFDs, outdoor LFDs, special LFDs, third party LFDs, IF/Wall stiffener (IF/Wall Pro) light emitting diode displays (LEDs), a/P series LEDs, and the like.

It should be understood by those skilled in the art that the above application scenario is only an example, and the exemplary embodiments according to the present disclosure are not limited to the above application scenario.

Referring to fig. 2, at S201, a user input including a content delivery requirement is received.

According to embodiments of the present disclosure, commands or data to be used may be received as user input from outside by any suitable means.

Referring to fig. 3, a user may log in a content delivery device (e.g., CMS) by scanning a displayed two-dimensional code using an electronic device (e.g., a smart phone) to use a delivery-related function (e.g., submit a content delivery demand), thereby displaying corresponding delivery content on a display screen.

According to embodiments of the present disclosure, content delivery requirements may include, but are not limited to, delivery area requirements for delivering content (e.g., a physical location (e.g., a description of a location such as a software valley, a han kou road, a cottage road, etc.), delivery time requirements for delivering content (e.g., a specific time or period of delivery (e.g., five pm or afternoon) and/or a delivery duration (e.g., 1 hour, etc.), types of delivered content (e.g., food, automotive, financial, sports, electronic, etc.).

According to embodiments of the present disclosure, the step of receiving user input including content delivery requirements includes a user management step (e.g., user registration, user login, user rights management), a device management step (device registration, device monitoring, device remote control), and other steps performed in response to the user input.

Fig. 4 is a sequence diagram illustrating a content delivery method according to an embodiment of the present disclosure. Referring to fig. 4, in step S401, user input (e.g., a registered account or login) related to user management is received from a user terminal.

In step S402, user input (e.g., delivery area/location, content type, delivery time, duration of delivery, number of delivery devices (e.g., number of display screens), etc.) including a content delivery demand is received from a user terminal.

When user input is received, specific delivery information and delivery content may be determined based on the user input. Returning to fig. 2, in step S202, in response to the user input, the delivery information and the delivery content are determined using the delivery recommendation model according to the content delivery requirements.

According to embodiments of the present disclosure, the placement recommendation model may include a device recommendation model. When the release recommendation model is a device recommendation model, the step of determining release information by using the release recommendation model according to content release requirements comprises the following steps: determining a plurality of alternative devices according to the requirement of the delivery area included in the content delivery requirement, acquiring first statistical data of all the alternative devices, and determining the delivery device for delivering the content among the plurality of alternative devices by using a delivery device recommendation model according to the acquired first statistical data.

According to embodiments of the present disclosure, the first statistics may include environmental data in the vicinity of the delivering device, such as surrounding organization information (e.g., banks, universities, communities, etc.), surrounding personnel characteristic data (e.g., programmers, financial white collars, college students, etc.), device delivery frequency (e.g., frequency at which a certain device was previously used to deliver content (such as a two-dimensional code history scan number of the device for delivering content)). Table 1 below shows exemplary first statistics.

TABLE 1

Here, "number" may represent a data item number in the statistical data, "delivery device number" may represent a number for distinguishing a delivery device, "history delivery times" may represent the number of times the delivery device is used to deliver content, "two-dimensional code scanning times" represent the number of times a two-dimensional code corresponding to the delivery device is scanned for using a delivery-related function.

According to embodiments of the present disclosure, the first statistics may be counted by using a monitoring module (e.g., sensor module, camera module, etc.) on the delivery device.

As an example, the monitoring personnel data may be tracked by using a camera module (e.g., a miniature camera in fig. 3) to obtain the first statistics. For example, the first statistical data may be obtained by a method of object extraction (background modeling, foreground analysis), object recognition (pattern recognition, feature point analysis), object tracking, or the like.

As an example, the geographic location may be obtained by using a location sensor to obtain the first statistical data.

As an example, the surrounding organization information data may be obtained by accessing an organization information website to obtain the first statistics. According to embodiments of the present disclosure, the first statistics may be stored to a database for access.

According to embodiments of the present disclosure, the environmental data of the delivery device may include personnel characteristic data (or referred to as ambient personnel characteristic data). According to embodiments of the present disclosure, personnel characteristic data may be obtained by processing the collected data using artificial intelligence algorithms. In particular, the step of obtaining personnel characteristic data may comprise: preprocessing the collected organization information data, wherein training features comprise feature information such as organization categories, addresses, areas, industries and the like; establishing a model training sample set; manually tagging a training sample set, the tag comprising personnel feature types, wherein the personnel feature types include, but are not limited to, professional features (programmers, financial white collars, college students, biological medicines, construction blue collars, etc.), age features (elderly, young children, young people, etc.), gender features, lifestyle features, etc.; training the sample dataset based on an artificial intelligence algorithm (e.g., a supervised neural network) to generate a human feature classification model; the human feature classification model is used to predict the input data and output a probability value Pi for a label i, where i is a positive integer for distinguishing between different labels. Fig. 5 is a diagram illustrating a process of classifying person features according to an embodiment of the present disclosure. Referring to fig. 5, by using a neural network, a person feature (e.g., programmer, financial white collar, college, biomedical, construction blue collar, etc.) and a corresponding probability (Pi) are finally obtained as output via an input layer, a hidden layer, and an output layer of the neural network based on input data (e.g., organization information data), for example, the probability that the person feature is a programmer is determined to be P1, etc., based on the input data.

The neural network model may be obtained through training. Here, "obtaining by training" refers to training a neural network model having a plurality of training data by a training algorithm, thereby obtaining a predefined operating rule or neural network model configured to perform a desired feature (or purpose).

As an example, the neural network model may include a plurality of neural network layers. Each of the plurality of neural network layers includes a plurality of weight values, and the neural network calculation is performed by calculation between the calculation result of the previous layer and the plurality of weight values. Examples of neural networks include, but are not limited to, convolutional Neural Networks (CNNs), deep Neural Networks (DNNs), recurrent Neural Networks (RNNs), boltzmann machines limited (RBMs), deep Belief Networks (DBNs), bi-directional recurrent deep neural networks (BRDNNs), generative Antagonism Networks (GANs), and deep Q networks.

With continued reference to fig. 4, at step S403, a list of available devices (including a plurality of alternative devices) that meet the content delivery requirements may be queried. In step S404, a device recommendation model is invoked to calculate the best delivery device. In the content delivery method of fig. 4, step S404 may be selected by the user or other settings, or step S404 may be omitted, and the device input by the user or all of the delivery devices may be directly used as the delivery device.

According to an embodiment of the present disclosure, the step of determining a delivery device for delivering the delivery content among a plurality of candidate devices using a delivery device recommendation model according to the acquired first statistical data comprises: calculating a first device recommendation score for each candidate device according to the content type included in the put content demand and the environment data of each candidate device included in the first statistical data, wherein the first device recommendation score indicates the matching degree of the environment near the put device and the content type; calculating a second device recommendation score for each candidate device according to the device delivery frequency included in the first statistics, wherein the second device recommendation score indicates the frequency with which the delivery device was previously used to deliver content; determining a device recommendation score for each candidate device according to a weighted sum of the calculated first device recommendation score and the calculated second device recommendation score; and determining a delivery device for delivering the delivery content among the plurality of alternative devices according to the determined device recommendation score. This is described in detail below with reference to fig. 6.

In step S601, a plurality of available alternative devices are queried according to the delivery area demand included in the content delivery demand and first statistics (e.g., environmental data (e.g., personnel characteristic data) and device delivery frequency (such as a historical delivery number and a two-dimensional code scan number)) of the alternative devices are acquired.

In step S602, a first device recommendation score S1 for each candidate device is calculated based on the content type included in the put content demand and the context data of each candidate device included in the first statistics (e.g., based on a scoring rule that a preset content type matches the context (e.g., a person feature)). Here, the first device recommendation score is used to measure how well the type of delivered content matches the environment in the vicinity of the current delivery device. Although only personnel features are shown in fig. 6, it should be understood that other environmental features, such as organization categories, may also be included.

According to embodiments of the present disclosure, a weighted sum of the content type and the matching score of each environmental data may be calculated by taking the probability value of each environmental data as a weight to determine the first device recommendation score. As an example, referring to fig. 6, assuming that the content type is "fine-pull" and the person features are "programmer (probability is 0.9)" and "financial white collar (probability is 0.1)", the first device recommendation score (e.g., matching score) S1 is s1=95×0.9+100×0.1=95.5, where 95 indicates a preset matching score of "fine-pull" and "programmer", and 100 indicates a preset matching score of "fine-pull" and "financial white collar". In fig. 6, an exemplary table on the right may be determined through similar weighting calculations.

In step S603, the second device recommendation score S2 of each of the alternative devices is calculated according to the device placement frequency (such as the historical placement times and the two-dimensional code scanning times) included in the first statistical data, for example, the second device recommendation score S2 of each of the alternative devices is calculated according to a scoring rule of the preset historical placement times and the two-dimensional code scanning times. As an example, assuming that the historical placement number is C1 and the two-dimensional code scanning number is C1, the second device recommendation score S2 is w1×c1+w2×c2, where W1 and W2 are preset weight values.

In step S604, a device recommendation score for each candidate device is calculated according to the weighted sum of the first device recommendation score S1 and the second device recommendation score S2, and the delivery device is recommended according to the device recommendation score. For example, the device recommendation score is s1×w3+s2×w4, where W3 and W4 are preset weight values. As an example, the user may select a delivery device by ranking the candidate devices according to the device recommendation score and returning the ranking result to the user.

The respective weight values according to the embodiments of the present disclosure may be preset through empirical values or may be calculated through an artificial intelligence model.

According to the embodiment of the disclosure, the user can be helped to adaptively select the optimal throwing device in consideration of the user demands and the environmental data of the throwing device, and the user does not need to conduct excessive investigation on the regional characteristics of the throwing region, so that the time and the labor cost are saved.

According to embodiments of the present disclosure, the impression recommendation model may further include an impression period recommendation model. When the release recommendation model is a period recommendation model, the step of determining release information by using the release recommendation model according to content release requirements comprises the following steps: determining a plurality of alternative periods according to the delivery time requirements included in the content delivery requirements, acquiring second statistical data of all delivery devices, and determining a delivery period for delivering the content among the plurality of alternative periods by using a delivery period recommendation model according to the acquired second statistical data.

According to embodiments of the present disclosure, the second statistical data may comprise personnel flow data in the vicinity of the delivery device, e.g. personnel flow data over a specific period of time. Table 2 below shows exemplary second statistics. As an example, the time period is counted in units of one hour, it being understood that the personnel flow data may be counted in any time count unit.

TABLE 2

According to embodiments of the present disclosure, the second statistical data may be the same as or different from the first statistical data, and the manner in which the second statistical data is obtained is similar to that in which the first statistical data is obtained, and a repetitive description is not made here.

With continued reference to fig. 4, in step S405, the period recommendation model is invoked to calculate the optimal delivery period. In the content delivery method of fig. 4, step S405 is selectable by the user or other settings, or step S405 may be omitted, and a period or all of the periods input by the user may be directly used as the delivery period.

In addition, step S404 and step S405 may be performed simultaneously or sequentially, and step S404 may be performed before or after step S405.

According to an embodiment of the present disclosure, the step of determining a delivery period for delivering the delivery content among a plurality of alternative periods using a delivery period recommendation model according to the acquired second statistical data comprises: calculating a time period recommendation score for each alternative time period from the person flow data for each alternative time period included in the second statistical data and the maximum person flow data within one time period in the second statistical data; and determining a delivery period for delivering the delivery content among the plurality of alternative periods according to the determined period recommendation score.

This will be described in detail with reference to fig. 7. Fig. 7 is a flowchart illustrating a process of determining a delivery period according to an embodiment of the present disclosure.

In step S701, a plurality of alternative periods are determined according to the delivery time demand included in the content delivery demand, and second statistical data (e.g., personnel flow data) of all the delivery devices is acquired.

In step S702, a time period recommendation score is calculated based on the people flow data for each alternative time period (e.g., people flow data during 10:00-11:00, people flow data during 11:00-12:00) and the maximum people flow data for one time period (e.g., the maximum people flow data for one hour period in a half of a year that is counted). As an example, the people flow data for each alternative period of each delivery device may be represented as < ID, T, C >, where ID may represent the number of the delivery device, T may represent the period number, and C may represent the people flow data or the number of people flows within that period. As an example, the maximum traffic data within one period may represent, for example, the maximum traffic data or the number of traffic per unit period within a specific long period, here, the maximum traffic data N within one period within one half year is queried, taking one half year as an example.

According to an embodiment of the present disclosure, the period recommendation score S3 is calculated by dividing the person flow data of each of the alternative periods by the maximum person flow data, in other words, the maximum person flow data within one period is regarded as a full score, and the period recommendation score is determined by dividing the person flow data of each of the alternative periods by the full score, that is, s3=c 100%/N.

In step S703, a delivery period is determined according to the period recommendation score. As an example, the alternative time periods may be selected by sorting the time periods by a time period recommendation score and returning the sorting result to the user for the user to select a delivery time period.

According to the embodiment of the disclosure, the user can be helped to adaptively select the optimal throwing period in consideration of the user demands and the personnel flow data near the throwing equipment, and the user is not required to study the personnel flow characteristics of the throwing target group, so that the time and the labor cost are saved.

Further, according to embodiments of the present disclosure, the device recommendation model and the period recommendation model may be used simultaneously. According to an embodiment of the present disclosure, the step of determining the delivery information using the delivery recommendation model according to the content delivery requirements further comprises: calculating the equipment recommendation score of each piece of alternative equipment according to the acquired first statistical data; calculating a time period recommendation score of each alternative time period according to the acquired second statistical score; determining a delivery device and a delivery period for delivering the delivery content from among the plurality of candidate devices and the plurality of candidate periods according to a weighted sum of the device recommendation score of each candidate device and the period recommendation score of each candidate period.

As an example, the step of calculating the device recommendation score and the period recommendation score is similar to the specific step of using the device recommendation model and the period recommendation model described above, and after the device recommendation score and the period recommendation score are obtained, the total recommendation score S may be calculated by a weighted sum of the two, and an optimal combination of the device and the period may be determined based on the total recommendation score. As an example, the best delivery information may be selected by ranking the combination of candidate devices and candidate time periods by a total recommendation score and returning the ranking results to the user.

According to the embodiment of the disclosure, through the fusion use of the device recommendation and the time period recommendation, the optimal throwing device and throwing time which are adaptive to the environment and mutually adaptive to each other can be determined, so that resource throwing is performed through an intelligently generated throwing strategy.

Further, according to embodiments of the present disclosure, the delivery content may include delivery content directly input by the user and/or delivery content determined using a delivery recommendation model.

According to embodiments of the present disclosure, the delivery content may be determined using a delivery recommendation model according to content delivery requirements in response to user input.

According to an embodiment of the present disclosure, the step of determining the delivery content using the delivery recommendation model according to the content delivery requirements includes: according to the peripheral personnel characteristic data and the content delivery requirements of at least one delivery device included in the delivery area, an Artificial Intelligence (AI) model is used to generate delivery content matched with the personnel characteristics indicated by the peripheral personnel characteristic data.

As an example, AI models may be obtained through training. Here, "obtaining by training" refers to training a basic AI model with a plurality of training data by a training algorithm to obtain predefined operational rules or AI models configured to perform a desired feature (or purpose).

As an example, the AI model may include a plurality of neural network layers. Each of the plurality of neural network layers includes a plurality of weight values, and the neural network calculation is performed by calculation between the calculation result of the previous layer and the plurality of weight values. Examples of neural networks include, but are not limited to, convolutional Neural Networks (CNNs), deep Neural Networks (DNNs), recurrent Neural Networks (RNNs), boltzmann machines limited (RBMs), deep Belief Networks (DBNs), bi-directional recurrent deep neural networks (BRDNNs), generative Antagonism Networks (GANs), and deep Q networks.

According to embodiments of the present disclosure, the AI model may further include a generative pre-training transducer (GPT) model. As an example, the step of generating delivery content matching with the person feature indicated by the surrounding person feature data using the AI model according to the surrounding person feature data and the content delivery demand of at least one delivery device included in the delivery area includes: based on the peripheral personnel characteristic data and the content type included in the input environmental data of the delivery device, automatically generating content matched with the peripheral personnel characteristic data corresponding to the content type by using the GPT model as output. This will be described below with reference to fig. 8.

Referring back to fig. 4, when the user directly inputs (or uploads) the delivered content at step S406, the delivered content is audited at step S407.

Alternatively, when the user determines that the delivered content is intelligently generated, in step S409, a content production model (e.g., AI model) is invoked to generate personalized delivered content.

Referring to fig. 8, when a user inputs a content type "pulled noodle delicacy" or an uploaded content (e.g., a picture content of pulled noodle) and a put-in area (e.g., a build area), a picture content of pulled noodle matching a person feature of the put-in area corresponding to the "pulled noodle delicacy" for information presentation is automatically generated, for example, a cartoon advertisement picture matching a person feature "programmer" around the software valley display screen 1 or an exquisite advertisement picture matching a person feature "financial white collar" around the river CBD display screen 2 in the build area is generated.

Returning to fig. 2, in step S203, the delivery content is delivered according to the delivery information. According to the embodiment of the disclosure, the delivery content can be delivered based on the various types of delivery information determined in the steps.

Fig. 9 is a diagram illustrating an example of a scenario in which a content delivery method according to an embodiment of the present disclosure is applied. Referring to fig. 9, when a user C inputs a user input (e.g., uploads the delivery content), the delivery content for meta-universe presentation may be generated based on the user input, and the generated delivery content may be presented on a corresponding device.

Referring back to fig. 4, when the user determines that the delivered content is intelligently generated, the content generation model is invoked to generate the delivered content in step S408. In the content delivery method of fig. 4, step S408 may be selected by the user or other settings, or step S408 may be omitted and the content uploaded by the user may be directly used as the delivered content.

According to the embodiment of the disclosure, personalized release content can be automatically generated for display according to the user requirements, the generated personalized content can better accord with the preference of personnel characteristics, the propaganda effect is enhanced, the application scene of the embodiment of the disclosure can be expanded, and the possibility is provided for content release expanding to a meta-universe virtual display screen.

With continued reference to fig. 4, at step S409, a request is received from the user terminal for the user to submit an order and a payment message is completed. According to an embodiment of the present disclosure, the step of receiving user input including content delivery requirements further comprises: generating content delivery order information in response to a user submitting a delivery order; performing a payment operation (e.g., online payment) by a user; in response to the payment being successful, a content delivery order is generated.

When order payment is completed, a corresponding drop operation may be performed.

In step S410, the completed order is added to the delivery list to be delivered.

In step S411, the content may be delivered by using the device management interface.

In step S412, the delivery content is presented (e.g., played) at the delivery device segment.

"delivery" operations according to embodiments of the present disclosure may include, but are not limited to, transmitting data of the delivered content to a corresponding electronic device, presenting the delivered content and/or storing the data of the delivered content, or the like.

Referring to fig. 10, the content delivery apparatus 1000 includes a communication module 1001, a processing module 1003, and a delivery module 1004.

The communications module 1001 is configured to receive user input including content delivery requirements. That is, the communication module 1001 may perform the operation corresponding to the above-described step S201. The communications module 1001 may be used to perform the operations described above in connection with receiving user inputs, which are not described in detail herein.

The processing module 1002 is configured to: and responding to the user input, and determining the release information and the release content according to the content release requirement by using a release recommendation model. That is, the processing module 1002 may perform the operation corresponding to step S202 described above. According to an embodiment of the present disclosure, the processing module 1002 may further include: the user management module is used for executing the steps of user registration, user login, user authority management and the like; the device management module is used for executing the steps of device registration, device monitoring, remote control and the like; the content generation module is used for executing the step of generating the released content; the content auditing model is used for executing the step of auditing the released content; the order management module is used for generating order information, paying orders online, completing orders and the like in response to the content delivery requirements submitted by users.

The delivery module 1003 is configured to deliver the delivery content according to the delivery information. That is, the delivery model 1003 may perform the operation corresponding to step S203 described above. According to embodiments of the present disclosure, the processing module 1002 may further include a content delivery model for performing the above-described content delivery-related steps.

According to an embodiment of the present disclosure, the delivery recommendation model comprises a delivery device recommendation model and/or a delivery period recommendation model, wherein the processing module 1002 is configured to determine the delivery information using the delivery recommendation model according to the content delivery requirements by: determining a plurality of alternative devices according to the requirement of a delivery area included in the content delivery requirement, acquiring first statistical data of all the alternative devices, and determining a delivery device for delivering the content among the plurality of alternative devices by using a delivery device recommendation model according to the acquired first statistical data; and/or determining a plurality of alternative time periods according to the delivery time requirements included in the content delivery requirements, acquiring second statistical data of all delivery devices, and determining a delivery time period for delivering the content among the plurality of alternative time periods by using a delivery time period recommendation model according to the acquired second statistical data.

According to an embodiment of the present disclosure, the processing module 1002 is configured to determine a delivery device for delivering the delivery content among a plurality of candidate devices using a delivery device recommendation model from the acquired first statistical data by: calculating a first device recommendation score for each candidate device according to the content type included in the put content demand and the environment data of each candidate device included in the first statistical data, wherein the first device recommendation score indicates the matching degree of the environment near the put device and the content type; calculating a second device recommendation score for each candidate device according to the device delivery frequency included in the first statistics, wherein the second device recommendation score indicates the frequency with which the delivery device was previously used to deliver content; determining a device recommendation score for each candidate device according to a weighted sum of the calculated first device recommendation score and the calculated second device recommendation score; and determining a delivery device for delivering the delivery content among the plurality of alternative devices according to the determined device recommendation score.

According to an embodiment of the present disclosure, the processing module 1002 is configured to determine a delivery period for delivering the delivery content from the acquired second statistical data using a delivery period recommendation model among a plurality of alternative periods by: calculating a time period recommendation score for each alternative time period from the person flow data for each alternative time period included in the second statistical data and the maximum person flow data within one time period in the second statistical data; and determining a delivery period for delivering the delivery content among the plurality of alternative periods according to the determined period recommendation score.

According to an embodiment of the present disclosure, the processing module 1002 is configured to determine the delivery information using a delivery recommendation model according to the content delivery requirements by: calculating the equipment recommendation score of each piece of alternative equipment according to the acquired first statistical data; calculating a time period recommendation score of each alternative time period according to the acquired second statistical score; determining a delivery device and a delivery period for delivering the delivery content from among the plurality of candidate devices and the plurality of candidate periods according to a weighted sum of the device recommendation score of each candidate device and the period recommendation score of each candidate period.

According to an embodiment of the present disclosure, the content delivery requirements include a delivery area, wherein the processing module 1002 is configured to determine the delivery content using a delivery recommendation model from the content delivery requirements by: and generating the delivery content matched with the personnel characteristics indicated by the peripheral personnel characteristic data by using an artificial intelligent model according to the peripheral personnel characteristic data of at least one delivery device included in the delivery area and the content delivery requirement.

The specific manner in which the various modules of the content delivery device 1000 perform operations has been described in detail in connection with embodiments of related methods, and will not be described in detail herein.

According to an embodiment of the present disclosure, there is also provided an electronic apparatus. An electronic device includes: at least one processor; at least one memory storing computer-executable instructions, wherein the computer-executable instructions, when executed by the at least one processor, cause the at least one processor to perform the content delivery method as described above.

By way of example, the electronic device may be a PC computer, tablet device, personal digital assistant, smart phone, or other device capable of executing the above-described set of instructions. Here, the electronic device is not necessarily a single electronic device, but may be any device or an aggregate of circuits capable of executing the above-described instructions (or instruction set) singly or in combination. The electronic device may also be part of an integrated control system or system manager, or may be configured as a portable electronic device that interfaces with either locally or remotely (e.g., via wireless transmission).

In an electronic device, a processor may include a Central Processing Unit (CPU), a Graphics Processor (GPU), a programmable logic device, a special purpose processor system, a microcontroller, or a microprocessor. By way of example, and not limitation, processors may also include analog processors, digital processors, microprocessors, multi-core processors, processor arrays, network processors, and the like.

The processor may execute instructions or code stored in the memory, wherein the memory 201 may also store data. The instructions and data may also be transmitted and received over a network via a network interface device, which may employ any known transmission protocol.

The memory may be integrated with the processor, for example, RAM or flash memory disposed within an integrated circuit microprocessor or the like. In addition, the memory may include a stand-alone device, such as an external disk drive, a storage array, or any other storage device usable by a database system. The memory and the processor may be operatively coupled or may communicate with each other, for example, through an I/O port, a network connection, etc., such that the processor is able to read files stored in the memory.

In addition, the electronic device may also include a video display (such as a liquid crystal display) and a user interaction interface (such as a keyboard, mouse, touch input device, etc.). All components of the electronic device may be connected to each other via a bus and/or a network.

There is also provided, in accordance with an embodiment of the present disclosure, a computer-readable storage medium, wherein instructions in the computer-readable storage medium, when executed by at least one processor, cause the at least one processor to perform the content delivery method as described above.

By way of example, the computer-readable storage medium may comprise: read-only memory (ROM), random-access programmable read-only memory (PROM), electrically erasable programmable read-only memory (EEPROM), random-access memory (RAM), dynamic random-access memory (DRAM), static random-access memory (SRAM), flash memory, nonvolatile memory, CD-ROM, CD-R, CD + R, CD-RW, CD+RW, DVD-ROM, DVD-R, DVD + R, DVD-RW, DVD+RW, DVD-RAM, BD-ROM, BD-R LTH, BD-RE, blu-ray or optical disk memory, hard Disk Drive (HDD), solid State Disk (SSD), card memory (such as a multimedia card, secure Digital (SD) card or ultra-fast digital (XD) card), magnetic tape, floppy disk, magneto-optical data storage, hard disk, solid state disk, and any other means configured to store and provide computer programs and any associated data, data files and data structures to a processor or computer in a non-transitory manner that enables the processor or computer to execute the computer programs. The computer programs in the computer readable storage media described above can be run in an environment deployed in an electronic device, such as a client, host, proxy device, server, etc., and further, in one example, the computer programs and any associated data, data files, and data structures are distributed across networked computer systems such that the computer programs and any associated data, data files, and data structures are stored, accessed, and executed in a distributed fashion by one or more processors or computers.

Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any adaptations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

It is to be understood that the present disclosure is not limited to the precise arrangements and instrumentalities shown in the drawings, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A content delivery method, comprising:

receiving user input including content delivery requirements;

responding to the user input, and determining release information and release content by using a release recommendation model according to the content release requirement;

and delivering the delivery content according to the delivery information.

2. The content delivery method according to claim 1, wherein the delivery recommendation model comprises a delivery device recommendation model and/or a delivery period recommendation model,

The step of determining the delivery information by using a delivery recommendation model according to the content delivery requirements comprises the following steps:

determining a plurality of alternative devices according to the requirement of a delivery area included in the content delivery requirement, acquiring first statistical data of all the alternative devices, and determining a delivery device for delivering the content among the plurality of alternative devices by using a delivery device recommendation model according to the acquired first statistical data; and/or

And determining a plurality of alternative time periods according to the delivery time requirements included in the content delivery requirements, acquiring second statistical data of all delivery devices, and determining a delivery time period for delivering the content among the plurality of alternative time periods by using a delivery time period recommendation model according to the acquired second statistical data.

3. The content delivery method according to claim 2, wherein the step of determining a delivery device for delivering the delivered content among a plurality of candidate devices using a delivery device recommendation model according to the acquired first statistical data comprises:

calculating a first device recommendation score for each candidate device according to the content type included in the put content demand and the environment data of each candidate device included in the first statistical data, wherein the first device recommendation score indicates the matching degree of the environment near the put device and the content type;

Calculating a second device recommendation score for each candidate device according to the device delivery frequency included in the first statistics, wherein the second device recommendation score indicates the frequency with which the delivery device was previously used to deliver content;

determining a device recommendation score for each candidate device according to a weighted sum of the calculated first device recommendation score and the calculated second device recommendation score;

and determining a delivery device for delivering the delivery content among the plurality of alternative devices according to the determined device recommendation score.

4. The content delivery method according to claim 2, wherein the step of determining a delivery period for delivering the delivered content among a plurality of alternative periods using a delivery period recommendation model according to the acquired second statistical data comprises:

calculating a time period recommendation score for each alternative time period from the person flow data for each alternative time period included in the second statistical data and the maximum person flow data within one time period in the second statistical data;

and determining a delivery period for delivering the delivery content among the plurality of alternative periods according to the determined period recommendation score.

5. The content delivery method according to claim 2, wherein the step of determining delivery information using a delivery recommendation model according to the content delivery demand further comprises:

calculating the equipment recommendation score of each piece of alternative equipment according to the acquired first statistical data;

calculating a time period recommendation score of each alternative time period according to the acquired second statistical score;

determining a delivery device and a delivery period for delivering the delivery content from among the plurality of candidate devices and the plurality of candidate periods according to a weighted sum of the device recommendation score of each candidate device and the period recommendation score of each candidate period.

6. The content delivery method according to any one of claims 1 to 5, wherein the content delivery demand includes a delivery area,

the step of determining the release content by using the release recommendation model according to the content release requirement comprises the following steps:

and generating the delivery content matched with the personnel characteristics indicated by the peripheral personnel characteristic data by using an artificial intelligent model according to the peripheral personnel characteristic data of at least one delivery device included in the delivery area and the content delivery requirement.

7. A content delivery apparatus comprising:

a communication module configured to: receiving user input including content delivery requirements;

a processing module configured to: responding to the user input, and determining release information and release content by using a release recommendation model according to the content release requirement;

a launch module configured to: and delivering the delivery content according to the delivery information.

8. The content delivery device of claim 7, wherein the delivery recommendation model comprises a delivery device recommendation model and/or a delivery period recommendation model,

wherein the processing module is configured to determine the delivery information using a delivery recommendation model according to the content delivery demand by:

9. The content delivery device of claim 8, wherein the processing module is configured to determine a delivery device for delivering the delivery content from among a plurality of candidate devices using a delivery device recommendation model according to the acquired first statistics by:

10. The content delivery device of claim 8, wherein the processing module is configured to determine a delivery period for delivering the delivered content from the acquired second statistical data using a delivery period recommendation model among a plurality of alternative periods by:

11. The content delivery device of claim 8, wherein the processing module is configured to determine the delivery information using a delivery recommendation model according to the content delivery demand by:

12. The content delivery apparatus according to any one of claims 7 to 11, wherein the content delivery demand includes a delivery area,

wherein the processing module is configured to determine the delivery content using a delivery recommendation model according to the content delivery demand by:

13. An electronic device, comprising:

at least one processor;

at least one memory storing computer-executable instructions,

wherein the computer executable instructions, when executed by the at least one processor, cause the at least one processor to perform the content delivery method of any one of claims 1 to 6.

14. A computer readable storage medium, wherein instructions in the computer readable storage medium, when executed by at least one processor, cause the at least one processor to perform the content delivery method of any one of claims 1 to 6.