A multi-channel digital content intelligent distribution method, device and storage medium based on membrane computing

Through the multi-channel digital content intelligent distribution method based on membrane computing, the problem of low digital content distribution efficiency in the prior art is solved, and the processing speed and user satisfaction are improved by optimizing the distribution strategy, ensuring the smoothness and quality of the distribution process.

CN118779534BActive Publication Date: 2024-11-08CHENGDU LANSER HUIYIN CULTURE MEDIA CO LTD
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202411266534.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-11
Publication Date
2024-11-08
Estimated Expiration
2044-09-11

AI Technical Summary

Technical Problem

In the prior art, digital content distribution efficiency is low, making it difficult to meet users' needs for high-quality and high-speed content access.

Method used

Using a multi-channel digital content intelligent distribution method based on membrane computing, a multi-objective constraint optimization function is established by extracting the data characteristics of digital content, determining the membrane layer structure, and optimizing the distribution strategy through the communication rules between the main membrane and the sub-film Maximize distribution efficiency and user satisfaction and minimize distribution costs.

Benefits of technology

It improves the processing speed and efficiency of content distribution, accurately match user needs, improves user satisfaction, and ensures the smoothness of the distribution process and content quality.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118779534B_ABST
    Figure CN118779534B_ABST
Patent Text Reader

Abstract

The present invention discloses a multi-channel digital content intelligent distribution method, device and storage medium based on membrane computing, and relates to the field of membrane computing technology. The method comprises: step one, extracting data features of digital content and establishing a multi-objective constraint optimization function; step two, determining the membrane layer structure, extracting data features based on the digital content type to set the initial population in the membrane; step three, setting a selection method based on membrane computing, and screening out main membrane population elements through communication rules; step four, setting an intelligent distribution strategy according to the main membrane population elements, and realizing a multi-channel distribution method for digital content; dividing different membrane layers through a membrane computing model, and realizing intelligent scheduling of the digital content distribution process through the communication rules of each membrane layer, which can more accurately match user needs and content and improve user satisfaction.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of digital content intelligent distribution, and in particular relates to a multi-channel digital content intelligent distribution method, device and storage medium based on membrane computing. Background Art

[0002] The essence of membrane computing is to abstract the different functional organs of cells into membrane functions to achieve cell-like computing capabilities. The membrane structure in the cell-type P system can be regarded as a modular processing method, and each membrane layer is responsible for completing a specific task. In digital content distribution, the processing flow can also be divided into multiple modules, each module is responsible for processing specific content or performing specific tasks. The parallel characteristics in membrane computing can also provide reference for digital content distribution. During the distribution process, parallel processing technology can be used to process multiple contents or tasks at the same time to improve distribution efficiency.

[0003] With the rapid growth of digital media content and the increasing demand of users for high-quality, high-speed content access, traditional digital content distribution networks can no longer meet the demand. Therefore, intelligent multi-channel digital content distribution networks have gradually emerged and become one of the key technologies to solve modern network transmission problems. Intelligent multimedia content distribution network technology is widely used in online video, streaming services, virtual reality, augmented reality and other fields. Through intelligent distribution, the content in these fields can be transmitted to user devices faster and more stably, improving user experience and satisfaction. Summary of the invention

[0004] The purpose of the present invention is to provide a multi-channel digital content intelligent distribution method, device and storage medium based on membrane computing, which are used to solve the technical problem of low content distribution efficiency in the prior art.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] A multi-channel digital content intelligent distribution method based on membrane computing, comprising:

[0007] Step 1: Extract the data features of digital content and establish a multi-objective constraint optimization function; Multi-channel distribution means that digital content needs to be delivered to users through multiple channels such as the Internet, social media, and mobile applications. Each channel has its own unique transmission characteristics, user groups, and feedback mechanisms. The extracted data features of digital content include: distribution efficiency, user satisfaction, and distribution cost. Maximizing distribution efficiency and user satisfaction, and minimizing distribution cost are determined as the objective function. Digital content resource restrictions, content compliance, and channel characteristics are used as constraints to construct a multi-objective constraint optimization function. When there are M types of digital content, the specific expression of the multi-objective constraint optimization function is as follows:

[0008]

[0009] Wherein, i represents the i-th digital content type, k represents the k-th distribution channel, M represents a total of M digital content types, and N represents a total of N distribution channels;

[0010] represents the average distribution efficiency of digital content of the i-th digital content type in the k-th channel, measured by the data distribution speed indicator;

[0011] represents the average user satisfaction of the digital content of the i-th digital content type in the k-th channel, measured by the user's favorable comment rate, that is, the ratio of the number of favorable comments of the digital content to the total number of views;

[0012] represents the average distribution cost of digital content of the i-th digital content type in the k-th channel, directly using cost as the measurement standard;

[0013] w k (i) represents the average distribution quantity of digital content of the i-th digital content type in the k-th channel;

[0014] represents a channel parameter and δ(t) represents the impulse function.

[0015] Step 2: Determine the membrane layer structure, extract data features based on the digital content type to set the initial population in the membrane; adopt the membrane structure of the cell-type P system. When there are N distribution channels, the membrane structure includes a main membrane, N sub-membranes and 1 auxiliary membrane. The main membrane is used to receive digital content distribution requests and distribution results from each sub-membrane, and coordinate the data flow between the sub-membranes to ensure the smooth distribution process. The auxiliary membrane is used to recycle elements that the main membrane does not want. Each sub-membrane corresponds to a distribution channel, and the distribution strategy corresponding to the digital content type is extracted during the distribution of digital content in different channels.

[0016] According to the historical data of distribution channels, in the distribution process of different channels, the distribution strategy of each digital content is composed of the average distribution efficiency Average user satisfaction Average distribution cost As a feature, establish a distribution strategy feature dataset for each digital content For digital content types that cannot be distributed in a certain channel, it is represented in the data feature set of the channel as Each channel contains M data features, expressed as F(k) = {f1(k), ..., f i (k), …, f M(k)}, define the value function for optimizing the distribution strategy of multi-channel digital content. The specific expression of the value function is as follows:

[0017]

[0018] Where \(t(i)\) represents the distribution time of digital content type \(i\), and \(n(i)\) represents the individual value of digital content type \(i\). Calculate the value function for all types of digital content in each channel. Each channel screens out the \(X\) types of digital content with the largest value function values, where \(X < M\), and ensure that the value function values of all channels screened out cover all types of digital content. Retain the corresponding feature dataset and set it as the in-membrane population of the corresponding sub-membrane of the channel. The set of in-membrane populations of the sub-membrane is represented as \(C(k)=\{v(1,k),\ldots,v(i,k),\ldots,v(x,k)\}\).

[0019] Step 3: Set the selection method based on membrane computing, and screen out the main membrane population elements through communication rules; through the communication between the main membrane and the sub-membranes, compare the differences in the value functions of the same type of digital content distributed through different channels, and screen out the distribution channel with the largest corresponding value function for each type of digital content. The specific method is as follows:

[0020] Each type of digital content \(i\) corresponds to an in-membrane population of a sub-membrane. The in-membrane population corresponding to each type of digital content \(i\) contains at most 3 value function elements. Set the initial population in the main membrane as \(U=(u(1),\ldots,u(i),\ldots,u(M))\), where \(u(i)=\{v x (i,k x ),v y (i,k y ),v z (i,k z )\}, where \(x\), \(y\), and \(z\) correspond to the \(x\)th, \(y\)th, and \(z\)th distribution channels respectively, and \(v x (i,k x )\geq v y (i,k y )\geq v z (i,k z ). The values of the 3 value function elements contained in the initial population are 0. Through the communication between the main membrane and the sub-membranes, update the elements contained in each population. Among them, the sub-membrane contains \(X\) populations, and each population represents a value function element. When communicating with the main membrane, each population will find the corresponding population included in the main membrane and compare the sizes of the value function values. When the value function value in the sub-membrane population is greater than or equal to the value function value of the corresponding population in the main membrane, add the value function value of the corresponding sub-membrane into the main membrane population, replace the element with the smallest value function value in the corresponding main membrane population, and mark the distribution channel of the sub-membrane element. The specific communication rules are as follows:

[0021] In the main membrane u(i) = {v x (i,k x ), v y (i,k y ), v z (i,k z )} and the communication rules of v(i, k) in the submembrane:

[0022] v(i, k)<v z (i,k z )→u(i)={v x (i,k x ),v y (i,k y ),v z (i,k z )}

[0023] v y (i,k y )>v(i,k)≥v z (i,k z )→u(i)={v x (i,k x ),v y (i,k y ),v(i,k)}

[0024] v x (i,k x )>v(i,k)≥v y (i,k y )→u(i)={v x (i,k x ),v(i,k),v y (i,k y )}

[0025] v(i, k)≥v x (i,k x )→u(i)={v(i,k),v x (i,k x ),v y (i,k y )}

[0026] Through the above communication rules, after the main membrane communicates with all sub-membranes, each main membrane population element obtained is u(i) = {v(i, k1), v(i, k2), v(i, k3)}.

[0027] Step 4: According to the main film population elements, set the intelligent distribution strategy to realize the multi-channel distribution method of digital content; after step 3, for each type of digital content, the three largest value function elements can be matched from the main film, and the distribution channel corresponding to each element is known. By setting the digital content distribution ratio function, the intelligent distribution strategy is realized. The distribution strategy implementation method is as follows:

[0028] For digital content of type i, according to its corresponding population element value u(i)={v(i, k1), v(i, k2), v(i, k3)} in the main membrane, the distribution ratio of this type of digital content in different channels is divided, and the specific steps include:

[0029] The channel corresponding to each element is determined by the population element value u(i)={v(i, k1), v(i, k2), v(i, k3)}, and the distribution channels k1, k2, and k3 corresponding to the digital content of type i are set, and the corresponding population element values ​​are population elements v(i, k1), v(i, k2), and v(i, k3), respectively. The digital content of type i is divided into three parts according to the distribution channel, and each part is distributed through different channels, where the division ratio is as follows:

[0030]

[0031] Among them A k1 (i) represents the distribution ratio of digital content of type i in distribution channel k1, A k2 (i) represents the distribution ratio of digital content of type i in distribution channel k2, A k3 (i) represents the distribution ratio of digital content of type i in distribution channel k3, a1, a2, and a3 represent the corresponding channel variables, and ensure that A k1 (i)+A k2 (i)+A k3 (i) = 1. Through artificial intelligence algorithms, by adjusting the channel variables corresponding to a1, a2, and a3, the distribution ratio is adjusted to obtain the best distribution strategy and achieve the maximum benefit of digital content.

[0032] For channels with preset distribution upper limits, for example, restrictions on the publishing frequency, quality of digital content or audience size of digital content publishers, when the digital content passing through the channel reaches the limit, all population element values ​​of the corresponding channels in the main membrane and the auxiliary membrane are adjusted to 0, and then the main membrane communicates with the auxiliary membrane, and the communication rules are consistent with the communication rules between the main membrane and the sub-membrane, and the main membrane population element values ​​are updated, and then the above-mentioned distribution strategy implementation method is used to obtain the optimal distribution strategy.

[0033] The multi-channel digital content intelligent distribution device based on membrane computing includes:

[0034] Multi-objective constraint optimization function module: used to determine the multi-objective constraint optimization function;

[0035] Membrane structure establishment module: used to determine the membrane structure and set the initial population in the membrane;

[0036] Population element determination module: used to communicate with all sub-membranes through the main membrane to determine the population elements of the main membrane;

[0037] Distribution strategy intelligent generation module: used to adjust the distribution ratio of digital content in different channels and obtain the distribution strategy.

[0038] A computer-readable storage medium stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute a multi-channel digital content intelligent distribution method based on film computing.

[0039] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:

[0040] 1. The present invention divides different membrane layers through a membrane computing model, and realizes intelligent scheduling of the digital content distribution process through the communication rules of each membrane layer. This distributed computing method can effectively improve the processing speed and efficiency of content distribution, can more accurately match user needs and content, and improve user satisfaction;

[0041] 2. The present invention adopts membrane computing method, and by establishing multi-objective constraint optimization function and feature extraction, it can effectively extract feature subsets, automatically screen and evaluate the distributed content, and ensure the quality and accuracy of the distributed content.

[0042] 3. The present invention optimizes the distribution strategy of multi-channel digital content by determining the film layer structure, establishing a feature data set and defining a value function, and defining the communication rules between film layers, thereby realizing and coordinating the data flow between the film layers and ensuring the smooth progress of the distribution process. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0044] Figure 1 A step diagram of a multi-channel digital content intelligent distribution method based on membrane computing is shown;

[0045] Figure 2 The system structure diagram of a multi-channel digital content intelligent distribution device based on membrane computing is shown. DETAILED DESCRIPTION

[0046] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0047] Example 1

[0048] like Figure 1 As shown, this embodiment provides a multi-channel digital content intelligent distribution method based on membrane computing, which specifically includes the following steps:

[0049] Step 1: Extract the data features of digital content and establish a multi-objective constraint optimization function; Multi-channel distribution means that digital content needs to be delivered to users through multiple channels such as the Internet, social media, and mobile applications. Each channel has its own unique transmission characteristics, user groups, and feedback mechanisms. The extracted data features of digital content include: distribution efficiency, user satisfaction, and distribution cost. Maximizing distribution efficiency and user satisfaction, and minimizing distribution cost are determined as the objective function. Digital content resource restrictions, content compliance, and channel characteristics are used as constraints to construct a multi-objective constraint optimization function. When there are M types of digital content, the specific expression of the multi-objective constraint optimization function is as follows:

[0050]

[0051] Wherein, i represents the i-th digital content type, k represents the k-th distribution channel, M represents a total of M digital content types, and N represents a total of N distribution channels;

[0052] represents the average distribution efficiency of digital content of the i-th digital content type in the k-th channel, measured by the data distribution speed indicator;

[0053] The average user satisfaction of the digital content of the i-th digital content type in the k-th channel is measured by the user's favorable comment rate, that is, the ratio of the number of favorable comments of the digital content to the total number of views;

[0054] represents the average distribution cost of digital content of the i-th digital content type in the k-th channel, directly using cost as the measurement standard;

[0055] w k (i) represents the average distribution quantity of digital content of the i-th digital content type in the k-th channel;

[0056] represents a channel parameter, and δ(t) represents an impulse function.

[0057] Step 2: Determine the membrane structure, extract data features based on the digital content type to set the initial population inside the membrane; adopt the membrane structure of the cellular P system. When there are N distribution channels, the membrane structure includes a main membrane, N sub-membranes, and 1 auxiliary membrane. The main membrane is used to receive the digital content distribution requests and distribution results from each sub-membrane, and coordinate the data flow between each sub-membrane to ensure the smooth progress of the distribution process. The auxiliary membrane is used to recycle the elements not wanted by the main membrane. Each sub-membrane corresponds to a distribution channel, and the distribution strategy corresponding to the digital content type is extracted during the distribution process of the digital content in different channels.

[0058] According to the historical data of the distribution channels, during the distribution process in different channels, the distribution strategy of each type of digital content is determined by the average distribution efficiency average user satisfaction average distribution cost as features to establish a distribution strategy feature dataset for each type of digital content For the digital content type that cannot be distributed in a certain channel, its data characteristics in this channel are represented as Each channel contains M data feature sets, denoted as F(k) = {f1(k), …, f i (k), …, f M (k)}. Define a value function to optimize the distribution strategy of multi-channel digital content. The specific expression of the value function is as follows:

[0059]

[0060] where t(i) represents the distribution time of digital content type i, and n(i) represents the individual value of digital content type i. Calculate the value function for all types of digital content in each channel. Each channel screens out the X types of digital content with the largest value function values, where X < M, and ensure that the value function values of all screened channels cover all types of digital content. Retain the corresponding feature dataset and set it as the population inside the membrane of the corresponding sub-membrane of this channel. The set of populations inside the membrane of the sub-membrane is denoted as C(k) = {v(1, k), …, v(i, k), …, v(x, k)}.

[0061] Step 3: Set the selection method based on membrane computing, screen out the elements of the main membrane population through communication rules; through the communication between the main membrane and the sub-membranes, compare the differences in the value functions of the same type of digital content distributed through different channels, and screen out the distribution channel with the largest value function for each type of digital content. The specific method is as follows:

[0062] Each digital content i corresponds to a population in a sub-membrane. The population in the sub-membrane corresponding to each digital content i contains at most 3 value function elements. The initial population in the main membrane is set to U = (u(1), ..., u(i), ..., u(M)), where u(i) = {v x (i,k x ), v y (i,k y ), v z (i,k z )}, x, y, z correspond to the xth, yth, and zth distribution channels respectively, and v x (i,k x )≥v y (i,k y )≥v z (i,k z ), the initial population contains 3 value function elements with a value of 0. Through the communication between the main membrane and the sub-membrane, the elements contained in each population are updated. The sub-membrane contains X populations, each of which represents a value function element. When communicating with the main membrane, each population will find the corresponding population included in the main membrane and compare the value function values. When the value function value in the sub-membrane population is greater than or equal to the value function value of the corresponding population in the main membrane, the value function value of the corresponding sub-membrane is added to the main membrane population, replacing the element with the smallest value function value in the corresponding main membrane population, and marking the distribution channel of the sub-membrane element. The specific communication rules are as follows:

[0063] In the main membrane u(i) = {v x (i,k x ), v y (i,k y ), v z (i,k z )} and the communication rules of v(i, k) in the submembrane:

[0064] v(i, k)<v z (i,k z )→u(i)={v x (i,k x ),v y (i,k y ),v z (i,k z )}

[0065] v y (i,k y )>v(i,k)≥v z (i,k z )→u(i)={v x (i,k x ),v y(i,k y ),v(i,k)}

[0066] v x (i,k x )>v(i,k)≥v y (i,k y )→u(i)={v x (i,k x ),v(i,k),v y (i,k y )}

[0067] v(i, k)≥v x (i,k x )→u(i)={v(i,k),v x (i,k x ),v y (i,k y )}

[0068] Through the above communication rules, after the main membrane communicates with all sub-membranes, each main membrane population element obtained is u(i) = {v(i, k1), v(i, k2), v(i, k3)}.

[0069] Step 4: According to the main film population elements, set the intelligent distribution strategy to realize the multi-channel distribution method of digital content; after step 3, for each type of digital content, the three largest value function elements can be matched from the main film, and the distribution channel corresponding to each element is known. By setting the digital content distribution ratio function, the intelligent distribution strategy is realized. The distribution strategy implementation method is as follows:

[0070] For digital content of type i, according to its corresponding population element value u(i)={v(i, k1), v(i, k2), v(i, k3)} in the main membrane, the distribution ratio of this type of digital content in different channels is divided, and the specific steps include:

[0071] The channel corresponding to each element is determined by the population element value u(i)={v(i, k1), v(i, k2), v(i, k3)}, and the distribution channels k1, k2, and k3 corresponding to the digital content of type i are set, and the corresponding population element values ​​are the population element values ​​v(i, k1), v(i, k2), and v(i, k3). The digital content of type i is divided into three parts according to the distribution channel, and each part is distributed through different channels, where the division ratio is as follows:

[0072]

[0073] Among them A k1 (i) represents the distribution ratio of digital content of type i in distribution channel k1, Ak2 (i) represents the distribution ratio of digital content of type i in distribution channel k2, A k3 (i) represents the distribution ratio of digital content of type i in distribution channel k3, a1, a2, and a3 represent the corresponding channel variables, and ensure that A k1 (i)+A k2 (i)+A k3 (i) = 1. Through artificial intelligence algorithms, by adjusting the channel variables corresponding to a1, a2, and a3, the distribution ratio is adjusted to obtain the best distribution strategy and achieve the maximum benefit of digital content.

[0074] For channels with preset distribution upper limits, for example, restrictions on the publishing frequency, quality of digital content or audience size of digital content publishers, when the digital content passing through the channel reaches the limit, all population element values ​​of the corresponding channels in the main membrane and the auxiliary membrane are adjusted to 0, and then the main membrane communicates with the auxiliary membrane, and the communication rules are consistent with the communication rules between the main membrane and the sub-membrane, and the main membrane population element values ​​are updated, and then the above-mentioned distribution strategy implementation method is used to obtain the optimal distribution strategy.

[0075] Embodiment 2

[0076] like Figure 2 As shown, a multi-channel digital content intelligent distribution device based on membrane computing specifically includes:

[0077] Multi-objective constraint optimization function module: Determine the objective function of maximizing distribution efficiency and user satisfaction and minimizing distribution cost, and take digital content resource restrictions, content compliance and channel characteristics as constraints to construct a multi-objective constraint optimization function. When there are M types of digital content, the specific expression of the multi-objective constraint optimization function is as follows:

[0078]

[0079] Wherein, i represents the i-th digital content type, k represents the k-th distribution channel, M represents a total of M digital content types, and N represents a total of N distribution channels;

[0080] represents the average distribution efficiency of digital content of the i-th digital content type in the k-th channel, measured by the data distribution speed indicator;

[0081] represents the average user satisfaction of the digital content of the i-th digital content type in the k-th channel, measured by the user's favorable comment rate, that is, the ratio of the number of favorable comments of the digital content to the total number of views;

[0082] Denote the average distribution cost of digital content of the \(i\)-th digital content type in the \(k\)-th channel, directly using cost as the measurement standard;

[0083] w k (i) Denote the average distribution quantity of digital content of the \(i\)-th digital content type in the \(k\)-th channel;

[0084] Denote a channel parameter, and \(\delta(t)\) denotes the impulse function.

[0085] Membrane structure establishment module: Adopt the membrane structure of the cell-like P system. When there are \(N\) distribution channels, the membrane structure includes a main membrane, \(N\) sub-membranes, and 1 auxiliary membrane. The main membrane is used to receive the digital content distribution requests and distribution results from each sub-membrane, and coordinate the data flow between each sub-membrane to ensure the smooth progress of the distribution process. The auxiliary membrane is used to recycle the elements not needed by the main membrane. Each sub-membrane corresponds to a distribution channel, and extracts the distribution strategy of the corresponding digital content type during the distribution process of digital content in different channels.

[0086] According to the historical data of the distribution channels, define a value function for optimizing the distribution strategy of multi-channel digital content. The specific expression of the value function is as follows:

[0087]

[0088] Where \(t\) represents the distribution time of digital content type \(i\), \(n\) represents the individual value of digital content type \(i\). Calculate the value function for all types of digital content in each channel. Each channel screens out the \(X\) types of digital content with the largest value function values, \(X < M\), and ensures that the value function values of all channels screened out include all types of digital content. Retain the corresponding feature data set and set it as the in-membrane population of the corresponding sub-membrane of the channel, denoted as \(C(k)=\{v(1,k),\ldots,v(i,k),\ldots,v(x,k)\}\).

[0089] Population element determination module: Through the communication between the main membrane and the sub-membranes, compare the differences in the value functions of the same type of digital content distributed through different channels, and screen out the distribution channel with the largest value function for each type of digital content. The specific method is as follows:

[0090] Through the communication between the main membrane and the sub-membranes, update the elements included in each population. When communicating with the main membrane, each population will find the corresponding population included in the main membrane and compare the magnitudes of the value function values. When the value function value in the sub-membrane population is greater than or equal to the value function value of the corresponding population in the main membrane, add the value function value of the corresponding sub-membrane into the main membrane population, replace the element with the smallest value function value in the corresponding main membrane population, and mark the distribution channel of the sub-membrane element. The specific communication rules are as follows:

[0091] In the main membrane u(i) = {v x (i,k x ), v y (i,k y ), v z (i,k z )} and the communication rules of v(i, k) in the submembrane:

[0092] v(i, k)<v z (i,k z )→u(i)={v x (i,k x ),v y (i,k y ),v z (i,k z )}

[0093] v y (i,k y )>v(i,k)≥v z (i,k z )→u(i)={v x (i,k x ),v y (i,k y ),v(i,k)}

[0094] v x (i,k x )>v(i,k)≥v y (i,k y )→u(i)={v x (i,k x ),v(i,k),v y (i,k y )}

[0095] v(i, k)≥v x (i,k x )→u(i)={v(i,k),v x (i,k x ),v y (i,k y )}

[0096] Through the above communication rules, after the main membrane communicates with all sub-membranes, each main membrane population element obtained is u(i) = {v(i, k1), v(i, k2), v(i, k3)}.

[0097] Distribution strategy intelligent generation module: for digital content of type i, according to its corresponding population element value u(i)={v(i, k1), v(i, k2), v(i, k3)} in the main membrane, the distribution ratio of this type of digital content is divided in different channels. The specific steps include:

[0098] The channel corresponding to each element is determined by the population element value u(i)={v(i, k1), v(i, k2), v(i, k3)}, and the distribution channels k1, k2, and k3 corresponding to the digital content of type i are set, and the corresponding population element values ​​are the population element values ​​v(i, k1), v(i, k2), and v(i, k3). The digital content of type i is divided into three parts according to the distribution channel, and each part is distributed through different channels, where the division ratio is as follows:

[0099]

[0100] Among them A k1 (i) represents the distribution ratio of digital content of type i in distribution channel k1, A k2 (i) represents the distribution ratio of digital content of type i in distribution channel k2, A k3 (i) represents the distribution ratio of digital content of type i in distribution channel k3, a1, a2, and a3 represent the corresponding channel variables, and ensure that A k1 (i)+A k2 (i)+A k3 (i) = 1. Through artificial intelligence algorithms, by adjusting the channel variables corresponding to a1, a2, and a3, the distribution ratio is adjusted to obtain the best distribution strategy and achieve the maximum benefit of digital content.

[0101] For channels with preset distribution upper limits, for example, restrictions on the publishing frequency, quality of digital content or audience size of digital content publishers, when the digital content passing through the channel reaches the limit, all population element values ​​of the corresponding channels in the main membrane and the auxiliary membrane are adjusted to 0, and then the main membrane communicates with the auxiliary membrane, and the communication rules are consistent with the communication rules between the main membrane and the sub-membrane, and the main membrane population element values ​​are updated, and then the above-mentioned distribution strategy implementation method is used to obtain the optimal distribution strategy.

[0102] In the implementation process, each step of the above method embodiment can be completed by an integrated logic circuit of hardware in a processor or an instruction in the form of software. The above processor can be a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a ready-made programmable gate array or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component. The methods and steps disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or any conventional processor. In combination with the method steps disclosed in the present application, it can be directly embodied as a hardware decoding processor to execute, or it can be executed by a combination of hardware and software modules in a decoding processor. The software module can be located in a mature storage medium in the field such as a random access memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in a memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0103] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

[0104] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A multi-channel digital content intelligent distribution method based on membrane computing, characterized in that: Including: Step 1: Extract the data features of digital content and establish a multi-objective constrained optimization function; Determine the objective function to maximize the distribution efficiency and user satisfaction, and minimize the distribution cost. Take the digital content resource limit, content compliance, and channel characteristics as constraints to construct a multi-objective constrained optimization function. When there are M types of digital content, the specific expression of the multi-objective constrained optimization function is as follows: Where i represents the i-th digital content type, k represents the k-th distribution channel, M represents a total of M digital content types, N represents a total of N distribution channels, and during the distribution of the i-th digital content type through the k-th distribution channel, f i a (k) represents the average distribution efficiency, f i b (k) represents the average user satisfaction, f i c (k) represents the average distribution cost, w k (i) represents the average distribution quantity; represents a channel parameter, δ(t) represents the impulse function; Step 2: Determine the membrane structure and set the initial population in the membrane based on the data features extracted according to the digital content type; Adopt the membrane structure of the cellular P system. When there are N distribution channels, the membrane structure includes a main membrane, N sub-membranes, and 1 auxiliary membrane. The main membrane is used to receive the digital content distribution requests and distribution results from each sub-membrane and coordinate the data flow between the sub-membranes. The auxiliary membrane is used to recycle the elements not needed by the main membrane. Each sub-membrane corresponds to a distribution channel, and the distribution strategy corresponding to the digital content type is extracted during the distribution process of the digital content in different channels; Step 3: Set the selection method based on membrane computing and screen out the main membrane population elements through communication rules; Step 4: Set an intelligent distribution strategy according to the main membrane population elements to implement the multi-channel distribution method of digital content.

2. The multi-channel digital content intelligent distribution method based on membrane computing according to claim 1 is characterized in that: Including: The specific method for setting the initial population in the membrane based on the data features extracted according to the digital content type in Step 2 includes: By the average distribution efficiency f i a (k), average user satisfaction f i b (k), average distribution cost f i c (k) As a feature, establish a distribution strategy feature dataset f i (k) = {f i a (k), f i b (k), f i c (k)}, each channel contains M data feature sets, expressed as F(k) = {f1(k), ..., f i (k), …, f M (k)}, define the value function to optimize the distribution strategy of multi-channel digital content. The specific expression of the value function is as follows: Where t(i) represents the distribution time of digital content type i, and n(i) represents the individual value of digital content type i. Calculate the value function for all types of digital content in each channel. Each channel screens out the X types of digital content with the largest value function values, where X < M, ensuring that the value function values of all screened channels cover all types of digital content. Retain the corresponding feature data set and set it as the in-membrane population of the corresponding sub-membrane of the channel. The set of in-membrane populations of the sub-membranes is represented as C(k) = {v(1, k), …, v(i, k), …, v(X, k)}.

3. The multi-channel digital content intelligent distribution method based on membrane computing according to claim 1 is characterized in that: Including: The specific content of Step 3 includes: Each digital content i corresponds to a population in a sub-membrane. The population in the sub-membrane corresponding to each digital content i contains at most 3 value function elements. The initial population in the main membrane is set to U = (u(1), ..., u(i), ..., u(M)), where u(i) = {v x (i,k x ), v y (i,k y ), v z (i,k z )}, x, y, z correspond to the xth, yth, and zth distribution channels respectively, and v x (i,k x )≥v y (i,k y )≥v z (i,k z ), the three value function elements contained in the initial population are 0, and the population elements of the main membrane are updated through the communication between the main membrane and the sub-membrane. In the main membrane, u(i) = {v x (i,k x ), v y (i,k y ), v z (i,k z )} and the communication rules of v(i, k) in the submembrane: v(i,k)<v z (i,k z )→u(i)={v x (i,k x ),v y (i,k y ),v z (i,k z )} v y (i,k y )>v(i,k)≥v z (i,k z )→u(i)={v x (i,k x ),v y (i,k y ),v(i,k)} v x (i,k x )>v(i,k)≥v y (i,k y )→u(i)={v x (i,k x ),v(i,k),v y (i,k y )} v(i,k)≥v x (i,k x )→u(i)={v(i,k),v x (i,k x ),v y (i,k y )} After the main membrane communicates with all sub-membranes through the above communication rules, each main membrane population element obtained.

4. The multi-channel digital content intelligent distribution method based on membrane computing according to claim 1 is characterized in that: Including: The specific content of Step 4 includes: The implementation method of the distribution strategy includes: setting the distribution channels k1, k2, k3 corresponding to the digital content of type i, and the corresponding population element values are the population element values v(i, k1), v(i, k2), v(i, k3). Divide the digital content of type i into 3 parts according to the distribution channels, and each part is distributed through different channels. The division ratio is as follows: Among them A k1 (i) represents the distribution ratio of digital content of type i in distribution channel k1, A k2 (i) represents the distribution ratio of digital content of type i in distribution channel k2, A k3 (i) represents the distribution ratio of digital content of type i in distribution channel k3, a1, a2, and a3 represent the corresponding channel variables, and ensure that A k1 (i)+A k2 (i)+A k3 (i) = 1, through artificial intelligence algorithm, according to the distribution restrictions of different channels, the distribution ratio is adjusted by adjusting the channel variables corresponding to a1, a2, and a3 to obtain the corresponding distribution strategy; For the channel with a preset distribution limit, when the digital content reaches the distribution limit of this channel, adjust all the population element values corresponding to this channel in the main membrane and the auxiliary membrane to 0. Then, through the communication between the main membrane and the auxiliary membrane, update the main membrane population element values, and then through the above distribution strategy implementation method, obtain the corresponding distribution strategy.

5. A multi-channel digital content intelligent distribution device based on membrane computing, applied to a multi-channel digital content intelligent distribution method based on membrane computing as claimed in any one of claims 1 to 4, characterized in that: Including: Multi-objective constrained optimization function module: used to determine the multi-objective constrained optimization function; Membrane structure establishment module: used to determine the membrane structure and set the initial population in the membrane; Population element determination module: used to determine the main membrane population elements through the communication between the main membrane and all sub-membranes; Distribution strategy intelligent generation module: used to adjust the distribution ratio of digital content in different channels and obtain the distribution strategy.

6. A computer-readable storage medium, characterized in that: It stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute a multi-channel digital content intelligent distribution method based on film computing as described in any one of claims 1-4.

Citation Information

Patent Citations

  • Cloud resource scheduling optimization method based on improved particle swarm optimization of membrane system

    CN107203412A

  • Resource allocation method and system, allocation model training method and electronic equipment

    CN117389719A

  • Methods and Systems for Identifying Cross-Platform Audiences and Optimizing Campaigns

    US20180096397A1