Cloud disk content propagation value evaluation method, device, equipment, medium and product

Abstract

The invention discloses a cloud disk content propagation value evaluation method, device and equipment, a medium and a product. The method comprises the following steps: constructing a personal knowledge gene pool of each cloud disk user based on an operation behavior of each cloud disk user and a personal knowledge base; constructing a social structure expression map of the cloud disk circle according to the personal knowledge gene banks of all the cloud disk users; performing cross-structure gene hybridization operation on the social structure expression map of the cloud disk circle and the gene segment of the cloud disk user of the to-be-shared content to generate a fusion gene segment; and performing propagation simulation based on the social structure expression map of the fusion gene segment and the cloud disk circle to obtain all propagation paths of the to-be-shared content and a propagation potential information entropy flux score of each propagation path, determining a target propagation path, and calculating a propagation value vector of the to-be-shared content. According to the method, fusion modeling is carried out based on user behaviors and social structures of circles, and beforehand evaluation of content propagation potential, path evolution prediction and propagation value vector feedback are realized.

Description

Technical Field

[0001] This invention relates to the field of data analysis technology, and in particular to a method, apparatus, equipment, medium and product for assessing the value of cloud storage content dissemination. Background Technology

[0002] With the gradual promotion and application of the "circles" function in cloud storage products, users can share files in a targeted manner within social graphs such as "family circles, office circles, study circles, and friend circles." Currently, cloud storage content propagation prediction mainly relies on content recommendation mechanisms based on tag matching and propagation prediction models based on response data. However, in the cloud storage circle function, user behavior exhibits obvious circle-level isolation characteristics and structured semantic preferences, making it impossible for traditional methods to model the adaptation evolution path of cloud storage content propagation within the circle structure. Furthermore, in the cloud storage circle scenario, content propagation is characterized by strong response delays and complex path evolution. Traditional methods cannot distinguish the propagation value of short-term responsive content (such as trending materials) and long-term accumulated content (such as learning resources and family materials) within the circle, making it difficult for users to make optimal decisions before sharing. Summary of the Invention

[0003] The purpose of this invention is to provide a method, apparatus, device, medium, and product for assessing the dissemination value of cloud storage content. Based on the fusion modeling of user behavior and the social structure of social circles, it enables pre-assessment of content dissemination potential, prediction of path evolution, and feedback of dissemination value vector, thereby solving the problems of coarse granularity of dissemination adaptability modeling and single dimension of dissemination value assessment in current cloud storage content sharing.

[0004] To achieve the above objectives, embodiments of the present invention provide a method for evaluating the dissemination value of cloud storage content, including: Based on the operational behavior and personal knowledge base of each cloud disk user, a personal knowledge gene base is constructed for each cloud disk user; wherein, the personal knowledge gene base includes multiple gene fragments. Based on the personal knowledge gene databases of all cloud storage users, a social structure expression graph of the cloud storage circle is constructed; wherein, the cloud storage circle includes multiple cloud storage users; The social structure representation graph of the cloud storage circle is used to perform cross-structure gene hybridization operation with the gene fragments of the cloud storage users who intend to share content, to generate fused gene fragments. Based on the fusion gene fragment and the social structure expression map of the cloud disk circle, a propagation simulation was performed to obtain all propagation paths of the content to be shared and the propagation potential information entropy flux score of each propagation path. The target propagation path is determined based on the propagation potential information entropy flux score, and the propagation value vector of the content to be shared is calculated.

[0005] As an improvement to the above scheme, the user's operational behavior includes the user's semantic preferences, activity level, comment frequency, and sharing frequency in the cloud storage community.

[0006] As an improvement to the above solution, the construction of a personal knowledge gene database for each cloud disk user based on their operational behavior and personal knowledge base includes: For each cloud drive user, multiple gene fragments are constructed based on the user's operational behavior and the file semantic tags in the personal knowledge base; Personal knowledge gene fragment sequences are generated based on the multiple gene fragments to obtain the personal knowledge gene library.

[0007] As an improvement to the above scheme, the gene fragment includes four dimensions: circle interaction chemotaxis strength, circle semantic evolution heterogeneity index, circle content diffusion preference factor, and circle semantic phenotypic encoding set.

[0008] As an improvement to the above scheme, the method for calculating the circle interaction chemotaxis strength is as follows: Obtain the cumulative frequency of the circle structure interaction behavior corresponding to the gene fragment in the historical record; The circle interaction chemotaxis intensity of the gene fragment is calculated based on the cumulative frequency and the preset circle adaptation weight.

[0009] As an improvement to the above scheme, the formula for calculating the circle interaction chemotaxis strength is as follows: ; In the formula, Represents gene fragments The intensity of circle interaction chemism; Indicates cumulative frequency; This indicates the preset circle adaptation weight.

[0010] As an improvement to the above scheme, the calculation method of the circle semantic evolution heterogeneity index is as follows: Obtain the feature vector of semantic interaction of the gene fragment in consecutive circles within the historical window; The semantic evolution heterogeneity index of the gene fragment is calculated based on the semantic difference between adjacent feature vectors.

[0011] As an improvement to the above scheme, the formula for calculating the circle semantic evolution heterogeneity index is as follows: ; In the formula, Represents gene fragments Circle semantic evolution heterogeneity index; Indicates the first Feature vectors of user interactions between secondary cloud storage and communities; This indicates the total number of interactions between cloud drive users and the community within the history window. Indicates the first Feature vectors of user interactions between secondary cloud storage and communities; It is a positive number.

[0012] As an improvement to the above scheme, the calculation method for the circle content diffusion preference factor is as follows: Traverse the historical circle content sharing and dissemination records corresponding to the gene fragment, and extract behavioral features within a preset time window; The behavioral characteristics are weighted statistically to calculate the circle content diffusion preference factor of the gene fragment.

[0013] As an improvement to the above scheme, the formula for calculating the circle content diffusion preference factor is as follows: ; In the formula, Represents gene fragments The content diffusion preference factor in the circle; Indicates the length of the time window; This indicates the number of people whose content posted by cloud storage users within the same circle becomes visible in the first week. This indicates the frequency with which content posted by a cloud storage user within a circle is responded to by other cloud storage users. express The weights; This indicates the frequency with which content posted by cloud storage users within the community is restructured, tagged, or recreated. express The weights; This indicates the frequency of cross-circle forwarding of content posted by users within the same cloud storage circle.

[0014] As an improvement to the above scheme, the calculation method for the circle semantic phenotypic encoding set is as follows: Multimodal semantic analysis is performed on the files that cloud drive users browse, comment on, forward, and recreate in the circle to extract semantic tags and count the frequency of occurrence of the semantic tags in the circle; The semantic propagation weight of the semantic tag is determined based on the frequency of occurrence and the number of times the semantic tag is forwarded, re-expressed, and reconstructed by other cloud disk users. Based on the semantic labels and the semantic propagation weights, the set of circle semantic phenotype codes for the gene fragment is calculated.

[0015] As an improvement to the above scheme, the calculation formula for the circle semantic phenotypic encoding set is as follows: ; In the formula, Represents gene fragments The set of circle semantic phenotypic encodings; Indicates semantic tags; Represents the semantic propagation weight of semantic tags; This indicates the frequency of semantic tags within the circle; Indicates the number of semantic tags; This indicates the number of times a semantic tag has been forwarded, re-expressed, or reconstructed by other cloud storage users.

[0016] As an improvement to the above solution, the step of constructing a social structure representation graph of the cloud storage community based on the personal knowledge gene base of all cloud storage users includes: Based on the personal knowledge gene database of all cloud disk users within the cloud disk community, a social structure expression map of the cloud disk community is constructed; wherein, the social structure expression map includes multiple social gene expression fragments.

[0017] As an improvement to the above scheme, the social gene expression fragment includes four dimensions: circle topology information flux density field, circle semantic phenotype polarization gradient, circle topology dynamic resilience entropy gradient, and circle gene expression spectrum.

[0018] As an improvement to the above solution, the step of performing cross-structural gene hybridization operations on the social structure representation graph of the cloud storage circle and the gene fragments of the cloud storage users who intend to share content to generate fused gene fragments includes: Obtain candidate gene fragments from cloud drive users who intend to share content; Calculate the semantic similarity between the candidate gene fragment and each social gene expression fragment in the social structure expression map of the cloud disk circle; In response to the semantic similarity being greater than a first preset threshold, gene cross-fusion operation is performed on the candidate gene fragment and the social gene expression fragment to obtain the fused gene fragment; In response to the semantic similarity being less than or equal to a first preset threshold, the cloud drive user who intends to share the content is prompted that the candidate gene fragment is not suitable for sharing in the cloud drive community.

[0019] As an improvement to the above scheme, the step of calculating the semantic similarity between the candidate gene fragment and each social gene expression fragment in the social structure expression map of the cloud disk circle includes: Calculate the first similarity between the circle semantic phenotype encoding set of the candidate gene fragment and the circle semantic phenotype polarization gradient of the social gene expression fragment; Calculate the second similarity between the circle interaction chemotaxis intensity of the candidate gene fragment and the circle topological information flux density field of the social gene expression fragment; Calculate the third similarity between the circle content diffusion preference factor of the candidate gene fragment and the circle topological dynamics structure resilience entropy gradient of the social gene expression fragment; The semantic similarity is obtained by weighted summation of the first similarity, the second similarity, and the third similarity.

[0020] As an improvement to the above scheme, the propagation simulation based on the fused gene fragment and the social structure expression map of the cloud disk circle is used to obtain all propagation paths of the content to be shared and the propagation potential information entropy flux score of each propagation path, including: Using the fusion gene fragment as a viral RNA sequence and the social structure expression map of the cloud storage circle as a host social environment, the infection decoherence propagation path of the fusion gene fragment in the cloud storage circle, the local immunity judgment of the circle, the mutation path projection prediction, and the incubation period assessment and measurement were simulated. Based on the infection decoherence propagation path, the local immunity judgment of the circle, the mutation path projection prediction, and the incubation period assessment, all propagation paths of the content to be shared are obtained, and the propagation potential information entropy flux score of each propagation path is calculated.

[0021] As an improvement to the above scheme, the simulation of the infection decoherence propagation path of the fusion gene fragment in the cloud disk circle, the local immunity judgment of the circle, the mutation path projection prediction, and the latency period assessment measurement includes: Based on the circle semantic phenotype encoding set of the fused gene fragments, social gene expression fragments with circle semantic phenotype polarization gradients higher than a second preset threshold are found in the social structure expression map of the cloud disk circle, and used as initial infection nodes to form an initial infection node set. Based on the initial set of infected nodes, the evolution of the infection decoherence propagation path of the fusion gene fragment is simulated; In each evolution of the propagation path, a local immunity judgment mechanism is executed synchronously to detect whether the cloud disk users in the cloud disk circle have developed herd immunity to the fused gene fragment. Perform mutation path projection prediction to determine whether the fused gene fragment may be semantically reconstructed, recreated, and relabeled by cloud disk users in the cloud disk circle, and evolve into new propagation primitives; During the evolution of each propagation path, latency period assessment and measurement are performed simultaneously to simulate the response delay of the fused gene fragment from publication to the first effective response in the cloud disk circle.

[0022] As an improvement to the above scheme, the formula for calculating the propagation potential information entropy flux score is as follows: ; In the formula, Information entropy and flux score represent the propagation potential of a propagation path; The average semantic cosine similarity between the set of circle semantic phenotype encodings in the personal knowledge gene base of each cloud disk user node in the propagation path and the fused gene fragment; The circle topology information flux density field represents the virtual circle, which is composed of cloud disk user nodes in the propagation path. The circle semantic phenotypic polarization gradient represents the virtual circle; This represents the proportion of immune nodes in the transmission pathway multiplied by the immunosuppressive attenuation factor. This represents the percentage of highly mutated nodes in the propagation path multiplied by the mutation path enhancement factor. All represent weights; This represents the latent decay term.

[0023] As an improvement to the above scheme, the propagation potential information entropy flux score is proportional to the propagation probability of the propagation path.

[0024] As an improvement to the above scheme, determining the target propagation path based on the propagation potential information entropy flux score includes: Propagation paths with a propagation potential information entropy flux score greater than a third preset threshold are selected as the target propagation paths.

[0025] As an improvement to the above scheme, the formula for calculating the propagation value vector of the content to be shared is as follows: ; In the formula, This represents the propagation value vector of the content to be shared; Indicates the scale of short-term transmission; Indicates the scale of the medium-term spread; Indicates the scale of long-term transmission; All represent weights.

[0026] This invention also provides a cloud storage content dissemination value assessment device, comprising: The first construction module is used to construct a personal knowledge gene library for each cloud disk user based on the user's operation behavior and personal knowledge base; wherein, the personal knowledge gene library includes multiple gene fragments. The second construction module is used to construct a social structure expression graph of the cloud storage circle based on the personal knowledge gene database of all the cloud storage users; wherein, the cloud storage circle includes multiple cloud storage users; The gene fusion module is used to perform cross-structural gene hybridization operations on the social structure expression map of the cloud disk circle and the gene fragments of the cloud disk users who intend to share the content, and generate fused gene fragments. The propagation simulation module is used to perform propagation simulation based on the fused gene fragment and the social structure expression map of the cloud disk circle, to obtain all propagation paths of the content to be shared and the propagation potential information entropy flux score of each propagation path; The value assessment module is used to determine candidate propagation paths based on the propagation potential information entropy flux score, and to calculate the propagation value vector of the content to be shared.

[0027] This invention also provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the cloud disk content dissemination value assessment method described above.

[0028] This invention also provides a computer-readable storage medium, which includes a stored computer program, wherein the computer program, when running, controls the device where the computer-readable storage medium is located to execute the cloud disk content dissemination value assessment method described above.

[0029] This invention also provides a computer program product, which includes a computer program or computer instructions. When the computer program or computer instructions are executed by a processor, they implement the cloud disk content dissemination value assessment method described above.

[0030] Compared to existing technologies, the beneficial effects of the cloud storage content dissemination value assessment method, apparatus, device, medium, and product provided by this invention are as follows: A personal knowledge gene library is constructed for each cloud storage user based on their operational behavior and personal knowledge base; wherein the personal knowledge gene library includes multiple gene fragments; a social structure expression graph of a cloud storage circle is constructed based on the personal knowledge gene libraries of all cloud storage users; wherein the cloud storage circle includes multiple cloud storage users; a cross-structure gene hybridization operation is performed between the social structure expression graph of the cloud storage circle and the gene fragments of the cloud storage user whose content is to be shared, generating a fused gene fragment; a dissemination simulation is performed based on the fused gene fragment and the social structure expression graph of the cloud storage circle to obtain all dissemination paths of the content to be shared and the dissemination potential information entropy flux score for each dissemination path; the target dissemination path is determined based on the dissemination potential information entropy flux score, and the dissemination value vector of the content to be shared is calculated. This invention constructs a four-tuple feature dimension for information dissemination through four-dimensional fragment modeling of social genes. The content to be shared is modeled as an information dissemination entity and injected into the social structure expression graph of the circle. It simulates the infection evolution path and dissemination response delay in different social environments, and predicts the dissemination variation path branches of the content in the social structure by combining the knowledge reconstruction ability of circle members. Finally, it outputs the dissemination value vector under short, medium and long time windows, realizing an intelligent recommendation mechanism that visualizes the dissemination path of content dissemination, measures the response cycle, and predicts circle adaptation. Attached Figure Description

[0031] Figure 1 This is a flowchart illustrating a preferred embodiment of a cloud storage content dissemination value assessment method provided by the present invention; Figure 2 This is a flowchart illustrating another preferred embodiment of a cloud storage content dissemination value assessment method provided by the present invention; Figure 3 This is a schematic diagram illustrating the construction of a personal knowledge gene base in a cloud storage content dissemination value assessment method provided by the present invention; Figure 4 This is a schematic diagram illustrating the construction of a social structure expression graph of cloud storage circles in a cloud storage content dissemination value assessment method provided by the present invention; Figure 5 This is a schematic diagram of a preferred embodiment of a cloud storage content dissemination value assessment device provided by the present invention; Figure 6 This is a schematic diagram of a preferred embodiment of a terminal device provided by the present invention. Detailed Implementation

[0032] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0033] Please see Figure 1 and Figure 2 , Figure 1 This is a flowchart illustrating a preferred embodiment of a cloud storage content dissemination value assessment method provided by the present invention. Figure 2 This is a flowchart illustrating another preferred embodiment of a cloud storage content dissemination value assessment method provided by the present invention. The cloud storage content dissemination value assessment method includes: S1. Based on the operation behavior and personal knowledge base of each cloud disk user, construct a personal knowledge gene base for each cloud disk user; wherein, the personal knowledge gene base includes multiple gene fragments. S2, construct a social structure representation graph of the cloud storage circle based on the personal knowledge gene database of all the cloud storage users; wherein, the cloud storage circle includes multiple cloud storage users; S3, perform cross-structural gene hybridization operation on the social structure representation graph of the cloud disk circle and the gene fragment of the cloud disk user to be shared to generate a fused gene fragment; S4. Based on the fusion gene fragment and the social structure expression map of the cloud disk circle, a propagation simulation is performed to obtain all propagation paths of the content to be shared and the propagation potential information entropy flux score of each propagation path. S5. Determine the target propagation path based on the propagation potential information entropy flux score, and calculate the propagation value vector of the content to be shared.

[0034] It should be noted that in this embodiment of the invention, cloud drive users are assumed to be DNA, and cloud drive communities are assumed to be chromosomes. Chromosomes are composed of different DNA molecules, representing that cloud drive community members are composed of different types of cloud drive users. The content of the file to be shared is then assumed to be an RNA virus. The process of the RNA virus infecting the chromosome is the process of the content to be shared spreading within the cloud drive community. This embodiment of the invention, by simulating the RNA infection process of a chromosome, determines whether the content to be shared can spread within the community and to how many people it can spread to.

[0035] In step S1, the construction of a personal knowledge gene database for each cloud disk user based on their operational behavior and personal knowledge base includes: S11, For each cloud disk user, construct multiple gene fragments based on the cloud disk user's operation behavior and the file semantic tags in the personal knowledge base; S12, Generate a personal knowledge gene fragment sequence based on the multiple gene fragments to obtain the personal knowledge gene library.

[0036] For details, please refer to Figure 3 , Figure 3 This is a schematic diagram illustrating the construction of a personal knowledge gene base in a cloud storage content dissemination value assessment method provided by this invention. In this embodiment of the invention, for each cloud storage user, multiple gene fragments are constructed based on the user's operational behavior and the semantic tags of files organized, labeled, and retrieved by the user in the AI ​​personal knowledge base. An interpretable and evolvable personal knowledge gene fragment sequence is generated from these multiple gene fragments, denoted as... This allows for the acquisition of a personal knowledge gene pool. The user's operational behavior includes semantic preferences in the content on the cloud drive community's homepage, activity level in clicking on advertisements / recommendations within the community, frequency of active comments, and frequency of secondary sharing.

[0037] Each gene segment It includes four dimensions, namely the intensity of circle interaction. Circle semantic evolution heterogeneity index Circle content diffusion preference factor and circle semantic phenotypic encoding set .

[0038] Furthermore, the calculation method for the circle interaction chemotaxis strength is as follows: Obtain the cumulative frequency of the circle structure interaction behavior corresponding to the gene fragment in the historical record; The circle interaction chemotaxis intensity of the gene fragment is calculated based on the cumulative frequency and the preset circle adaptation weight.

[0039] Specifically, the intensity of circle interaction trends This is used to measure a user's level of interaction and activity within a specific circle, such as frequent following, frequent clicking on circle ads, and low re-sharing. First, obtain gene fragments. The cumulative frequency of corresponding circle structure interaction behaviors in historical records Among them, cumulative frequency This includes: the frequency of users clicking on semantic tag cards for this type of content on the homepage of the circle; the increase in the number of similar circles followed by users within a statistical period; the cumulative number of times users click on recommended ad slots within the circle; and the number of times users create secondary content or reshare content within the circle. Subsequently, the cumulative frequency is analyzed. Add 1, take the logarithm to the base 2, and multiply by the preset circle adaptation weight. This weight is pre-set by the business based on its contribution to the circle propagation network according to its behavior. Through the above calculations, the gene fragment is finally obtained. The intensity of circle interaction tendency in the user's knowledge behavior system That is, the strength of circle interaction chemistry. The calculation formula is: ; In the formula, Represents gene fragments The intensity of circle interaction chemism; Indicates cumulative frequency; This indicates the preset circle adaptation weight.

[0040] Furthermore, the method for calculating the circle semantic evolution heterogeneity index is as follows: Obtain the feature vector of semantic interaction of the gene fragment in consecutive circles within the historical window; The semantic evolution heterogeneity index of the gene fragment is calculated based on the semantic difference between adjacent feature vectors.

[0041] Specifically, the heterogeneity index of circle semantic evolution. This is used to measure the evolution trend of a user's semantic behavior within a specific circle, and to determine whether their knowledge preferences are undergoing mutation, reconstruction, or cross-circle migration. First, gene fragments are extracted. Feature vectors of consecutive circular semantic interactions within a historical window (e.g., two weeks). .in, Indicates the first The feature vector of user interactions with circles (such as liking and commenting) in the secondary cloud drive includes: the semantic tag set of the overall shared content of the circle to which the current interaction occurs, the frequency of the user's re-expression of content in the circle (such as modifying tags and re-sharing), the exposure duration of circle content on the user's home screen, and the cosine similarity between the circle's semantic tags and the tags in the user's AI personal knowledge base. Subsequently, the sum of the absolute values ​​of the semantic differences between adjacent behavioral features is calculated as the numerator of the semantic heterogeneous evolution trend; the denominator is the maximum value among all adjacent feature semantic differences. To prevent division by zero, a very small positive number ε is added to the denominator, ultimately yielding the gene fragment. Circle semantic evolution heterogeneity index That is, the circle semantic evolution heterogeneity index. The calculation formula is: ; In the formula, Represents gene fragments Circle semantic evolution heterogeneity index; Indicates the first Feature vectors of user interactions between secondary cloud storage and communities; This indicates the total number of interactions between cloud drive users and the community within the history window. Indicates the first Feature vectors of user interactions between secondary cloud storage and communities; It is a positive number.

[0042] Furthermore, the calculation method for the circle content diffusion preference factor is as follows: Traverse the historical circle content sharing and dissemination records corresponding to the gene fragment, and extract behavioral features within a preset time window; The behavioral characteristics are weighted statistically to calculate the circle content diffusion preference factor of the gene fragment.

[0043] Specifically, the content diffusion preference factor within the circle This is used to assess the strength of a user's content dissemination preference and the ability to penetrate different circles. First, iterate through the gene fragments. The corresponding historical content sharing and dissemination records are extracted into the time series. arrive Within: The number of people who can see the content posted by this user within the circle in the first week. ; The frequency with which this user's posts receive responses (likes, comments, shares) from other users within the group. ; The frequency with which this user's posts are restructured, tagged, and recreated within the community ; Frequency of cross-circle forwarding of content posted by this user within the same circle (e.g., forwarding from the office circle to the learning circle); The above behavioral characteristics are weighted and statistically analyzed, and then... Considered as the basic propagation signal, It is given double the weight because it represents deep user engagement. It is weighted three times due to its chain-propagation effect. Finally, the above data are summed along the time axis and then divided by the time window length. To obtain gene fragments Circle content diffusion preference factor in historical performance That is, the content diffusion preference factor within the circle. The calculation formula is: ; In the formula, Represents gene fragments The content diffusion preference factor in the circle; Indicates the length of the time window; This indicates the number of people whose content posted by cloud storage users within the same circle becomes visible in the first week. This indicates the frequency with which content posted by a cloud storage user within a circle is responded to by other cloud storage users. express The weights; This indicates the frequency with which content posted by cloud storage users within the community is restructured, tagged, or recreated. express The weights; This indicates the frequency of cross-circle forwarding of content posted by users within the same cloud storage circle.

[0044] Furthermore, the calculation method for the circle semantic phenotypic encoding set is as follows: Multimodal semantic analysis is performed on the files that cloud drive users browse, comment on, forward, and recreate in the circle to extract semantic tags and count the frequency of occurrence of the semantic tags in the circle; The semantic propagation weight of the semantic tag is determined based on the frequency of occurrence and the number of times the semantic tag is forwarded, re-expressed, and reconstructed by other cloud disk users. Based on the semantic labels and the semantic propagation weights, the set of circle semantic phenotype codes for the gene fragment is calculated.

[0045] Specifically, the set of circle semantic phenotypic encodings This method is used to model the semantic phenotypic preference structure of users' content interactions within a specific circle. First, multimodal semantic analysis is performed on files that users browse, comment on, forward, and recreate within the circle to extract semantic tags. And count the frequency of its appearance in this circle. Subsequently, the frequency of the semantic tag is divided by the total frequency of all semantic tags for that user within that circle to obtain the frequency percentage. The number of times the semantic tag is reposted, re-expressed, or reconstructed by other users within that circle is also included. The semantic propagation weights are enhanced through the following functions: ; Ultimately, semantic tags With weighted semantic weights This is combined into a circle semantic phenotypic encoding set, resulting in the circle semantic phenotypic encoding set. That is, the set of semantic phenotypic encodings for circles. The calculation formula is: ; In the formula, Represents gene fragments The set of circle semantic phenotypic encodings; Indicates semantic tags; Represents the semantic propagation weight of semantic tags; This indicates the frequency of semantic tags within the circle; Indicates the number of semantic tags; This indicates the number of times a semantic tag has been forwarded, re-expressed, or reconstructed by other cloud storage users.

[0046] In step S2, constructing a social structure representation graph of the cloud storage community based on the personal knowledge gene base of all cloud storage users includes: S21. Based on the personal knowledge gene database of all cloud disk users in the cloud disk circle, construct the social structure expression map of the cloud disk circle; wherein, the social structure expression map includes multiple social gene expression fragments.

[0047] For details, please refer to Figure 4 , Figure 4 This is a schematic diagram illustrating the construction of a social structure representation graph of a cloud storage circle in a cloud storage content dissemination value assessment method provided by this invention. This embodiment of the invention is based on the personal knowledge gene database of all members of the cloud storage circle. In addition, features such as the number of zombie followers in the circle, the overlap of circles followed by members, and the number of KOLs and their followers within the circle are used to construct a social structure expression map of cloud storage circles. For example, cloud storage communities (such as family communities, office communities, and study communities) can be viewed as a social ecosystem unit, based on the personal knowledge gene pool of all members within the community. Data is used to construct a social structure graph representing the user's social circle, denoted as... , of which each A fragment represents a segment of social gene expression. The fragment is based on the personal knowledge gene pool of all members in the circle. After performing regular clustering, it is further processed into a semantic primitive that can express behavior. Expressible behavioral semantic primitive fragments consist of four dimensions of information: circle topology information flux density field. Circle semantic phenotypic polarization gradient Circle topological dynamics resilience entropy gradient Circle gene expression profile Compound generation.

[0048] Furthermore, the circle topological information flux density field This is used to measure the flux density of information dissemination within a circle, reflecting whether the circle possesses good information flow capabilities and content carrying potential. First, define the observation window for information flux. In the formula, The observation period is set for the system (e.g., the past 7 days). Then, statistics are compiled within the circle of that window. Total number of sharing actions by all members under the segment. File interaction frequency (Including browsing, commenting, liking, forwarding, etc.), semantic cosine similarity of circle members' attention to other circles. Number of KOLs in the circle Compared to its average number of fans Finally, the above data is weighted and merged. By combining this with a time decay function, a circle topological information flux density field with structural sensitivity and cross-sphere propagation prediction capability is constructed. That is, the circle topological information flux density field. The calculation formula is:

[0049] Furthermore, the circle semantic phenotypic polarization gradient The degree of polarization used to characterize the semantic preferences of content within a circle is a key dimension for assessing whether content can adapt to the semantic ecosystem of that circle. Firstly, from the perspective of the circle itself... Extract semantic tag set from the historical sharing content of all members under the segment. (Extracted from cloud drive file names), then each tag is counted. Propagation density in this circle This refers to the sharing frequency and average dissemination rate of the content corresponding to that tag. Subsequently, the dissemination density of all tags is considered. Knowledge tag frequency and the cross-response strength of members to this semantic tag in other circles. (i.e., the frequency of sharing similar semantic content in other circles), the circle semantic phenotypic polarization gradient is calculated. That is, the circle semantic phenotypic polarization gradient. The calculation formula is:

[0050] Furthermore, the entropy gradient of the circle topological dynamics resilience This is used to determine whether the target circle has a good information carrying capacity. First, obtain information from the target circle's internal database. User personal knowledge gene database node degree of all members under the segment .in, Indicates the first in the circle Each member. Secondly, the proportion of "zombie followers" in this circle was statistically analyzed. This refers to the percentage of circle members who have consistently shown no interaction, semantic output, or forwarding behavior, yet are marked as "active users." Subsequently, the average node degree of the individual knowledge gene pool of all members in the circle is calculated. This parameter reflects the overall information activity level of the circle. Next, the node degree of each member is... With average node degree After normalization, we get Then, a weighted average of the normalized value within the circle is calculated. This serves as the initial input for structural stability. Then, an adjustable structural stability gain factor is applied. The above results are then enhanced nonlinearly. Finally, they are substituted into a logistic function. A structural stability score between 0 and 1 is generated, which serves as the loop topological dynamics resilience entropy gradient. That is, the entropy gradient of the topological dynamics of the circle. The calculation formula is:

[0051] Furthermore, the gene expression profile of the circle In order to be in the circle The personal knowledge gene pool of all members under the segment The expression spectrum obtained by weighted averaging of vectors reflects the overall behavioral characteristics and knowledge preferences of the community. The weight of each user is allocated based on whether the member is a KOL and the number of followers. Finally, The calculation formula is:

[0052] In the formula, This indicates the weight of a member as a KOL in the circle, and the weight is allocated based on the number of users' followers.

[0053] The social structure representation graph of the cloud storage community constructed using the above methods This allows for the modeling of social circles as evolutionary social gene maps, possessing the ability to structurally evaluate the content dissemination environment. For example, a social structure representation map of cloud storage circles. The expression is as follows:

[0054] In step S3, the social structure representation graph of the cloud storage circle is used to perform cross-structural gene hybridization operation with the gene fragments of the cloud storage users who intend to share content, generating fused gene fragments, including: S31, Obtain candidate gene fragments of cloud drive users who intend to share content; S32, Calculate the semantic similarity between the candidate gene fragment and each social gene expression fragment in the social structure expression map of the cloud disk circle; S33, in response to the semantic similarity being greater than a first preset threshold, perform gene cross-fusion operation on the candidate gene fragment and the social gene expression fragment to obtain the fused gene fragment; S34, in response to the semantic similarity being less than or equal to a first preset threshold, the cloud drive user who intends to share the content is prompted that the candidate gene fragment is not suitable for sharing in the cloud drive community.

[0055] It should be noted that, in this embodiment of the invention, the cloud storage user who intends to share content is regarded as a separate social ecosystem unit, and its gene fragments are compared with the expression map of the social structure of the target circle's cloud storage circle. Perform cross-structural gene hybridization operations to simulate the propagation and fitness of the user's genes within the circle, and generate fusion gene fragments. . fusion gene fragments As the initial seed for propagation, it provides input for the evolution of subsequent propagation paths.

[0056] Specifically, in this embodiment of the invention, the knowledge base of the publisher (i.e., the cloud drive user who intends to share the content) is used. Extract candidate gene fragments from the content that is currently intended to be shared to the community. : ; in, : Indicates the circle interaction chemotaxis strength of this segment, calculated by step S1; : Represents the circle semantic evolution heterogeneity index of the segment, which is calculated by step S1; : Represents the circle content diffusion preference factor of this segment, which is calculated in step S1; : Represents the set of circle semantic phenotypic codes for this segment, which is calculated in step S1.

[0057] Further, in step S32, the semantic similarity between the candidate gene fragment and each social gene expression fragment in the social structure expression map of the cloud disk circle is calculated, including: S321, Calculate the first similarity between the circle semantic phenotype encoding set of the candidate gene fragment and the circle semantic phenotype polarization gradient of the social gene expression fragment; S322, Calculate the second similarity between the circle interaction chemotaxis intensity of the candidate gene fragment and the circle topological information flux density field of the social gene expression fragment; S323, Calculate the third similarity between the circle content diffusion preference factor of the candidate gene fragment and the circle topological dynamics structure resilience entropy gradient of the social gene expression fragment; S324, the first similarity, the second similarity and the third similarity are weighted and summed to obtain the semantic similarity.

[0058] Specifically, in the embodiments of the present invention, when calculating candidate gene fragments... Social structure representation map of circles All social gene fragments semantic similarity First, candidate gene fragments are extracted from cloud drive users who intend to share content. Circle semantic phenotypic encoding set and social gene fragments in the target circle circle semantic phenotypic polarization gradient And using the cosine similarity function Semantic similarity is calculated between the two entities to obtain a first similarity score, which serves as the basic semantic matching value. Next, candidate gene fragments are extracted. Circle interaction tropism strength With social gene fragments Circle topology information flux density field The normalized Euclidean distance was used as the behavioral intensity similarity, i.e., the second similarity. Next, candidate gene fragments are extracted. Circle content diffusion preference factor With social gene fragments Circle topological dynamics structure toughness entropy gradient The Pearson correlation coefficient was used to calculate the matching degree of their propagation patterns, which was then used as the third similarity. Finally, the three similarity values ​​are multiplied by their respective weights. , , ,in, Through weighted fusion of the above three parts, candidate gene fragments are finally obtained. Social structure representation map of circles Social Gene Fragments semantic similarity :

[0059] If semantic similarity (Business setting value, default 0.7), then candidate gene fragments will be selected. Social gene expression fragments Perform gene cross-fusion operations to obtain fused gene fragments. :

[0060] in, This is a weighted gene fragment fusion operation. This is the fusion control coefficient.

[0061] If semantic similarity If the message indicates that the content to be shared is not suitable for dissemination within this circle, the user is advised to choose a different content to share.

[0062] This invention constructs a framework that includes the intensity of circle interaction chemistries by linking users' cloud drive operation behavior with semantic tags in an AI personal knowledge base. Circle semantic evolution heterogeneity index Circle content diffusion preference factor Circle semantic phenotypic encoding set A personal knowledge gene pool with four-dimensional features Furthermore, by clustering and fusing the behavioral data of circle members, a topological information flux density field is generated. Semantic phenotypic polarization gradient Topological dynamics resilience entropy gradient Gene expression profile Equal-dimensional circle social structure representation graph Subsequently, based on a semantic similarity threshold judgment mechanism, the user behavior fragments of the content to be shared are compared with... Perform cross-structural gene hybridization operations to generate fusion gene fragments. As the initial seed for propagation, this invention provides a basis for the evolution of propagation paths. Compared to traditional content recommendation mechanisms based on coarse-grained tags or user profiles, this invention constructs a four-dimensional gene fragment model of user behavior and circle social structure, integrating semantic tags, propagation tendencies, structural adaptability, and mutation capabilities to achieve multi-level evolutionary modeling of content propagation adaptability. This invention supports dynamic matching and path prediction between content and cloud storage circle structure, effectively avoiding semantic mismatches and propagation path failures, and significantly improving the accuracy and structural interpretability of content propagation. It solves the problems of semantic mismatch between user content and circle structure and unpredictable propagation efficiency, improving the structural adaptability and propagation success rate of content recommendation, and has significant technological advancements and practical application value.

[0063] In step S4, the propagation simulation is performed based on the social structure expression map of the fused gene fragment and the cloud disk circle to obtain all propagation paths of the content to be shared and the propagation potential information entropy flux score of each propagation path, including: S41, using the fusion gene fragment as a viral RNA sequence and the social structure expression map of the cloud disk circle as a host social environment, simulate the infection decoherence propagation path of the fusion gene fragment in the cloud disk circle, the circle's local immunity judgment, the mutation path projection prediction, and the incubation period assessment and measurement. S42, based on the infection decoherence propagation path, the circle local immunity judgment, the mutation path projection prediction, and the incubation period assessment measurement, obtain all propagation paths of the content to be shared, and calculate the propagation potential information entropy flux score for each propagation path.

[0064] Specifically, in this embodiment of the invention, the content of the file to be shared is considered as an information virus. and its corresponding fusion gene fragment The core RNA sequence of this viral virus represents the social structure of the target community's cloud storage network. As a host social environment, the simulation yields results across four dimensions: infection decoherence propagation path of the content to be shared (equivalent to fused gene fragments) in the target circle, local immunity assessment within the circle, mutation path projection prediction, and latency period evaluation. This results in all possible propagation paths of the content to be shared, as well as its propagation potential information entropy flux score. .

[0065] Furthermore, the simulation of the fusion gene fragment's infection decoherence propagation path within the cloud disk circle, the circle's local immunity assessment, mutation path projection prediction, and latency period evaluation includes: Based on the circle semantic phenotype encoding set of the fused gene fragments, social gene expression fragments with circle semantic phenotype polarization gradients higher than a second preset threshold are found in the social structure expression map of the cloud disk circle, and used as initial infection nodes to form an initial infection node set. Based on the initial set of infected nodes, the evolution of the infection decoherence propagation path of the fusion gene fragment is simulated; In each evolution of the propagation path, a local immunity judgment mechanism is executed synchronously to detect whether the cloud disk users in the cloud disk circle have developed herd immunity to the fused gene fragment. Perform mutation path projection prediction to determine whether the fused gene fragment may be semantically reconstructed, recreated, and relabeled by cloud disk users in the cloud disk circle, and evolve into new propagation primitives; During the evolution of each propagation path, latency period assessment and measurement are performed simultaneously to simulate the response delay of the fused gene fragment from publication to the first effective response in the cloud disk circle.

[0066] Specifically, in this embodiment of the invention, the fusion gene fragment As the core RNA sequence of the virus, it is injected into the social structure map of the target circle. In the middle, the evolution of the propagation path is initiated: 1) Based on fusion gene fragments Circle semantic phenotypic encoding set (Calculated from step S2), starting in the circle social structure graph Searching for circle semantic phenotypic polarization gradients (Calculated from step S2) Higher than the second preset threshold Social gene fragments As the initial infection node of this virus, a set of initial infection nodes is formed. The matching degree calculation method is as described in step S32. The calculation method.

[0067] 2) Once the initial set of infected nodes is obtained The simulation begins by examining the evolution of the infection and re-coherence propagation path of the content to be shared, starting from the initial node. The path extension in the graph follows the logic below: a) For each social gene segment If its circle topological dynamic structure toughness entropy gradient High (threshold defined by business needs), and its circle topology information flux density field If the value exceeds a set threshold, it indicates that the node has good propagation capabilities, and the social gene fragment will be... Expanding into an intermediate node in the propagation path, this social gene fragment The corresponding set of user IDs is added to the initialized propagation path set. ; b) If a certain social gene segment Circle topological dynamics resilience entropy gradient A lower threshold (defined by business needs) indicates a weaker information-carrying capacity within the circle, which will limit the social gene segments. The propagation depth of all associated paths, with a maximum of 2 propagation nodes, and the social gene fragments are included. The corresponding set of user IDs is identified as having low propagation potential, and is included in the initial propagation path set. Exclude user ID nodes after its second-level offspring to prevent the path from expanding indefinitely in low-activity circles.

[0068] 3) During each evolution of the propagation path, a local immunity judgment mechanism is executed simultaneously to detect whether circle members have developed herd immunity to the content: a) Detect whether there are any items in the circle with a semantic similarity higher than the content to be shared. If the semantic content has been spread multiple times in the circle but the response rate is low (e.g., comments, reposts, and likes are all lower than the circle average), it is determined that the circle has local immunity to this content type. Extract the set of all user IDs involved in the historical dissemination records. b) Detect the initial propagation path set The corresponding social gene fragments in each path Circle gene expression profile Calculate its personal knowledge gene pool corresponding to all user IDs involved in the historical dissemination records. Middle circle semantic phenotypic encoding set The cosine similarity is used; if the similarity is greater than a threshold, then the social gene segment is considered valid. This belongs to the immune phenomenon point; c) If there are immune phenomenon nodes, the propagation weight of the path will be reduced, it will be marked as an inefficient propagation path, and the response decay factor of the semantic label in the propagation path will be injected into the scoring function for subsequent path selection. d) If more than half of the nodes in a certain propagation path are marked as immune nodes, then the path is determined to be an invalid path and is not included in the final path set.

[0069] 4) Next, perform mutation path projection prediction to determine whether the content to be shared is likely to undergo semantic reconstruction, re-creation, tag rewriting, or other operations by users within the circle, thereby evolving into new propagation primitives: a) Detect the initial propagation path set Each social gene segment If the circle semantic evolution heterogeneity index of all members in its fragment is A higher threshold (defined by business needs) indicates that this social gene segment... The corresponding members possess strong re-expression abilities (such as frequently performing secondary processing, content editing, and tag reconstruction). b) Mark paths containing such members as highly mutated paths, and inject mutated branches into these paths during the evolution of the propagation path. That is, treat these members as separate social ecological units and compare their circle's social structure representation graph with the target circle's cloud storage circle social structure representation graph. Perform cross-structural gene hybridization to generate a novel fusion gene fragment. (See step S3 for details), and step S4 is re-executed accordingly. The newly generated path branch will be connected to the initialized propagation path set. In this context, it serves as a variant branch.

[0070] 5) During the evolution of each propagation path, a latency period assessment is conducted simultaneously to simulate the response delay of the content to be shared within the community from publication to the first effective response (such as the first like, comment, or share): a) Extract each social gene fragment from all candidate paths All members' first response time in history (i.e., the time elapsed after the first like, comment, or share following registration), and calculate the average first response time. If the average first response time exceeds the threshold defined by the business logic, then this path is defined as a potential latent decay path.

[0071] b) For a pathway defined as a potential latent decay path, if a certain social gene segment in that pathway... Circle topology information flux density field The value is relatively low (based on a business-defined threshold), and the circle topology dynamics resilience entropy is also low. If the value is too low (based on a business-defined threshold), it is determined that there will be latent attenuation in the content propagation along this path. A latent attenuation path label is added to this path, and the propagation potential information entropy flux score of this path is subsequently calculated. At this time, a latent decay term needs to be added to reduce the propagation weight under this path.

[0072] 6) After completing the evolution of all propagation paths in the above steps, a final set of propagation paths for the content to be shared within the target audience is obtained. Each path Includes the set of user nodes along the propagation path. .

[0073] 7) For each transmission path Calculate its propagation potential information entropy flux score This score reflects the probability of this propagation path occurring, incorporating the following influencing factors: Based on semantic matching degree of fused gene fragments; The topological information flux density field of the circle corresponding to the social gene fragment in the circle structure and the polarization gradient of the circle semantic phenotype. Are there inefficient transmission paths? Does it contain highly variable paths? Does a latent decay path exist? All the above factors are combined using a multimodal weighted fusion calculation to obtain the propagation potential information entropy flux score for each propagation path. The calculation formula is as follows: ; In the formula, Information entropy and flux score represent the propagation potential of a propagation path; This represents the personal knowledge gene pool of each cloud disk user node in the propagation path. The set of circle semantic phenotypic encodings The average semantic cosine similarity with the fused gene fragment; The circle topology information flux density field represents the virtual circle (the calculation method is detailed in step S2). The virtual circle is composed of each cloud disk user node in the propagation path. The circle semantic phenotypic polarization gradient represents the virtual circle (the calculation method is detailed in step S2); This represents the proportion of immune nodes in the transmission path multiplied by an immunosuppressive attenuation factor, where the immunosuppressive attenuation factor is calculated from the personal knowledge gene pool of all cloud disk users in the virtual circle. The average value of the circle content diffusion preference factor (see step S1 for the calculation method). This represents the percentage of highly mutated nodes in the propagation path multiplied by the mutation path enhancement factor, where the mutation path factor is calculated by statistically analyzing the personal knowledge gene pools of all users with highly mutated nodes. The average value of the circle interaction chemotaxis intensity (see step S1 for the calculation method); All represent weights. ,in The preceding negative sign indicates the negative impact of immunosuppressive factors on transmission potential; Represents the latent decay term, where This specifies the number of users whose initial response time exceeds the average response time set by the service under this propagation path. The default value is 0.

[0074] It should be noted that the propagation potential information entropy flux score The numerical range is in Between these two factors, the information entropy flux score of the propagation potential is directly proportional to the propagation probability of the propagation path. The higher the information entropy flux score of the propagation potential, the greater the propagation probability of the corresponding propagation path, and the more valuable it is for propagation.

[0075] In step S5, determining the target propagation path based on the propagation potential information entropy flux score includes: Propagation paths with a propagation potential information entropy flux score greater than a third preset threshold are selected as the target propagation paths.

[0076] For example, the top N (e.g., top 3) propagation paths with the highest information entropy throughput score in terms of propagation potential are selected as target propagation paths. The top 3 target propagation paths with the greatest propagation potential are then fed back to the user interface for the user to decide whether to share, to which circle to share, and whether to optimize the file semantic tags. Users can choose the path with the highest probability of propagation from the path recommendations to share, thus achieving precise adaptation and path optimization for content propagation.

[0077] At the same time, the potential audience size of the content to be shared within the short, medium, and long-term time windows is calculated as the dissemination value vector of the content to be shared.

[0078] For example, the formula for calculating the propagation value vector of the content to be shared is: ; In the formula, This represents the propagation value vector of the content to be shared; Indicates the scale of short-term transmission; Indicates the scale of the medium-term spread; Indicates the scale of long-term transmission; All represent weights. .

[0079] Among them, the scale of short-term transmission This indicates that the content to be shared comes first. The predicted number of users that can be reached within a time window (e.g., 7 days) is constructed as follows: First, from the propagation path set generated in step S4 Filter out all information entropy flux scores with propagation potential (e.g., 0.6) path; Next, extract the historical first response time data for all user nodes along these paths. And the flux density field of the circle topology information of the circle it belongs to. This is used to determine whether the content can trigger an immediate response; If the historical first response time of user nodes in the path is generally less than 5 days, and the circle topology information flux density field If the number of paths is large, the system categorizes these paths as short-term propagation nodes and calculates the short-term propagation scale by summing the total number of user nodes for each path. .

[0080] Mid-term spread scale Indicates content in The predicted number of users that can be reached within a window (e.g., 30 days) is constructed using a method similar to short-term propagation scales. The main difference lies in the rating. The threshold for judgment is different from the threshold for judging the user's first response time in history. The threshold here is defined by the business and will not be repeated here.

[0081] Long-term spread scale Indicates content in The predicted number of users that can be reached within a window (e.g., 90 days) is constructed using a method similar to short-term propagation scales. The main difference lies in the rating. The threshold for judgment is different from the threshold for judging the user's first response time in history. The threshold here is defined by the business and will not be repeated here.

[0082] This invention, in its embodiments, models the content to be shared as an information virus and utilizes fused gene fragments. Social structure expression map of circles The study simulates four transmission pathways—infection decoherence transmission pathway, herd local immune suppression pathway, mutation evolution pathway, and latency period pathway—to construct a set of transmission pathways. And generate a propagation potential information entropy flux score for each propagation path. Subsequently based on The scoring system feeds back the top N paths with the greatest dissemination potential to the user interface, while also calculating the dissemination scale over short, medium, and long-term time windows to construct a dissemination value vector for the content to be shared. This invention generates a structured predictive value for the lifecycle of content dissemination, serving as a framework for predicting the spread of content. Compared to traditional methods that rely heavily on single scores or response statistics when assessing content dissemination potential, lacking the ability to model the hierarchical evolution of dissemination paths and time cycles, this invention constructs short-, medium-, and long-term dissemination scale predictions, combining dimensions such as path evolution, immunosuppression, mutation branching, and latency periods to generate a dissemination value vector. This vector can be dynamically fed back to the user, supporting dissemination path recommendations, circle selection, and tag optimization, significantly enhancing the predictability of content dissemination and the decision-making guidance capabilities for user interaction. It solves the problems of invisible, unpredictable, and unoptimizable content dissemination paths, improving the intelligence of path recommendations before content sharing, the perceptibility of dissemination trends, and the ability to assist user decision-making, possessing high accuracy in dissemination prediction and user interaction guidance capabilities.

[0083] Accordingly, the present invention also provides a cloud storage content dissemination value assessment device, which can realize all the processes of the cloud storage content dissemination value assessment method in the above embodiments.

[0084] Please see Figure 5 , Figure 5 This is a schematic diagram of a preferred embodiment of a cloud storage content dissemination value assessment device provided by the present invention. The cloud storage content dissemination value assessment device includes: The first construction module 501 is used to construct a personal knowledge gene library for each cloud disk user based on the operation behavior and personal knowledge base of each cloud disk user; wherein, the personal knowledge gene library includes multiple gene fragments. The second construction module 502 is used to construct a social structure expression graph of the cloud disk circle based on the personal knowledge gene database of all the cloud disk users; wherein, the cloud disk circle includes multiple cloud disk users; Gene fusion module 503 is used to perform cross-structural gene hybridization operation on the social structure expression map of the cloud disk circle and the gene fragment of the cloud disk user who intends to share the content, and generate a fused gene fragment. The propagation simulation module 504 is used to perform propagation simulation based on the fused gene fragment and the social structure expression map of the cloud disk circle to obtain all propagation paths of the content to be shared and the propagation potential information entropy flux score of each propagation path. The value assessment module 505 is used to determine candidate propagation paths based on the propagation potential information entropy flux score, and to calculate the propagation value vector of the content to be shared. Preferably, Preferably, the user's operational behavior includes the user's semantic preferences, activity level, comment frequency, and sharing frequency within the cloud storage community.

[0085] Preferably, the first construction module 501 is specifically used for: For each cloud drive user, multiple gene fragments are constructed based on the user's operational behavior and the file semantic tags in the personal knowledge base; Personal knowledge gene fragment sequences are generated based on the multiple gene fragments to obtain the personal knowledge gene library.

[0086] Preferably, the gene fragment includes four dimensions: circle interaction chemotaxis strength, circle semantic evolution heterogeneity index, circle content diffusion preference factor, and circle semantic phenotypic encoding set.

[0087] Preferably, the method for calculating the chemotaxis strength of the circle interaction is as follows: Obtain the cumulative frequency of the circle structure interaction behavior corresponding to the gene fragment in the historical record; The circle interaction chemotaxis intensity of the gene fragment is calculated based on the cumulative frequency and the preset circle adaptation weight.

[0088] Preferably, the formula for calculating the chemotaxis strength of the circle interaction is: ; In the formula, Represents gene fragments The intensity of circle interaction chemism; Indicates cumulative frequency; This indicates the preset circle adaptation weight.

[0089] Preferably, the method for calculating the circle semantic evolution heterogeneity index is as follows: Obtain the feature vector of semantic interaction of the gene fragment in consecutive circles within the historical window; The semantic evolution heterogeneity index of the gene fragment is calculated based on the semantic difference between adjacent feature vectors.

[0090] Preferably, the formula for calculating the circle semantic evolution heterogeneity index is: ; In the formula, Represents gene fragments Circle semantic evolution heterogeneity index; Indicates the first Feature vectors of user interactions between secondary cloud storage and communities; This indicates the total number of interactions between cloud drive users and the community within the history window. Indicates the first Feature vectors of user interactions between secondary cloud storage and communities; It is a positive number.

[0091] Preferably, the calculation method for the circle content diffusion preference factor is as follows: Traverse the historical circle content sharing and dissemination records corresponding to the gene fragment, and extract behavioral features within a preset time window; The behavioral characteristics are weighted statistically to calculate the circle content diffusion preference factor of the gene fragment.

[0092] Preferably, the formula for calculating the circle content diffusion preference factor is: ; In the formula, Represents gene fragments The content diffusion preference factor in the circle; Indicates the length of the time window; This indicates the number of people whose content posted by cloud storage users within the same circle becomes visible in the first week. This indicates the frequency with which content posted by a cloud storage user within a circle is responded to by other cloud storage users. express The weights; This indicates the frequency with which content posted by cloud storage users within the community is restructured, tagged, or recreated. express The weights; This indicates the frequency of cross-circle forwarding of content posted by users within the same cloud storage circle.

[0093] Preferably, the calculation method for the circle semantic phenotypic encoding set is as follows: Multimodal semantic analysis is performed on the files that cloud drive users browse, comment on, forward, and recreate in the circle to extract semantic tags and count the frequency of occurrence of the semantic tags in the circle; The semantic propagation weight of the semantic tag is determined based on the frequency of occurrence and the number of times the semantic tag is forwarded, re-expressed, and reconstructed by other cloud disk users. Based on the semantic labels and the semantic propagation weights, the set of circle semantic phenotype codes for the gene fragment is calculated.

[0094] Preferably, the calculation formula for the circle semantic phenotypic encoding set is: ; In the formula, Represents gene fragments The set of circle semantic phenotypic encodings; Indicates semantic tags; Represents the semantic propagation weight of semantic tags; This indicates the frequency of semantic tags within the circle; Indicates the number of semantic tags; This indicates the number of times a semantic tag has been forwarded, re-expressed, or reconstructed by other cloud storage users.

[0095] Preferably, the second building module 502 is specifically used for: Based on the personal knowledge gene database of all cloud disk users within the cloud disk community, a social structure expression map of the cloud disk community is constructed; wherein, the social structure expression map includes multiple social gene expression fragments.

[0096] Preferably, the social gene expression fragment includes four dimensions: circle topological information flux density field, circle semantic phenotype polarization gradient, circle topological dynamic resilience entropy gradient, and circle gene expression spectrum.

[0097] Preferably, the gene fusion module 503 is specifically used for: Obtain candidate gene fragments from cloud drive users who intend to share content; Calculate the semantic similarity between the candidate gene fragment and each social gene expression fragment in the social structure expression map of the cloud disk circle; In response to the semantic similarity being greater than a first preset threshold, gene cross-fusion operation is performed on the candidate gene fragment and the social gene expression fragment to obtain the fused gene fragment; In response to the semantic similarity being less than or equal to a first preset threshold, the cloud drive user who intends to share the content is prompted that the candidate gene fragment is not suitable for sharing in the cloud drive community.

[0098] Preferably, calculating the semantic similarity between the candidate gene fragment and each social gene expression fragment in the social structure expression map of the cloud storage circle includes: Calculate the first similarity between the circle semantic phenotype encoding set of the candidate gene fragment and the circle semantic phenotype polarization gradient of the social gene expression fragment; Calculate the second similarity between the circle interaction chemotaxis intensity of the candidate gene fragment and the circle topological information flux density field of the social gene expression fragment; Calculate the third similarity between the circle content diffusion preference factor of the candidate gene fragment and the circle topological dynamics structure resilience entropy gradient of the social gene expression fragment; The semantic similarity is obtained by weighted summation of the first similarity, the second similarity, and the third similarity.

[0099] Preferably, the propagation simulation based on the social structure expression map of the fused gene fragment and the cloud storage circle to obtain all propagation paths of the content to be shared and the propagation potential information entropy flux score of each propagation path includes: Using the fusion gene fragment as a viral RNA sequence and the social structure expression map of the cloud storage circle as a host social environment, the infection decoherence propagation path of the fusion gene fragment in the cloud storage circle, the local immunity judgment of the circle, the mutation path projection prediction, and the incubation period assessment and measurement were simulated. Based on the infection decoherence propagation path, the local immunity judgment of the circle, the mutation path projection prediction, and the incubation period assessment, all propagation paths of the content to be shared are obtained, and the propagation potential information entropy flux score of each propagation path is calculated.

[0100] Preferably, the simulation of the infection decoherence propagation path of the fusion gene fragment in the cloud disk circle, the judgment of local immunity in the circle, the prediction of mutation path projection, and the measurement of latency period include: Based on the circle semantic phenotype encoding set of the fused gene fragments, social gene expression fragments with circle semantic phenotype polarization gradients higher than a second preset threshold are found in the social structure expression map of the cloud disk circle, and used as initial infection nodes to form an initial infection node set. Based on the initial set of infected nodes, the evolution of the infection decoherence propagation path of the fusion gene fragment is simulated; In each evolution of the propagation path, a local immunity judgment mechanism is executed synchronously to detect whether the cloud disk users in the cloud disk circle have developed herd immunity to the fused gene fragment. Perform mutation path projection prediction to determine whether the fused gene fragment may be semantically reconstructed, recreated, and relabeled by cloud disk users in the cloud disk circle, and evolve into new propagation primitives; During the evolution of each propagation path, latency period assessment and measurement are performed simultaneously to simulate the response delay of the fused gene fragment from publication to the first effective response in the cloud disk circle.

[0101] Preferably, the formula for calculating the propagation potential information entropy flux score is: ; In the formula, Information entropy and flux score represent the propagation potential of a propagation path; The average semantic cosine similarity between the set of circle semantic phenotype encodings in the personal knowledge gene base of each cloud disk user node in the propagation path and the fused gene fragment; The circle topology information flux density field represents the virtual circle, which is composed of cloud disk user nodes in the propagation path. The circle semantic phenotypic polarization gradient represents the virtual circle; This represents the proportion of immune nodes in the transmission pathway multiplied by the immunosuppressive attenuation factor. This represents the percentage of highly mutated nodes in the propagation path multiplied by the mutation path enhancement factor. All represent weights; This represents the latent decay term.

[0102] Preferably, the propagation potential information entropy flux score is proportional to the propagation probability of the propagation path.

[0103] Preferably, determining the target propagation path based on the propagation potential information entropy flux score includes: Propagation paths with a propagation potential information entropy flux score greater than a third preset threshold are selected as the target propagation paths.

[0104] Preferably, the formula for calculating the propagation value vector of the content to be shared is: ; In the formula, This represents the propagation value vector of the content to be shared; Indicates the scale of short-term transmission; Indicates the scale of the medium-term spread; Indicates the scale of long-term transmission; All represent weights.

[0105] In specific implementation, the working principle, control process and technical effects of the cloud disk content dissemination value assessment device provided in this embodiment of the invention are the same as those of the cloud disk content dissemination value assessment method in the above embodiments, and will not be repeated here.

[0106] Please see Figure 6 , Figure 6This is a schematic diagram of a preferred embodiment of a terminal device provided by the present invention. The terminal device includes a processor 601, a memory 602, and a computer program stored in the memory 602 and configured to be executed by the processor 601. When the processor 601 executes the computer program, it implements the cloud disk content dissemination value assessment method described in any of the above embodiments.

[0107] Preferably, the computer program can be divided into one or more modules / units (such as computer program 1, computer program 2, ...), and the one or more modules / units are stored in the memory 602 and executed by the processor 601 to complete the present invention. The one or more modules / units can be a series of computer program instruction segments capable of performing specific functions, and the instruction segments are used to describe the execution process of the computer program in the terminal device.

[0108] The processor 601 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor, or the processor 601 may be any conventional processor. The processor 601 is the control center of the terminal device, connecting various parts of the terminal device through various interfaces and lines.

[0109] The memory 602 mainly includes a program storage area and a data storage area. The program storage area can store the operating system, applications required for at least one function, etc., while the data storage area can store related data, etc. Furthermore, the memory 602 can be a high-speed random access memory, or a non-volatile memory, such as a plug-in hard drive, a smart media card (SMC), a secure digital card (SD), and a flash card, or it can be other volatile solid-state storage devices.

[0110] It should be noted that the aforementioned terminal devices may include, but are not limited to, processors and memory, as will be understood by those skilled in the art. Figure 6The structural diagram is merely an example of the terminal device described above and does not constitute a limitation on the terminal device described above. It may include more or fewer components than shown in the diagram, or combine certain components, or use different components.

[0111] This invention also provides a computer-readable storage medium, which includes a stored computer program, wherein the computer program, when running, controls the device where the computer-readable storage medium is located to execute the cloud disk content dissemination value assessment method described in any of the above embodiments.

[0112] This invention also provides a computer program product, which includes a computer program or computer instructions. When the computer program or computer instructions are executed by a processor, they implement the cloud disk content dissemination value assessment method described in any of the above embodiments.

[0113] This invention provides a method, apparatus, device, medium, and product for assessing the dissemination value of cloud storage content. It constructs a personal knowledge gene library for each cloud storage user based on their operational behavior and personal knowledge base; wherein the personal knowledge gene library includes multiple gene fragments. Based on the personal knowledge gene libraries of all cloud storage users, a social structure expression graph of a cloud storage circle is constructed; wherein the cloud storage circle includes multiple cloud storage users. A cross-structure gene hybridization operation is performed between the social structure expression graph of the cloud storage circle and the gene fragments of the cloud storage user whose content is to be shared, generating a fused gene fragment. Based on the fused gene fragment and the social structure expression graph of the cloud storage circle, a dissemination simulation is performed to obtain all dissemination paths of the content to be shared and a dissemination potential information entropy flux score for each dissemination path. The target dissemination path is determined based on the dissemination potential information entropy flux score, and the dissemination value vector of the content to be shared is calculated. This invention constructs a four-tuple feature dimension for information dissemination through four-dimensional fragment modeling of social genes. The content to be shared is modeled as an information dissemination entity and injected into the social structure expression graph of the circle. It simulates the infection evolution path and dissemination response delay in different social environments, and predicts the dissemination variation path branches of the content in the social structure by combining the knowledge reconstruction ability of circle members. Finally, it outputs the dissemination value vector under short, medium and long time windows, realizing an intelligent recommendation mechanism that visualizes the dissemination path of content dissemination, measures the response cycle, and predicts circle adaptation.

[0114] It should be noted that the system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, in the accompanying drawings of the system embodiments provided by this invention, the connection relationships between modules indicate that they have communication connections, which can be specifically implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without any creative effort.

[0115] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A method for evaluating the dissemination value of cloud storage content, characterized in that, include: Based on the operational behavior and personal knowledge base of each cloud disk user, a personal knowledge gene base is constructed for each cloud disk user; wherein, the personal knowledge gene base includes multiple gene fragments. Based on the personal knowledge gene databases of all cloud storage users, a social structure expression graph of the cloud storage circle is constructed; wherein, the cloud storage circle includes multiple cloud storage users; The social structure representation graph of the cloud storage circle is used to perform cross-structure gene hybridization operation with the gene fragments of the cloud storage users who intend to share content, to generate fused gene fragments. Based on the fusion gene fragment and the social structure expression map of the cloud disk circle, a propagation simulation was performed to obtain all propagation paths of the content to be shared and the propagation potential information entropy flux score of each propagation path. The target propagation path is determined based on the propagation potential information entropy flux score, and the propagation value vector of the content to be shared is calculated.

2. The cloud storage content dissemination value assessment method as described in claim 1, characterized in that, The user's actions include their semantic preferences, activity level, comment frequency, and sharing frequency within the cloud storage community.

3. The cloud storage content dissemination value assessment method as described in claim 1, characterized in that, The construction of a personal knowledge gene database for each cloud disk user, based on their operational behavior and personal knowledge base, includes: For each cloud drive user, multiple gene fragments are constructed based on the user's operational behavior and the file semantic tags in the personal knowledge base; Personal knowledge gene fragment sequences are generated based on the multiple gene fragments to obtain the personal knowledge gene library.

4. The cloud storage content dissemination value assessment method as described in claim 3, characterized in that, The gene fragments include four dimensions: circle interaction chemotaxis strength, circle semantic evolution heterogeneity index, circle content diffusion preference factor, and circle semantic phenotypic encoding set.

5. The cloud storage content dissemination value assessment method as described in claim 4, characterized in that, The method for calculating the circle interaction chemotaxis strength is as follows: Obtain the cumulative frequency of the circle structure interaction behavior corresponding to the gene fragment in the historical record; The circle interaction chemotaxis intensity of the gene fragment is calculated based on the cumulative frequency and the preset circle adaptation weight.

6. The cloud storage content dissemination value assessment method as described in claim 5, characterized in that, The formula for calculating the circle interaction chemistry strength is: ； In the formula, Represents gene fragments The intensity of circle interaction chemism; Indicates cumulative frequency; This indicates the preset circle adaptation weight.

7. The cloud storage content dissemination value assessment method as described in claim 4, characterized in that, The method for calculating the circle semantic evolution heterogeneity index is as follows: Obtain the feature vector of semantic interaction of the gene fragment in consecutive circles within the historical window; The semantic evolution heterogeneity index of the gene fragment is calculated based on the semantic difference between adjacent feature vectors.

8. The cloud storage content dissemination value assessment method as described in claim 7, characterized in that, The formula for calculating the circle semantic evolution heterogeneity index is as follows: ； In the formula, Represents gene fragments Circle semantic evolution heterogeneity index; Indicates the first Feature vectors of user interactions between secondary cloud storage and communities; This indicates the total number of interactions between cloud drive users and the community within the history window. Indicates the first Feature vectors of user interactions between secondary cloud storage and communities; It is a positive number.

9. The cloud storage content dissemination value assessment method as described in claim 4, characterized in that, The calculation method for the circle content diffusion preference factor is as follows: Traverse the historical circle content sharing and dissemination records corresponding to the gene fragment, and extract behavioral features within a preset time window; The behavioral characteristics are weighted statistically to calculate the circle content diffusion preference factor of the gene fragment.

10. The cloud storage content dissemination value assessment method as described in claim 9, characterized in that, The formula for calculating the circle content diffusion preference factor is: ； In the formula, Represents gene fragments The content diffusion preference factor in the circle; Indicates the length of the time window; This indicates the number of people whose content posted by cloud storage users within the same circle becomes visible in the first week. This indicates the frequency with which content posted by a cloud storage user within a circle is responded to by other cloud storage users. express The weights; This indicates the frequency with which content posted by cloud storage users within the community is restructured, tagged, or recreated. express The weights; This indicates the frequency of cross-circle forwarding of content posted by users within the same cloud storage circle.

11. The cloud storage content dissemination value assessment method as described in claim 4, characterized in that, The calculation method for the circle semantic phenotypic encoding set is as follows: Multimodal semantic analysis is performed on the files that cloud drive users browse, comment on, forward, and recreate in the circle to extract semantic tags and count the frequency of occurrence of the semantic tags in the circle; The semantic propagation weight of the semantic tag is determined based on the frequency of occurrence and the number of times the semantic tag is forwarded, re-expressed, and reconstructed by other cloud disk users. Based on the semantic labels and the semantic propagation weights, the set of circle semantic phenotype codes for the gene fragment is calculated.

12. The cloud storage content dissemination value assessment method as described in claim 11, characterized in that, The formula for calculating the circle semantic phenotypic encoding set is as follows: ； In the formula, Represents gene fragments The set of circle semantic phenotypic encodings; Indicates semantic tags; Represents the semantic propagation weight of semantic tags; This indicates the frequency of semantic tags within the circle; Indicates the number of semantic tags; This indicates the number of times a semantic tag has been forwarded, re-expressed, or reconstructed by other cloud storage users.

13. The cloud storage content dissemination value assessment method as described in claim 4, characterized in that, The step of constructing a social structure representation graph of the cloud storage community based on the personal knowledge gene database of all cloud storage users includes: Based on the personal knowledge gene database of all cloud disk users within the cloud disk community, a social structure expression map of the cloud disk community is constructed; wherein, the social structure expression map includes multiple social gene expression fragments.

14. The cloud storage content dissemination value assessment method as described in claim 13, characterized in that, The social gene expression fragment includes four dimensions: circle topological information flux density field, circle semantic phenotype polarization gradient, circle topological dynamic resilience entropy gradient, and circle gene expression spectrum.

15. The cloud storage content dissemination value assessment method as described in claim 14, characterized in that, The step of performing cross-structural gene hybridization operations on the social structure representation graph of the cloud storage circle and the gene fragments of the cloud storage users who intend to share content to generate fused gene fragments includes: Obtain candidate gene fragments from cloud drive users who intend to share content; Calculate the semantic similarity between the candidate gene fragment and each social gene expression fragment in the social structure expression map of the cloud disk circle; In response to the semantic similarity being greater than a first preset threshold, gene cross-fusion operation is performed on the candidate gene fragment and the social gene expression fragment to obtain the fused gene fragment; In response to the semantic similarity being less than or equal to a first preset threshold, the cloud drive user who intends to share the content is prompted that the candidate gene fragment is not suitable for sharing in the cloud drive community.

16. The cloud storage content dissemination value assessment method as described in claim 15, characterized in that, The calculation of the semantic similarity between the candidate gene fragment and each social gene expression fragment in the social structure expression map of the cloud storage circle includes: Calculate the first similarity between the circle semantic phenotype encoding set of the candidate gene fragment and the circle semantic phenotype polarization gradient of the social gene expression fragment; Calculate the second similarity between the circle interaction chemotaxis intensity of the candidate gene fragment and the circle topological information flux density field of the social gene expression fragment; Calculate the third similarity between the circle content diffusion preference factor of the candidate gene fragment and the circle topological dynamics structural resilience entropy gradient of the social gene expression fragment; The semantic similarity is obtained by weighted summation of the first similarity, the second similarity, and the third similarity.

17. The method for assessing the value of cloud storage content dissemination as described in claim 1, characterized in that, The propagation simulation based on the fused gene fragment and the social structure expression map of the cloud storage circle yields all propagation paths of the content to be shared and a propagation potential information entropy flux score for each path, including: Using the fusion gene fragment as a viral RNA sequence and the social structure expression map of the cloud disk circle as a host social environment, the infection decoherence propagation path of the fusion gene fragment in the cloud disk circle, the local immunity judgment of the circle, the mutation path projection prediction, and the incubation period assessment and measurement were simulated. Based on the infection decoherence propagation path, the local immunity judgment of the circle, the mutation path projection prediction, and the incubation period assessment, all propagation paths of the content to be shared are obtained, and the propagation potential information entropy flux score of each propagation path is calculated.

18. The cloud storage content dissemination value assessment method as described in claim 17, characterized in that, The simulation of the fusion gene fragment's infection decoherence propagation path, local immunity assessment within the cloud disk circle, mutation path projection prediction, and latency period assessment includes: Based on the circle semantic phenotype encoding set of the fused gene fragments, social gene expression fragments with circle semantic phenotype polarization gradients higher than a second preset threshold are found in the social structure expression map of the cloud disk circle, and used as initial infection nodes to form an initial infection node set. Based on the initial set of infected nodes, the evolution of the infection decoherence propagation path of the fusion gene fragment is simulated; In each evolution of the propagation path, a local immunity judgment mechanism is executed synchronously to detect whether the cloud disk users in the cloud disk circle have developed herd immunity to the fused gene fragment. Perform mutation path projection prediction to determine whether the fused gene fragment may be semantically reconstructed, recreated, and relabeled by cloud disk users in the cloud disk circle, and evolve into new propagation primitives; During the evolution of each propagation path, latency period assessment and measurement are performed simultaneously to simulate the response delay of the fused gene fragment from publication to the first effective response in the cloud disk circle.

19. The method for assessing the dissemination value of cloud storage content as described in claim 1, characterized in that, The formula for calculating the propagation potential information entropy flux score is as follows: ； In the formula, Information entropy and flux score represent the propagation potential of a propagation path; The average semantic cosine similarity between the set of circle semantic phenotype encodings in the personal knowledge gene base of each cloud disk user node in the propagation path and the fused gene fragment; The circle topology information flux density field represents the virtual circle, which is composed of cloud disk user nodes in the propagation path. The circle semantic phenotypic polarization gradient represents the virtual circle; This represents the proportion of immune nodes in the transmission pathway multiplied by the immunosuppressive attenuation factor. This represents the percentage of highly mutated nodes in the propagation path multiplied by the mutation path enhancement factor. All represent weights; This represents the latent decay term.

20. The method for assessing the value of cloud storage content dissemination as described in claim 1, characterized in that, The propagation potential information entropy flux score is directly proportional to the propagation probability of the propagation path.

21. The method for assessing the value of cloud storage content dissemination as described in claim 1, characterized in that, Determining the target propagation path based on the propagation potential information entropy flux score includes: Propagation paths with a propagation potential information entropy flux score greater than a third preset threshold are selected as the target propagation paths.

22. The method for assessing the value of cloud storage content dissemination as described in claim 1, characterized in that, The formula for calculating the propagation value vector of the content to be shared is: ； In the formula, This represents the propagation value vector of the content to be shared; Indicates the scale of short-term transmission; Indicates the scale of the medium-term spread; Indicates the scale of long-term transmission; All represent weights.

23. A device for assessing the value of cloud storage content dissemination, characterized in that, include: The first construction module is used to construct a personal knowledge gene library for each cloud disk user based on the user's operation behavior and personal knowledge base; wherein, the personal knowledge gene library includes multiple gene fragments. The second construction module is used to construct a social structure expression graph of the cloud storage circle based on the personal knowledge gene database of all the cloud storage users; wherein, the cloud storage circle includes multiple cloud storage users; The gene fusion module is used to perform cross-structural gene hybridization operations on the social structure expression map of the cloud disk circle and the gene fragments of the cloud disk users who intend to share the content, and generate fused gene fragments. The propagation simulation module is used to perform propagation simulation based on the fused gene fragment and the social structure expression map of the cloud disk circle, to obtain all propagation paths of the content to be shared and the propagation potential information entropy flux score of each propagation path; The value assessment module is used to determine candidate propagation paths based on the propagation potential information entropy flux score, and to calculate the propagation value vector of the content to be shared.

24. A terminal device, characterized in that, The device includes a processor and a memory, wherein the memory stores a computer program and the computer program is configured to be executed by the processor, wherein the processor, when executing the computer program, implements the cloud disk content dissemination value assessment method as described in any one of claims 1 to 6.

25. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein when the device containing the computer-readable storage medium executes the computer program, it implements the cloud disk content dissemination value assessment method as described in any one of claims 1 to 6.

26. A computer program product, characterized in that, The computer program product includes a computer program or computer instructions, which, when executed by a processor, implement the cloud disk content dissemination value assessment method as described in any one of claims 1 to 6.

Images