Intelligent storage management method and system for data of a set-top box

Abstract

The application discloses a kind of intelligent storage management method and system of set top box data, for improving the viewing experience of user.The method of the application includes: obtaining the user data of set top box, the user data includes historical viewing record and real-time interaction data;Value assessment is carried out to the viewing content type of different time periods in the user data based on preset scoring rules, and a content value score set is obtained;According to the content value score corresponding to the viewing content type of different time periods, storage space proportion is allocated, and the viewing content type lower than preset score in the content value score set is determined as to-be-cleaned content;Whether the current load state of the set top box is reasonable use state is detected;If not, release the storage space of the to-be-cleaned content.

Description

Technical Field

[0001] This application relates to the field of data storage technology, and in particular to an intelligent storage management method and system for set-top box data. Background Technology

[0002] With the rapid development of smart devices and streaming media technologies, the importance of data storage management for set-top boxes, as the core terminal for home entertainment, is becoming increasingly prominent. Efficient storage management not only affects the smoothness of the user experience but also directly impacts system operating efficiency and resource utilization, making it a key element in promoting the development of the smart home ecosystem. In the set-top box field, how to rationally utilize limited storage space to meet the diverse and personalized viewing needs of users has become an important area of ​​focus in technological research and industrial applications.

[0003] Currently, set-top boxes typically employ a static management method with fixed partitioned storage, which cannot be adjusted according to user needs. When storage space is insufficient, the only way to clear space is by deleting entire files, which may lead to the accidental deletion of content that users are interested in, affecting their viewing experience. Summary of the Invention

[0004] This application provides an intelligent storage management method and system for set-top box data to improve the user's viewing experience.

[0005] The first aspect of this application provides an intelligent storage management method for set-top box data, including:

[0006] Acquire user data from the set-top box, including historical viewing records and real-time interaction data;

[0007] The value of the content types viewed in the user data at different time periods is evaluated based on preset scoring rules to obtain a content value score set.

[0008] Storage space is allocated proportionally according to the content value scores corresponding to the types of content viewed in different time periods, and the types of content viewed with a content value score lower than a preset score are identified as content to be cleaned up.

[0009] Detect whether the current load status of the set-top box is a reasonable usage state;

[0010] If not, then release the storage space for the content to be cleaned.

[0011] Optionally, the step of evaluating the value of content types viewed in different time periods based on preset scoring rules to obtain a content value score set includes:

[0012] All viewed content from different time periods in the historical viewing records are grouped according to the type of viewed content;

[0013] Calculate the percentage of viewing frequency for each type of content in the corresponding time period;

[0014] Calculate the percentage of real-time interaction frequency for each type of viewed content within the corresponding time period;

[0015] Based on the viewing frequency ratio and the interaction frequency ratio, the content value score of each viewed content type is calculated to obtain a content value score set.

[0016] Optionally, the step of evaluating the value of content types viewed in different time periods based on preset scoring rules to obtain a content value score set further includes:

[0017] Calculate the percentage of actual viewing time for each type of content in the corresponding time period;

[0018] The content value score set is revised based on the actual viewing time percentage.

[0019] Optionally, the allocation of storage space according to the content value score corresponding to the content type viewed in different time periods includes:

[0020] The types of content viewed in different time periods within the content value score set are sorted in descending order according to their content value score.

[0021] The storage space of the set-top box is divided into a high-intensity storage area, a medium-intensity storage area, and a low-intensity storage area. The storage space ratios of the high-intensity storage area, the medium-intensity storage area, and the low-intensity storage area are sorted in descending order from high to low.

[0022] Content types ranked higher than the first preset rank are cached in the high-popularity storage area; content types ranked higher than the second preset rank but lower than the first preset rank are cached in the medium-popularity storage area; and content types ranked lower than the second preset rank are cached in the low-popularity storage area.

[0023] Optionally, determining that content types with a content value score below a preset score in the content value score set are content to be cleaned up includes:

[0024] Calculate the average content value score of all viewed content types in the low-heat storage area, and determine the average value as the preset score;

[0025] The method identifies content types in the low-heat storage area that have a viewing score below a preset rating as content to be cleaned up. Optionally, after releasing the storage space for the content to be cleaned up, the method further includes:

[0026] Extract the time features and content type features from the historical viewing records;

[0027] The time feature and the viewing content type feature are used as training samples to train the viewing content type preset model, which is used to output the viewing content type for a preset time period.

[0028] The set-top box's storage space ratio is reallocated according to the type of content viewed during the preset time period.

[0029] Optionally, after releasing the storage space of the content to be cleaned, the method further includes:

[0030] Receive user satisfaction feedback on the types of content viewed at different times;

[0031] The storage space ratio of the set-top box is reallocated based on the satisfaction feedback results.

[0032] A second aspect of this application provides an intelligent storage and management system for set-top box data, comprising:

[0033] The acquisition unit is used to acquire user data of the set-top box, including historical viewing records and real-time interaction data.

[0034] An evaluation unit is used to evaluate the value of the types of content viewed in the user data at different time periods based on preset scoring rules, and to obtain a content value score set.

[0035] The allocation unit is used to allocate storage space proportionally according to the content value score corresponding to the content type viewed in different time periods, and to determine the content type viewed with a content value score lower than the preset score as content to be cleaned up.

[0036] The detection unit is used to detect whether the current load status of the set-top box is a reasonable usage status;

[0037] The release unit is used to release the storage space of the content to be cleaned when the current load state of the set-top box is a reasonable usage state.

[0038] Optionally, the evaluation unit is specifically used for:

[0039] All viewed content from different time periods in the historical viewing records are grouped according to the type of viewed content;

[0040] Calculate the percentage of viewing frequency for each type of content in the corresponding time period;

[0041] Calculate the percentage of real-time interaction frequency for each type of viewed content within the corresponding time period;

[0042] Based on the viewing frequency ratio and the interaction frequency ratio, the content value score of each viewed content type is calculated to obtain a content value score set.

[0043] Optionally, the evaluation unit is further specifically used for:

[0044] Calculate the percentage of actual viewing time for each type of content in the corresponding time period;

[0045] The content value score set is revised based on the actual viewing time percentage.

[0046] As can be seen from the above technical solutions, this application has the following effects:

[0047] First, user data from the set-top box is acquired, including historical viewing records and real-time interaction data. Then, based on preset scoring rules, the value of viewed content types across different time periods is assessed, resulting in a content value score set. Next, storage space is allocated proportionally according to the content value scores corresponding to the viewed content types in different time periods, and content types with scores below the preset score are identified as content to be cleaned up. Finally, the set-top box's current load status is checked to ensure it is under reasonable usage; if not, storage space for the content to be cleaned up is released. This method, by assessing content value scores, reflects users' preferences for different content types at different times in real time. Using these scores to allocate storage space and determine content to be cleaned up allows for adjustments to storage space based on user needs, reducing the chance of accidentally deleting content that users are interested in, thereby improving the user's viewing experience. Attached Figure Description

[0048] Figure 1 This is a schematic diagram of an embodiment of an intelligent storage management method for set-top box data according to this application;

[0049] Figure 2-1 and Figure 2-2 This is a schematic diagram of another embodiment of the intelligent storage management method for set-top box data in this application;

[0050] Figure 3 This is a schematic diagram of an embodiment of an intelligent storage management system for set-top box data in this application;

[0051] Figure 4 This is a schematic diagram of another embodiment of an intelligent storage management system for set-top box data in this application. Detailed Implementation

[0052] This application provides an intelligent storage management method and system for set-top box data to improve the user's viewing experience.

[0053] The intelligent storage management method for set-top box data described in this application is implemented in a system or on a server. Please refer to [link / reference]. Figure 1 As shown, one embodiment of the intelligent storage management method for set-top box data in this application includes:

[0054] 101. Obtain user data from the set-top box, including historical viewing records and real-time interaction data;

[0055] In this embodiment, all user data stored in the set-top box's memory is acquired. This user data includes the user's historical viewing records and real-time interaction data. Since the set-top box's memory has limited storage space, the historical viewing records typically represent content viewed by the user within a certain time period, such as viewing records from the past 30 days or 60 days. Furthermore, the historical viewing records can contain videos, images, or text; the specific file format is not limited here. It is important to note that the historical viewing records also include corresponding time information, for example, video A watched by the user between 7:30 PM and 7:45 PM.

[0056] It should be noted that real-time interactive data refers to the human-computer interaction that users perform while watching relevant content. For example, a user may follow the author of video A and like video A while watching it.

[0057] 102. Based on preset scoring rules, evaluate the value of content types viewed in different time periods in user data to obtain a content value score set;

[0058] In this embodiment, the time information corresponding to each viewed content is extracted from historical viewing records, and the percentage of viewed content for each time period is calculated according to the time period sequence to determine the time periods with higher user activity. Time periods with lower viewed content percentages can be eliminated to determine the remaining different time periods for subsequent use. For example, if the preset viewed content percentage for a single time period is set to 10%, the viewed content percentage for the time period from 7:00 AM to 10:00 AM is 30%, the viewed content percentage for the time period from 5:00 PM to 7:00 PM is 20%, and the viewed content percentage for the time period from 10:00 PM to 11:00 PM is 40%, while the viewed content percentage for other time periods is less than 5%, then the time periods from 7:00 AM to 10:00 AM, 5:00 PM to 7:00 PM, and 10:00 PM to 11:00 PM can be determined as target time periods for subsequent use.

[0059] It's important to note that the content types viewed at different times refer to the total content types viewed by a user within a single time period. For example, if a user watched Video A, Video B, and Video C between 5 PM and 7 PM, where Video A is sports content, Video B is news content, and Video C is a program content, then by evaluating the value of the content types viewed at different times, we can obtain the degree of preference for different content types at different times.

[0060] 103. Allocate storage space according to the content value score corresponding to the content type viewed in different time periods, and identify the content types viewed with a content value score lower than the preset score as content to be cleaned up.

[0061] In this embodiment, the set-top box's storage space is divided into regions based on the content value rating of the viewed content types within different time periods, and the available memory is set for each region to improve the effective utilization of the set-top box's internal storage space. For example, during the period from 5 PM to 7 PM, sports content accounts for the highest proportion, so more storage space can be allocated to sports content; while educational content accounts for the lowest proportion, so less storage space can be allocated to educational content. Viewed content types with a content value rating lower than a preset rating can be listed as content to be cleaned up, so that low-value viewed content can be accurately cleaned up when memory is insufficient.

[0062] 104. Check if the current load status of the set-top box is a reasonable usage status. If so, proceed to step 105.

[0063] In this embodiment, firstly, performance probes deployed on the set-top box server node collect real-time metrics such as CPU (Central Processing Unit) utilization, memory usage, and disk read / write operations per second (IOPS). Then, a sliding window algorithm is used to calculate the average load on the acquired real-time metrics. When the average load is less than a threshold, it indicates that the set-top box's current load is within a reasonable usage range; conversely, when the average load is greater than or equal to the threshold, it indicates that the set-top box's current load is not within a reasonable usage range. Additionally, network traffic can be analyzed simultaneously using the NetFlow protocol. EWMA is used to process the inbound traffic data per second. When traffic surges above the baseline threshold and persists for a certain period, it is identified as an abnormal traffic spike. The results of this abnormal traffic spike determination are used to further confirm the set-top box's current load status, thereby improving the accuracy of load status detection.

[0064] 105. Release storage space for content to be cleaned up.

[0065] When the current load status of the set-top box is determined to be either reasonable or unreasonable, the content to be cleaned is cleared to release the storage space occupied by the content to be cleaned.

[0066] In this embodiment, user data from the set-top box is first acquired, including historical viewing records and real-time interaction data. Then, based on preset scoring rules, the value of viewed content types across different time periods is evaluated, resulting in a content value score set. Next, storage space is allocated proportionally according to the content value scores corresponding to the viewed content types in different time periods, and content types with scores lower than the preset score are identified as content to be cleaned up. Finally, the current load status of the set-top box is checked to ensure it is in a reasonable usage state; if not, the storage space for the content to be cleaned up is released. In this way, by evaluating content value scores, the user's preference for different content types at different time periods can be reflected in real time. Using these content value scores to allocate storage space and determine the content to be cleaned up allows for adjustments to storage space based on user needs, reducing the chance of accidentally deleting content that users are interested in, thereby improving the user's viewing experience.

[0067] Please see Figure 2-1 and Figure 2-2 As shown, another embodiment of the intelligent storage management method for set-top box data in this application includes:

[0068] 201. Obtain user data from the set-top box, including historical viewing records and real-time interaction data;

[0069] Step 201 in this embodiment is the same as described above. Figure 1 The type of step 101 in the illustrated embodiment will not be described again here.

[0070] 202. Group all viewed content from different time periods in the historical viewing records according to the type of viewed content;

[0071] 203. Calculate the percentage of viewing frequency for each type of content in the corresponding time period;

[0072] 204. Calculate the percentage of real-time interaction frequency for each type of viewed content within the corresponding time period;

[0073] 205. Calculate the content value score for each type of viewed content based on the percentage of viewing frequency and the percentage of interaction frequency, and obtain the content value score set;

[0074] Optionally, in this embodiment, the viewed content is first grouped by type for all viewed content within different time periods. For example, if a user watched Video A, Video B, Video C, and Video D between 5 PM and 7 PM, Video A, Video B, and Video C are grouped into the sports category, and Video D is grouped into the news category. Then, the viewing frequency percentage is calculated for each type of viewed content within each different time period. This viewing frequency percentage represents the proportion of the number of times each type of viewed content was viewed relative to the total number of times all types of viewed content were viewed within the same time period. For example, if a user watched Video A, Video B, Video C, and Video D between 5 PM and 7 PM, and the total number of views for all types of viewed content was 4, and the sports category included 3 videos (Video A, Video B, and Video C), while the news category included 1 video (Video D), then the viewing frequency percentage for the sports category was three-quarters, and the viewing frequency percentage for the news category was one-quarter. Next, the interaction frequency percentage is calculated for the real-time interaction data corresponding to the content types viewed within each different time period. This interaction frequency percentage represents the proportion of interactions for each content type relative to the total number of interactions within the same time period. For example, if a user interacts 5 times between 5 PM and 7 PM, including liking and commenting on video A in the sports category once, following video B in the sports category once, and following and commenting on video D in the news category once, then the interaction frequency percentage for the sports category is three-fifths, and the interaction frequency percentage for the news category is two-fifths. Finally, different weights are assigned to the viewing frequency percentage and the interaction frequency percentage, and the weighted viewing frequency percentage and interaction frequency percentage are summed to obtain the content value score. The corresponding formula is: ,in, Indicates the type of content viewed. Indicates the percentage of viewing frequency. The weighting represents the percentage of viewing frequency. Indicates the percentage of interaction frequency. The weight represents the percentage of interaction frequency.

[0075] In another possible approach, the actual viewing time percentage for each content type within a corresponding time period can be calculated. The content value score set is then adjusted based on this percentage. A correction factor is added to refine the calculated content value score, thereby improving its reliability. Specifically, the actual viewing time percentage represents the proportion of the actual viewing time for a single content type within a single time period relative to the total viewing time. For example, if the total duration of all videos in the sports category is 3 minutes, and the total duration of all videos in the news category is 5 minutes, and a user's actual viewing time for all videos in the sports category is 1 minute, and the actual viewing time for all videos in the news category is 2 minutes, then the actual viewing time percentage for the sports category is one-third, and the actual viewing time percentage for the news category is two-fifths. Multiplying the calculated content value score by the corresponding actual viewing time percentage yields the final content value score.

[0076] 206. Sort the types of content viewed in different time periods in the content value score set in descending order according to the content value score;

[0077] 207. Divide the set-top box's storage space into a high-intensity storage area, a medium-intensity storage area, and a low-intensity storage area. Sort the storage space percentages of the high-intensity storage area, medium-intensity storage area, and low-intensity storage area in descending order from high to low.

[0078] 208. Cache the viewing content types whose ranking is higher than the first preset ranking to the high popularity storage area, cache the viewing content types whose ranking is higher than the second preset ranking but lower than the first preset ranking to the medium popularity storage area, and cache the viewing content types whose ranking is lower than the second preset ranking to the low popularity storage area.

[0079] Optionally, in this embodiment, the different types of content viewed within the same time period are first sorted in descending order of content value score. For example, if the content value scores of the sports group, news group, and program group are 0.69, 0.72, and 0.55 respectively, the sorting order is news group > sports group > program group. Then, the set-top box's storage space is divided into high-popularity storage area, medium-popularity storage area, and low-popularity storage area based on the popularity of different content types. A preset percentage of storage space is assigned to each storage area, for example, 60% for the high-popularity storage area, 30% for the medium-popularity storage area, and 10% for the low-popularity storage area. Finally, different content types are cached in their corresponding storage areas according to a preset ranking. For example, the top 3 content types are cached in the high-popularity storage area, content types ranked 3-5 are cached in the medium-popularity storage area, and content types ranked 5th and below are cached in the low-popularity storage area.

[0080] 209. Calculate the average content value score of all viewed content types in the low-heat storage area, and determine the average value as the preset score;

[0081] 210. Identify content types in the low-popularity storage area that have been viewed below the preset rating as content to be cleaned up;

[0082] Optionally, in this embodiment, after completing the storage space allocation of the set-top box, the content value score of all viewed content types in the low-heat storage area is obtained, and then the average value of all content value scores is calculated and determined as the preset score. When the content value score of any viewed content type in the low-heat storage area is lower than the preset score, it indicates that the viewed content type is low-value content to be cleaned up. When the set-top box memory is insufficient, this part of the content to be cleaned up is cleared first to reasonably free up storage space.

[0083] 211. Check if the current load status of the set-top box is a reasonable usage status. If so, proceed to step 212.

[0084] 212. Release storage space for content to be cleaned up;

[0085] Steps 211 and 212 in this embodiment are the same as those described above. Figure 1 Steps 104 and 105 in the illustrated embodiment are similar and will not be described again here.

[0086] 213. Extract time features and content type features from historical viewing records;

[0087] 214. Use time features and viewing content type features as training samples to train the viewing content type preset model. The viewing content type preset model is used to output the viewing content type for a preset time period.

[0088] 215. Reallocate the set-top box's storage space ratio according to the types of content to be viewed during the preset time period;

[0089] Optionally, in this embodiment, the time features of different time periods and the viewing content type features of the corresponding time periods are first extracted from the historical viewing records. The time periods in the time features are consecutive time periods, such as 7:00-8:00, 9:00-10:00, and 10:00-11:00. Then, the time features of the previous time period and the corresponding viewing content type features are used as input features, and the time features of the next time period and the corresponding viewing content type features are used as prediction values ​​to train the initial model. The trained initial model is then determined as the viewing content type preset model. This viewing content type preset model can output the viewing content type for the next time period. For example, if the current time is 18:00, the viewing content type preset model predicts that the user may watch sports and news content at 19:00. Finally, the storage space ratio of the corresponding viewing content type features is adjusted according to the output value of the viewing content type preset model. For example, when the viewing content type preset model predicts that the user can watch sports content in the next time period, the storage space ratio of sports content can be increased to achieve proactive dynamic adjustment of the set-top box's storage space ratio and improve the flexibility of storage space.

[0090] 216. Receive user satisfaction feedback on the types of content viewed at different times;

[0091] 217. Based on the satisfaction feedback results, reallocate the storage space ratio of the set-top box.

[0092] Optionally, in this embodiment, a satisfaction survey link for the currently viewed content type can be sent to the user. The user can provide feedback through this survey link. For example, when the user finishes watching video A, a survey link pops up asking, "Are you satisfied with this type of video?" The user can choose "yes" or "no". After obtaining the user's satisfaction feedback, the types of viewed content that require storage space adjustment are determined based on the feedback. Then, the storage space ratio for the corresponding viewed content type is reallocated to dynamically adjust the set-top box's storage space allocation according to the user's real-time needs, further improving the user's viewing experience.

[0093] Please see Figure 3 As shown, one embodiment of the intelligent storage management system for set-top box data in this application includes:

[0094] The acquisition unit 301 is used to acquire user data of the set-top box, which includes historical viewing records and real-time interaction data.

[0095] Evaluation unit 302 is used to evaluate the value of the types of content viewed in different time periods in user data based on preset scoring rules, and obtain a content value score set;

[0096] The allocation unit 303 is used to allocate storage space proportionally according to the content value score corresponding to the viewing content type in different time periods, and to determine the viewing content type with a content value score lower than the preset score as content to be cleaned up.

[0097] The detection unit 304 is used to detect whether the current load status of the set-top box is a reasonable usage status;

[0098] Release unit 305 is used to release the storage space of the content to be cleaned when the current load state of the set-top box is a reasonable usage state.

[0099] In this embodiment, the acquisition unit 301 acquires user data from the set-top box, including historical viewing records and real-time interaction data. The evaluation unit 302 evaluates the value of viewing content types in different time periods based on preset scoring rules, obtaining a content value score set. The allocation unit allocates storage space proportionally according to the content value scores corresponding to the viewing content types in different time periods, and determines the viewing content types with content value scores lower than the preset score as content to be cleaned up. The detection unit 304 detects whether the current load state of the set-top box is a reasonable usage state. When the current load state of the set-top box is a reasonable usage state, the release unit 305 releases the storage space of the content to be cleaned up. In this way, by evaluating the content value score, the user's preference for different viewing content types in different time periods can be reflected in real time. Then, by using the content value score to allocate storage space proportionally and determine the content to be cleaned up, the storage space can be adjusted according to user needs, reducing the possibility of accidentally deleting content that users are interested in, thereby improving the user's viewing experience.

[0100] Please see Figure 4 As shown, another embodiment of the intelligent storage management system for set-top box data in this application includes:

[0101] The acquisition unit 401 is used to acquire user data of the set-top box, which includes historical viewing records and real-time interaction data.

[0102] Evaluation unit 402 is specifically used to group all viewed content in different time periods of historical viewing records according to the type of viewed content; calculate the viewing frequency ratio of each type of viewed content in the corresponding time period; calculate the interaction frequency ratio of the real-time interaction data corresponding to each type of viewed content in the corresponding time period; calculate the content value score of each type of viewed content based on the viewing frequency ratio and the interaction frequency ratio, and obtain the content value score set; it is also specifically used to calculate the actual viewing time ratio of each type of viewed content in the corresponding time period; and correct the content value score set based on the actual viewing time ratio.

[0103] The allocation unit 403 is specifically used to sort the viewed content types in different time periods of the content value score set in descending order of content value score; divide the set-top box's storage space into a high-popularity storage area, a medium-popularity storage area, and a low-popularity storage area, and sort the storage space ratio of the high-popularity storage area, medium-popularity storage area, and low-popularity storage area in descending order; cache the viewed content types with a ranking higher than a first preset ranking in the high-popularity storage area, cache the viewed content types with a ranking higher than a second preset ranking but lower than the first preset ranking in the medium-popularity storage area, cache the viewed content types with a ranking lower than the second preset ranking in the low-popularity storage area, calculate the average content value score of all viewed content types in the low-popularity storage area, and determine the average value as the preset score; determine the viewed content types in the low-popularity storage area with a score lower than the preset score as content to be cleaned up.

[0104] The detection unit 404 is used to detect whether the current load status of the set-top box is a reasonable usage status;

[0105] Release unit 405 is used to release the storage space of the content to be cleaned when the current load state of the set-top box is a reasonable usage state.

[0106] Extraction unit 406 is used to extract time features and content type features from historical viewing records;

[0107] Training unit 407 is used to train a preset model of viewing content type using time features and viewing content type features as training samples. The preset model of viewing content type is used to output the viewing content type for a preset time period.

[0108] The first reallocation unit 408 is used to reallocate the storage space ratio of the set-top box according to the viewing content type during a preset time period.

[0109] The receiving unit 409 is used to receive user satisfaction feedback results on the types of content viewed at different time periods;

[0110] The second reallocation unit 410 is used to reallocate the storage space ratio of the set-top box based on the satisfaction feedback results.

[0111] In this embodiment, the functions of each unit are the same as those described above. Figure 2-1 and Figure 2-2 The functions of steps 201 to 217 in the illustrated embodiment are similar and will not be described again here.

[0112] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0113] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection between apparatuses or units through some interfaces, and may be electrical, mechanical, or other forms.

[0114] The units described as separate components may or may not be physically separate. 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 units can be selected to achieve the purpose of this embodiment according to actual needs.

[0115] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0116] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

Claims

1. A method for intelligent storage and management of set-top box data, characterized in that, include: Acquire user data for the set-top box, including historical viewing records and real-time interaction data, wherein the real-time interaction data refers to the human-computer interaction performed by the user while watching relevant content; The value of viewed content types in different time periods of the user data is evaluated based on preset scoring rules to obtain a content value score set. This includes: grouping all viewed content in different time periods of the historical viewing records according to content type; calculating the viewing frequency percentage of each content type in the corresponding time period; calculating the interaction frequency percentage of real-time interaction data corresponding to each content type in the corresponding time period; calculating the content value score of each content type based on the viewing frequency percentage and the interaction frequency percentage, obtaining a content value score set, assigning different weights to the viewing frequency percentage and the interaction frequency percentage, and summing the weighted viewing frequency percentage and the interaction frequency percentage, as shown in the formula: ,in, Indicates the type of content viewed. This represents the value rating of content of type n. Indicates the percentage of viewing frequency. The weighting represents the percentage of viewing frequency. Indicates the percentage of interaction frequency. The weight representing the percentage of interaction frequency; Storage space is allocated proportionally according to the content value score corresponding to the content type viewed in different time periods. The content type viewed with a content value score lower than the preset score is identified as content to be cleaned up. The storage space of the set-top box is divided into a high-popularity storage area, a medium-popularity storage area, and a low-popularity storage area. The storage space ratios of the high-popularity storage area, the medium-popularity storage area, and the low-popularity storage area are sorted in descending order from high to low. Detect whether the current load status of the set-top box is a reasonable usage state; If not, then release the storage space of the content to be cleaned; The step of evaluating the value of content types viewed in different time periods based on preset scoring rules to obtain a content value score set also includes: Calculate the percentage of actual viewing time for each type of content in the corresponding time period; The content value score set is revised based on the actual viewing time percentage.

2. The intelligent storage management method for set-top box data according to claim 1, characterized in that, The allocation of storage space according to the content value rating corresponding to the content type viewed in different time periods includes: The types of content viewed in different time periods within the content value score set are sorted in descending order according to their content value score. Content types ranked higher than the first preset rank are cached in the high-popularity storage area; content types ranked higher than the second preset rank but lower than the first preset rank are cached in the medium-popularity storage area; and content types ranked lower than the second preset rank are cached in the low-popularity storage area.

3. The intelligent storage management method for set-top box data according to claim 2, characterized in that, The determination that content types with a content value score below a preset score are content to be cleaned up includes: Calculate the average content value score of all viewed content types in the low-heat storage area, and determine the average value as the preset score; Content types in the low-heat storage area that are viewed below a preset score are identified as content to be cleaned up.

4. The intelligent storage management method for set-top box data according to claim 1, characterized in that, After releasing the storage space for the content to be cleaned, the method further includes: Extract the time features and content type features from the historical viewing records; The time feature and the viewing content type feature are used as training samples to train the viewing content type preset model, which is used to output the viewing content type for a preset time period. The set-top box's storage space ratio is reallocated according to the type of content viewed during the preset time period.

5. The intelligent storage management method for set-top box data according to claim 1, characterized in that, After releasing the storage space for the content to be cleaned, the method further includes: Receive user satisfaction feedback on the types of content viewed at different times; The storage space ratio of the set-top box is reallocated based on the satisfaction feedback results.

6. An intelligent storage and management system for set-top box data, characterized in that, include: The acquisition unit is used to acquire user data of the set-top box. The user data includes historical viewing records and real-time interaction data. The real-time interaction data is the human-computer interaction performed by the user when watching relevant content. An evaluation unit is used to evaluate the value of viewed content types in different time periods of the user data based on preset scoring rules, and obtain a content value score set. Specifically, the evaluation unit is used to: group all viewed content in different time periods of the historical viewing records according to viewed content type; calculate the viewing frequency percentage of each viewed content type in the corresponding time period; calculate the interaction frequency percentage of real-time interaction data corresponding to each viewed content type in the corresponding time period; calculate the content value score of each viewed content type based on the viewing frequency percentage and the interaction frequency percentage, and obtain a content value score set, assigning different weights to the viewing frequency percentage and the interaction frequency percentage respectively, and summing the weighted viewing frequency percentage and the interaction frequency percentage, as shown in the formula: ,in, Indicates the type of content viewed. This represents the value rating of content of type n. Indicates the percentage of viewing frequency. The weighting represents the percentage of viewing frequency. Indicates the percentage of interaction frequency. The weight representing the percentage of interaction frequency; The allocation unit is used to allocate storage space according to the content value score corresponding to the viewing content type in different time periods, and to determine the viewing content type with a content value score lower than the preset score as content to be cleaned up. The storage space of the set-top box is divided into a high-popularity storage area, a medium-popularity storage area and a low-popularity storage area, and the storage space ratio of the high-popularity storage area, the medium-popularity storage area and the low-popularity storage area are sorted in descending order from high to low. The detection unit is used to detect whether the current load status of the set-top box is a reasonable usage status; The release unit is used to release the storage space of the content to be cleaned when the current load state of the set-top box is a reasonable usage state; The evaluation unit is also specifically used for: Calculate the percentage of actual viewing time for each type of content in the corresponding time period; The content value score set is revised based on the actual viewing time percentage.

Images