CN119450154B

CN119450154B - Intelligent box based on edge calculation and data processing method thereof

Info

Publication number: CN119450154B
Application number: CN202510048370.0A
Authority: CN
Inventors: 徐笔荣; 杨孝骏
Original assignee: Shenzhen Geek Intelligent Technology Co ltd; Shenzhen Baitong Xuanwu Technology Co ltd
Current assignee: Shenzhen Geek Intelligent Technology Co ltd
Priority date: 2025-01-13
Filing date: 2025-01-13
Publication date: 2025-04-15
Anticipated expiration: 2045-01-13
Also published as: CN119450154A

Abstract

The invention relates to the technical field of data processing, in particular to an intelligent box based on edge calculation and a data processing method thereof, comprising the following steps: acquiring a historical search data set, performing preprocessing operation on the historical search data set by utilizing an edge computing unit to obtain an initial analysis data set, summarizing the initial analysis data set to obtain a large data set, analyzing the large data set to obtain an optimized word frequency sequence, acquiring a sliding frequency extraction group, analyzing the optimized word frequency sequence based on a search trend evaluation method and the sliding frequency extraction group to obtain a time period film and television resource library, and initiating a new prompt on a film and television for a user after confirming that film and television resources corresponding to retrieval terms in a user retrieval catalog exist in the time period film and television resource library, so as to finish intelligent box data processing based on edge computing. The invention can analyze the search data of the intelligent box in the past time period to obtain a valuable time period film and television resource library by utilizing edge calculation, and intelligently and newly prompt the user.

Description

Intelligent box based on edge calculation and data processing method thereof

Technical Field

The invention relates to the technical field of data processing, in particular to an intelligent box based on edge calculation and a data processing method thereof.

Background

The edge computing unit is a computing node which is deployed near the user, has the capability of data processing and analysis, can receive information sent by the user, performs some preliminary processing, and sends the data after the preliminary processing to the cloud for reducing the computing pressure of the data center. The intelligent box is a device for connecting a television and the Internet for a user.

In the prior art, when a user uses an intelligent box to play a television, a problem often exists that a user cannot find a video resource expected to be watched by the user, and when the intelligent box and the cloud thereof are introduced, the user only introduces the video resource in a mode of video market, internal economy and the like, for example, directly introduces the video resource for commercial hot-broadcasting.

Although the above technology can realize the video resource introduction of the intelligent box, the intelligent box does not reasonably utilize the usage data left by the demands of some users, and the intelligent box is not uniform in corresponding user, and the video resource is directly introduced by single commercial hot-cast, so that the user demand cannot be met by the intelligent box, and therefore, how to use the user search data and meet the user demand and intelligently provide the video resource is a problem to be solved urgently.

Disclosure of Invention

The invention provides an intelligent box based on edge calculation, a data processing method and a computer thereof, which can analyze the search data of the intelligent box in the past time period to obtain a valuable time period film and television resource library by utilizing the edge calculation, and carry out intelligent new prompt on a user.

In order to achieve the above object, the present invention provides an intelligent box based on edge computing and a data processing method thereof, comprising:

the edge computing-intelligent box analysis system comprises an edge computing unit, a data analysis unit and an intelligent box unit, wherein the intelligent box unit comprises a plurality of intelligent boxes;

Sequentially extracting intelligent boxes from the intelligent box units, and executing the following operations on the extracted intelligent boxes:

Based on the intelligent box receiving a log authorization instruction from a user, acquiring a history searching dataset of the intelligent box in a pre-constructed history period according to the log authorization instruction, sending the history searching dataset to the edge computing unit, and performing preprocessing operation on the history searching dataset by using the edge computing unit receiving the history searching dataset to obtain an initial analysis dataset;

Summarizing initial analysis data sets corresponding to a plurality of intelligent boxes to obtain a big data set, analyzing the big data set by using a data analysis unit to obtain an optimized word frequency sequence, wherein the big data set comprises a plurality of big data, the optimized word frequency sequence comprises a plurality of optimized word frequency groups, and the optimized word frequency groups are ordered according to the sequence from big to small;

Acquiring a sliding frequency extraction group, and analyzing the optimized word frequency sequence based on a pre-constructed search trend evaluation method and the sliding frequency extraction group to obtain a plurality of value movie and television entries, wherein the sliding frequency extraction group comprises blank groups with preset numbers;

Acquiring a time period movie resource library corresponding to a plurality of value movie and television entries, sequentially extracting intelligent boxes from the plurality of intelligent boxes, intercepting an initial analysis data set of the intelligent boxes based on a preset time period to obtain a time period search data set, analyzing the time period search data set to obtain a user search catalog, wherein the time period movie and television resource library comprises a plurality of movie and television resources, the movie and television resources are in one-to-one correspondence to the value movie and television entries, and the user search catalog comprises zero, one or a plurality of search entries;

If it is confirmed that the movie resources corresponding to the search terms in the user search directory exist in the time period movie resource library, an intelligent box is utilized to initiate a new movie prompt based on the search terms to the user, and intelligent box data processing based on edge calculation is completed based on the new movie prompt.

Optionally, the acquiring, according to the log authorization instruction, the historical search dataset of the smart box in a preconfigured historical period includes:

Analyzing the log authorization instruction to obtain a history period and a history search log, wherein the history search log comprises a plurality of unit search records;

Sequentially extracting unit search records from the historical search logs, acquiring the time of the extracted unit search records to obtain target time, if the target time is within the historical period, reserving the extracted unit search records, otherwise, removing the extracted unit search records;

and summarizing the reserved unit search records to obtain a historical search data set.

Optionally, the performing, by using the edge computing unit that receives the historical search dataset, a preprocessing operation on the historical search dataset to obtain an initial analysis dataset includes:

sequentially extracting the history search data from the history search data set using the edge calculation unit, and performing the following operations on the extracted history search data:

Extracting time, information level and information content from the historical search data to obtain a plurality of target information, and executing the following operations on the target information in the plurality of target information:

Judging whether the target information accords with the pre-constructed field constraint condition, if so, constructing a key identifier based on the target information, taking the key identifier as a key, taking the target information as a value, constructing an initial information key value pair, and if not, eliminating historical search data corresponding to the target information;

After confirming that each target information in the plurality of target information accords with the corresponding field constraint condition, summarizing the key value pairs of the initial information to obtain initial analysis data corresponding to the historical search data;

and summarizing the initial analysis data to obtain an initial analysis data set.

Optionally, the analyzing the big data set by using the data analysis unit to obtain the optimized word frequency sequence includes:

the following operations are executed on big data in the big data set:

Extracting information content from big data to obtain content data, extracting search terms and search results from the content data, if the search results are preset no-result values, reserving the search terms, otherwise, removing the big data corresponding to the content data;

Summarizing the reserved search terms to obtain an optimized word data set, and performing recursion operation on the optimized word data set to obtain an optimized word frequency sequence.

Optionally, the performing a recursive operation on the optimized word dataset to obtain an optimized word frequency sequence includes:

sequentially extracting optimized word data from the optimized word data set, and performing the following operations on the extracted optimized word data:

acquiring an initial word frequency sequence, wherein the initial word frequency sequence comprises a plurality of word frequency groups, the word frequency groups comprise target words and frequencies, and the initial value of the frequencies is 0;

If the target words corresponding to the optimized word data exist in a plurality of word frequency groups in the initial word frequency sequence, performing a progressive operation on the frequencies of the word frequency groups corresponding to the target words in the initial word frequency sequence to obtain updated word frequency groups, updating the initial word frequency sequence by using the updated word frequency groups, and returning the steps of sequentially extracting the optimized word data from the optimized word data set by taking the updated initial word frequency sequence as the initial word frequency sequence;

Otherwise, constructing an initial added word frequency group by taking optimized word data as target words, assigning the frequency of the initial added word frequency group to be 1 to obtain an added word frequency group, importing the added word frequency group into an initial word frequency sequence, taking the added word frequency group as a word frequency group, taking the initial word frequency sequence after importing the added word frequency group as the initial word frequency sequence, and returning to the step of sequentially extracting the optimized word data from the optimized word data set;

After the optimized word data in the optimized word data set is confirmed to be extracted, the word frequency sub-groups in the initial word frequency sequence are subjected to sorting operation according to the sequence from large frequency to small frequency, and the optimized word frequency sequence is obtained.

Optionally, the obtaining the sliding frequency extraction group, analyzing the optimized word frequency sequence based on a pre-constructed search trend evaluation method and the sliding frequency extraction group, to obtain a plurality of value movie and television entries, including:

Sequentially extracting optimized word frequency groups from the optimized word frequency sequence, and sequentially mapping the extracted optimized word frequency groups into blank groups in the sliding frequency extraction group until all blank groups in the sliding frequency extraction group are mapped with the optimized word frequency groups to obtain entry groups to be analyzed, wherein the entry groups to be analyzed comprise a plurality of entry frequency groups to be analyzed, the entry frequency groups to be analyzed are in one-to-one correspondence with the optimized word frequency groups, and the entry frequency groups to be analyzed are sequenced according to the sequence from the first to the last of the mapping of the optimized word frequency groups to the blank groups;

Judging whether the to-be-analyzed entry group is a pre-constructed value entry group, if the to-be-analyzed entry group is the value entry group, sliding and intercepting the optimized word frequency sequence based on the to-be-analyzed entry group and the sliding frequency extraction group to obtain an updated entry group, taking the updated entry group as the to-be-analyzed entry group, returning to the step of judging whether the to-be-analyzed entry group is the pre-constructed value entry group until the to-be-analyzed entry group is not the value entry group, summarizing the value entry group to obtain a plurality of value entry groups, and executing repeated entry de-duplication operation on the plurality of value entry groups to obtain a plurality of value movie entries.

Optionally, the determining whether the term group to be analyzed is a pre-constructed value term group, if the term group to be analyzed is a value term group, includes:

sequentially extracting word frequency groups to be analyzed from the word frequency groups to be analyzed, and executing the following operations on the extracted word frequency groups to be analyzed:

Obtaining a search term corresponding to a word frequency group to be analyzed, obtaining a target term, obtaining an up-mapping date and a data expiration date based on the target term, obtaining a daily search frequency chart based on the up-mapping date, the data expiration date and the target term, constructing a daily frequency search quantity regression model based on the daily search frequency chart and a pre-constructed frequency difference autoregressive model, calculating search quantities of a plurality of preset prediction target time points by using the daily frequency search quantity regression model to obtain a plurality of prediction search quantities, mapping the plurality of prediction search quantities and the prediction target time points corresponding to each prediction search quantity into the pre-constructed blank daily search frequency chart to obtain a prediction frequency chart, wherein the horizontal axis of the prediction frequency chart is the prediction target time point, the vertical axis is the prediction search quantity, and the prediction target time points are in one-to-one correspondence with the prediction search quantity;

performing linear fitting operation on the predicted frequency chart to obtain a fitting straight line, acquiring the slope of the fitting straight line, obtaining a searching frequency trend value, and if the searching frequency trend value is greater than a preset trend threshold value, confirming the target entry as a unit value entry;

Judging whether the number of unit value entries in the entry group to be analyzed is larger than the preset value number;

and if the number of the unit value entries in the entry group to be analyzed is greater than the value number, confirming that the entry group to be analyzed is the value entry group.

Optionally, the obtaining the daily search frequency chart based on the date of the mapping, the date of the expiration of the data and the target term includes:

acquiring a search period based on the mapping date and the data expiration date, dividing the search period to obtain a daily sequence, and constructing an initial daily search frequency coordinate system based on a target entry by taking the daily sequence as a horizontal axis and taking the frequency as a vertical axis;

sequentially extracting daily sequences from the daily sequences, extracting total daily search frequency corresponding to target vocabulary entries from the big data set based on the extracted daily sequences and the target vocabulary entries, mapping the total daily search frequency and the corresponding daily sequences into an initial daily search frequency coordinate system, and obtaining an initial daily search frequency chart after confirming that all the daily sequences in the daily sequences are extracted.

Optionally, the fitted straight line is as follows:

wherein, Representing the predicted search amount in the fitted line,Representing the predicted target time point in the fitted line,Represent the firstThe index of the target point in time is predicted,Representing the total number of predicted target time points,Represent the firstThe target point in time is predicted and,Representing the average of a plurality of predicted target time points,Represent the firstThe predicted search amount corresponding to the predicted target time point,And the average value of the prediction search amounts corresponding to the plurality of prediction target time points is represented.

To achieve the above object, the present invention further provides an edge computing-based smart box and a data processing system thereof, including:

the system acquisition module is used for acquiring an edge computing-intelligent box analysis system, wherein the edge computing-intelligent box analysis system comprises an edge computing unit, a data analysis unit and an intelligent box unit, and the intelligent box unit comprises a plurality of intelligent boxes;

The initial analysis data set acquisition module is used for sequentially extracting intelligent boxes from the intelligent box unit and executing the following operations on the extracted intelligent boxes, namely, based on the intelligent boxes, receiving log authorization instructions from users, acquiring historical search data sets of the intelligent boxes in a pre-constructed historical period according to the log authorization instructions, sending the historical search data sets to the edge calculation unit, and executing preprocessing operation on the historical search data sets by utilizing the edge calculation unit which receives the historical search data sets to obtain initial analysis data sets;

The value film and television entry acquisition module is used for summarizing initial analysis data sets corresponding to a plurality of intelligent boxes to obtain a big data set, analyzing the big data set by the data analysis unit to obtain an optimized word frequency sequence, wherein the big data set comprises a plurality of big data, the optimized word frequency sequence comprises a plurality of optimized word frequency groups, the optimized word frequency groups are ordered according to the sequence from big to small in frequency to obtain a sliding frequency extraction group, and the optimized word frequency sequence is analyzed based on a pre-constructed search trend evaluation method and the sliding frequency extraction group to obtain a plurality of value film and television entries, wherein the sliding frequency extraction group comprises blank groups with preset numbers;

The intelligent box prompting module is used for acquiring a time period movie resource library corresponding to a plurality of value movie entries, sequentially extracting intelligent boxes from the plurality of intelligent boxes, intercepting an initial analysis data set of the intelligent boxes based on a preset time period to obtain a time period searching data set, analyzing the time period searching data set to obtain a user searching directory, wherein the time period movie resource library comprises a plurality of movie resources, the movie resources are in one-to-one correspondence with the value movie entries, the user searching directory comprises zero or one or more searching entries, and if the fact that movie resources corresponding to the searching entries in the user searching directory exist in the time period movie resource library is confirmed, the intelligent boxes are utilized to initiate new prompting on the movie based on the searching entries for the user, and intelligent box data processing based on edge calculation is completed based on the new prompting on the movie.

In order to solve the above-mentioned problems, the present invention also provides an electronic apparatus including:

a memory storing at least one instruction;

and the processor executes the instructions stored in the memory to realize the intelligent box based on the edge calculation and the data processing method thereof.

In order to solve the above problems, the present invention also provides a computer readable storage medium having at least one instruction stored therein, the at least one instruction being executed by a processor in an electronic device to implement the above-described edge-calculation-based smart box and a data processing method thereof.

The invention aims to solve the problems in the background art, an edge computing-intelligent box analysis system is firstly obtained, intelligent boxes are sequentially extracted from an intelligent box unit, and the extracted intelligent boxes are all subjected to the following operations of receiving a log authorization instruction from a user based on the intelligent boxes, obtaining a history searching dataset of the intelligent boxes in a pre-built history period according to the log authorization instruction, sending the history searching dataset to the edge computing unit, and performing preprocessing operation on the history searching dataset by utilizing the edge computing unit which receives the history searching dataset to obtain an initial analysis dataset. The log authorization instruction also ensures that the use trace of the user is not revealed, and the method and the device also screen the historical search data set in the historical period to acquire the historical search data set in the historical period. Summarizing initial analysis data sets corresponding to a plurality of intelligent boxes to obtain a big data set, analyzing the big data set by a data analysis unit to obtain an optimized word frequency sequence, wherein the big data set comprises a plurality of big data, the optimized word frequency sequence comprises a plurality of optimized word frequency groups, the optimized word frequency groups are ordered according to the sequence from big to small in frequency to obtain a sliding frequency extraction group, and analyzing the optimized word frequency sequence based on a pre-constructed search trend evaluation method and the sliding frequency extraction group to obtain a plurality of value movie entries, wherein the sliding frequency extraction group comprises blank groups with preset numbers. The invention provides data support and target guidance for screening video resources which are searched in the intelligent box by a user but cannot be searched, thereby updating the television box resource library for the cloud. And the sliding frequency extraction group is utilized to evaluate the optimized word frequency sequence, the unit value entry is confirmed when the search frequency trend value is larger than the preset trend threshold value, when the number of the unit value entries in the sliding frequency extraction group is larger than the preset value number, the value entry group is obtained, the sliding frequency extraction group is utilized to carry out sliding interception on the optimized word frequency sequence, when the entry group to be analyzed is not the value entry group, the search quantity of the delayed optimized word frequency group is explained to be partially or completely not the unit value entry, the search trend is stopped at the moment, and the calculation quantity is saved when the value film and television entries are extracted as much as possible. Acquiring a time period movie resource library corresponding to a plurality of value movie entries, sequentially extracting intelligent boxes from the plurality of intelligent boxes, intercepting an initial analysis data set of the intelligent boxes based on a preset time period to obtain a time period search data set, analyzing the time period search data set to obtain a user search catalog, wherein the time period movie resource library comprises a plurality of movie resources, the movie resources are in one-to-one correspondence with the value movie entries, the user search catalog comprises zero or one or more search entries, if the fact that the movie resources corresponding to the search entries in the user search catalog exist in the time period movie resource library is confirmed, a new prompt on a movie based on the search entries is initiated to a user by the intelligent boxes, and the intelligent box data processing based on edge calculation is completed based on the new prompt on the movie. therefore, the invention can analyze the search data of the intelligent box in the past time period to obtain the valuable time period film and television resource library by utilizing edge calculation, and intelligently and newly prompt the user.

Drawings

FIG. 1 is a schematic flow chart of an intelligent box based on edge computing and a data processing method thereof according to an embodiment of the invention;

FIG. 2 is a functional block diagram of an edge-based smart box and a data processing system thereof according to an embodiment of the present invention;

Fig. 3 is a schematic structural diagram of an electronic device for implementing the intelligent box based on edge computation and the data processing method thereof according to an embodiment of the present invention;

Reference numerals illustrate:

1. Electronic equipment 10, a processor 11, a memory 12 and a bus.

The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.

Detailed Description

It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.

The embodiment of the application provides an intelligent box based on edge calculation and a data processing method thereof. The intelligent box based on edge calculation and the execution main body of the data processing method thereof comprise at least one of electronic equipment which is not limited to a server side, a terminal and the like and can be configured to execute the method provided by the embodiment of the application. In other words, the intelligent box based on edge computing and the data processing method thereof can be executed by software or hardware installed in a terminal device or a server device, wherein the software can be a blockchain platform. The server side comprises, but is not limited to, a single server, a server cluster, a cloud server or a cloud server cluster and the like.

Referring to fig. 1, a flow chart of an intelligent box based on edge computing and a data processing method thereof according to an embodiment of the invention is shown. In this embodiment, the intelligent box based on edge calculation and the data processing method thereof include:

S1, acquiring an edge computing-intelligent box analysis system, wherein the edge computing-intelligent box analysis system comprises an edge computing unit, a data analysis unit and an intelligent box unit, and the intelligent box unit comprises a plurality of intelligent boxes.

It can be understood that the edge computing-intelligent box analysis system is a system integrating an edge computing unit, a data analysis unit and an intelligent box unit, wherein the edge computing unit is a computing node deployed near the intelligent box unit, has the capability of data processing and analysis, can receive information sent by the intelligent box unit, performs some preliminary processing, and sends the information after the preliminary processing to a pre-built cloud for reducing computing pressure of a data center. The data analysis unit is a unit for analyzing and processing the data received by the edge calculation unit. The intelligent box unit is a unit formed by a plurality of intelligent boxes, and the intelligent boxes are devices for connecting televisions with the Internet by users.

S2, sequentially extracting intelligent boxes from the intelligent box unit, and executing the following operation on the extracted intelligent boxes, wherein the operation is based on the intelligent boxes to receive log authorization instructions from users, and a history search data set of the intelligent boxes in a pre-constructed history period is obtained according to the log authorization instructions.

It can be understood that the log authorization instruction is an instruction that the user responds to grant authorization after the intelligent box initiates an authorization request to the user, and when the intelligent box receives the log authorization instruction from the user, the intelligent box can upload and send the locally reserved log to the edge gateway for processing, so as to provide intelligent service for the user under the condition of user grant. The log authorization instructions also ensure that the user's usage trace is not compromised. The history period is a period of time in the past, the range of which may be defined by human beings, for example, 30 days in the past.

Further, the acquiring, according to the log authorization instruction, the historical search dataset of the intelligent box in the preconfigured historical period includes:

It can be understood that the history search log is a log of the intelligent box in a history period, and the log refers to a record generated when a user performs a search operation in the intelligent box, and the technology is the prior art and is not described herein. The unit search record is a record of a user when performing a search operation in the intelligent box, for example, the unit search record of the user when performing a search is [ movie a ], the time is [ a year b month c day d time e minutes f seconds ], and the search result is [ none ].

Further, the target time is the time in the unit search record. If the target time is within the history period, the target time is within a time interval formed by the history period, for example, the history period is 0 seconds to 0 seconds in time e of d-time of c-day of a-year b-month c-day, and the time of d-time e of d-day of a-year b-month c-day is earlier than the time of d-day g, and the target time is greater than zero in time interval formed by the history period, the target time is considered to be within the history period, and a unit search record is reserved.

It will be appreciated that the purpose of this step is to filter historical search datasets over a historical period. In the embodiment of the invention, the historical search data set is limited not to be an empty set, namely, the intelligent box does not have a historical search log in a historical period, and the intelligent box is considered to have no data processing or analysis requirement.

And S3, sending the historical search data set to the edge computing unit, and performing preprocessing operation on the historical search data set by using the edge computing unit which receives the historical search data set to obtain an initial analysis data set.

Further, the performing, by using the edge computing unit that receives the historical search dataset, a preprocessing operation on the historical search dataset to obtain an initial analysis dataset includes:

It can be understood that the information level is the severity or importance level of the historical search data, and is used for identifying and filtering information in the log, including DEBUG, INFO, WARN, wherein the information content is search content and search results in the historical search data, for example, the unit search record of a user in one search is [ movie A ], the time is [ a, b, c, d, e, f, s ], the search result is [ none ], the information level is [ INFO ], and the historical search data is [ a-b-c d:e: f INFO User searched for 'movie A', THE SEARCH result is [ none ], and the information content is [ User searched for 'movie A', THE SEARCH result is [ none ]. The search content is [ movie a ].

Further, the field constraint condition is a constraint that needs to be satisfied by the target information, so as to ensure the integrity of the target information, for example, a non-null constraint, a unique constraint, etc., and the technology is in the prior art. The target information is an information level, and corresponding field constraint conditions, such as non-null constraint, unique constraint and field type constraint, need to be met, and the field type constraint is enumeration. The enumeration is to include only specific values, e.g., DEBUG, INFO, WARN, etc. If the target information is information content, corresponding field constraint conditions, such as non-null constraint, unique constraint and field type constraint, need to be met, and the field type constraint is text.

It can be understood that the key identifier is an identifier used when constructing a key value pair for the target information, for example, the key identifier is [ time ], the target information is [ a-b-c d:e:f ], and the initial information key value pair is [ time, a-b-c d:e:f ]. The initial analysis data is a set formed by initial information key value pairs corresponding to the historical search data. The construction of the initial information key pair is a technology for constructing the key pair, which is a prior art and will not be described herein.

And S4, summarizing initial analysis data sets corresponding to the intelligent boxes to obtain a big data set, analyzing the big data set by using a data analysis unit to obtain an optimized word frequency sequence, wherein the big data set comprises a plurality of big data, the optimized word frequency sequence comprises a plurality of optimized word frequency groups, and the optimized word frequency groups are ordered according to the sequence from big to small.

Further, the analyzing the big data set by the data analyzing unit to obtain the optimized word frequency sequence includes:

the following operations are executed on big data in the big data set:

It is understood that the search term is a term or short text searched in the content data, and the search result is a result when the user searches the smart box for the search term. For example, the information content is User searched for 'movie A', THE SEARCH result is [ none ], the search term is [ movie A ], the search result is [ none ], and the search result is a preset no-result value.

It should be noted that, the purpose of this step is to screen out the video resources that the user searches in the intelligent box but cannot be searched, so as to provide data support and target guidance for updating the cloud to the television box resource library. For example, each user in the intelligent box unit searches for [ movie a ], and the search result is [ none ], which indicates that [ movie a ] cannot be watched on the television corresponding to the intelligent box, and when the cloud end parses such information, the copyright of [ movie a ] can be purchased and updated in the television box unit, so that the viewing requirement of the user can be met.

Further, the performing a recursive operation on the optimized word data set to obtain an optimized word frequency sequence includes:

It is understood that the initial word frequency sequence is a stored sequence formed by frequency of occurrence of word data in a large data set for statistical optimization, and the target word is a word stored in a word frequency group. The initial value of 0 for the frequency means that the frequency of occurrence of the target word is 0 before the recursive operation is performed on the optimized word data set, and that the target word has no specific value before the recursive operation is performed on the optimized word data set.

It should be noted that, the step of performing the step-up operation on the frequency of the word frequency group corresponding to the target word in the initial word frequency sequence is to add 1 to the frequency value of the word frequency group corresponding to the target word. The initial added word frequency group is a word frequency group constructed by taking optimized word data as a target word, and the initial value of the frequency is 0.

For example, if the optimized word data set includes three optimized word data and is respectively [ movie a, and movie B ], the word frequency sub-group structure of the initial word frequency sequence is [ target word, 0 ] and there are multiple word frequency groups, the optimized word data [ movie a ] is extracted, at this time, no target word corresponding to the optimized word data exists in the multiple word frequency groups in the initial word frequency sequence, an initial added word frequency group is constructed based on the optimized word data [ movie a ], namely [ movie a,0 ], the frequency of the initial added word frequency group is assigned as 1, and the added word frequency group [ movie a, 1] is obtained, and after the added word frequency group is imported into the initial word frequency sequence, the initial word frequency sequence is [ movie a,1 ]. Extracting second optimized word data [ film A ], wherein an initial word frequency sequence [ film A, 1] contains target words corresponding to the optimized word data, and then performing a progressive operation on the frequencies of the [ film A, 1] to obtain an updated word frequency group [ film A,2 ], and updating the initial word frequency sequence by using the updated word frequency group, namely replacing the [ film A, 1] in the initial word frequency sequence by using the [ film A,2 ], so that the updated initial word frequency sequence is the [ film A,2 ].

S5, acquiring a sliding frequency extraction group, and analyzing the optimized word frequency sequence based on a pre-constructed search trend evaluation method and the sliding frequency extraction group to obtain a plurality of value movie and television entries, wherein the sliding frequency extraction group comprises a preset number of blank groups.

Further, the obtaining the sliding frequency extraction group, analyzing the optimized word frequency sequence based on the pre-constructed search trend evaluation method and the sliding frequency extraction group, to obtain a plurality of value movie and television entries, including:

It can be understood that the sliding frequency extraction group includes a preset number of blank groups, and the sliding frequency extraction group is a sliding window for sliding extraction of the optimized word frequency sequence.

For example, if the preset number is 3, the sliding frequency extraction group is [ blank group, blank group ]. The optimized word frequency sequence is [ movie a, n ] [ movie b, m ] [ movie c, l ] [ movie d, g ], wherein n, m, l and g respectively represent the frequencies of the corresponding target words movie a, movie b, movie c and movie d. Extracting optimized word frequency groups [ film A, n ] and mapping the optimized word frequency groups into sliding frequency extraction groups to obtain [ film A, n, blank groups and blank groups ], extracting the optimized word frequency groups [ film b, m ] and mapping the optimized word frequency groups into the sliding frequency extraction groups to obtain [ film A, n, film b, m and blank groups ], extracting the optimized word frequency groups [ film c, l ] and mapping the optimized word frequency groups into the sliding frequency extraction groups to obtain [ film A, n, film b, m and film c, l ], and obtaining entry groups to be analyzed [ film A, n, film b, m and film c, l ], wherein the entry groups to be analyzed are respectively [ film A, n, film b, m and [ film c, l ]. The word frequency groups to be analyzed are sequenced according to the sequence from first to last of the mapping of the optimized word frequency groups to the blank groups, namely the word frequency groups to be analyzed in the entry groups to be analyzed are the same as the sequence in the optimized word frequency sequence.

Further, the sliding interception optimizing word frequency sequence is to intercept the sliding frequency extraction groups sequentially according to the sequence of the optimizing word frequency sequence, and the number of the optimizing word frequency groups intercepted in each sliding is 1.

The optimized word frequency sequence is shown as [ movie A, n ] [ movie b, m ] [ movie c, l ] [ movie d, g ], [ movie e, f ], wherein f represents the frequency of movie e, the word frequency groups to be analyzed are shown as [ movie A, n ], [ movie b, m ], [ movie c, l ], and the updated term groups obtained by sliding interception of the optimized word frequency sequence are shown as [ movie b, m, movie c, l, movie d, g ].

Further, the repeated term de-duplication operation is to remove repeated target terms in the multiple value term groups, and it is understood that in the previous example, the term groups to be analyzed [ movie a, n, movie b, m, movie c, l ] and the second term groups to be analyzed [ movie b, m, movie c, l, movie d, g ] are obtained, and the repeated term de-duplication operation is performed on the term groups to be analyzed and the second term groups to be analyzed, so that the multiple value movie terms obtained are movie a, n, movie b, m, movie c, l, movie d, g.

Further, the determining whether the term group to be analyzed is a pre-constructed value term group, if the term group to be analyzed is a value term group, includes:

It can be understood that the date of the mapping is the first date of official release of the target term, the date of the expiration is the last date of the time in the history period, and the daily search frequency chart is a frequency chart formed by using the daily search amount of the target term in the intelligent box unit. The frequency difference autoregressive model is a prediction model of daily search volume constructed based on an ARIMA model, and the ARIMA model is an autoregressive integral moving average model and can be used for prediction of time sequence analysis. The method processes and predicts time series data by combining three parts of Autoregressive (AR), differential (I) and Moving Average (MA), so that in the embodiment of the invention, the search amount of a plurality of preset predicted target time points can be predicted by constructing a frequency differential autoregressive model based on an ARIMA model, and the technology is the prior art and is not repeated here. The blank day search frequency chart is a frequency chart which is constructed in the same way as the corresponding day search frequency chart, but the blank day search frequency chart removes coordinate values in the day search frequency chart. The predicted frequency chart is obtained by leading the predicted target time point and the predicted search quantity into the blank day search frequency chart in a one-to-one correspondence manner.

Further, in the embodiment of the present invention, a linear fitting operation is performed on the predicted frequency chart, and a fitting straight line is obtained by performing the linear fitting operation by using a least square method, and the obtained straight line is the fitting straight line. The search frequency trend value is the slope of the fitted line. The trend threshold is the minimum value of the slope of the fitting straight line set by people, when the search frequency trend value is larger than the preset trend threshold, the search trend of the target entry in the time period corresponding to the plurality of predicted target time points is considered to meet the requirement set by people, for example, when the search frequency trend value is larger than the preset trend threshold, the value of introducing the corresponding film and television resources is considered to be still provided. Therefore, in the embodiment of the invention, the unit value entry is a target entry with a search frequency trend value greater than a preset trend threshold. The value term group is the term group with the number of unit value terms in the term group to be analyzed being greater than the value number. The value number is the artificially set number, and when the number of unit value entries in the entry group to be analyzed is larger than the value number, the film and television resources corresponding to the target words in the entry group to be analyzed are considered to have the value of introduction.

The term group to be analyzed is [ movie a, n, movie b, m, movie c, l ], the term group to be analyzed is [ movie b, m, movie c, l, movie d, g ], in the term group to be analyzed, the search frequency trend value of [ movie b, m ] is found to be larger than the preset trend threshold value, the term group is unit value term, but neither movie d is unit value term, the value number is artificially set to be 2, and at the moment, the term group to be analyzed is not value term group. And stopping the operation of sliding interception of the optimized word frequency sequence based on the to-be-analyzed entry group and the sliding frequency extraction group, and not summarizing the second to-be-analyzed entry group when summarizing the value entry group, wherein sliding interception operation is not executed on the optimized word frequency groups [ movie c, l, movie d, g ] and the lag thereof in the optimized word frequency sequence. The method and the device are characterized in that the optimized word frequency sequence is arranged according to the word frequency sequence from large to small in the foregoing, when the second to-be-analyzed word entry group is not a value word entry group, the search quantity of the optimized word frequency group which is lagged is partially or completely not a unit value word entry, so that the sliding interception operation is stopped at the moment, and the calculation quantity is saved when the value film and television word entry is extracted as much as possible.

It can be understood that the obtaining the daily search frequency chart based on the date of the mapping, the date of the expiration of the data and the target term includes:

Further, the search period is a time interval constructed by the date of the mapping and the date of the expiration of the data, and the dividing the search period is performed by taking 0:00 of each day as a dividing point and 24 hours as one day, for example, 1 month, 1 day, 0:00-1 month, 2 days, 0:00 is a daily sequence, and the daily sequence is one day. Further, the daily sequence is a sequence in which divided search periods are ordered in the order of dates. The direction in which the horizontal axis in the initial day search frequency coordinate system increases is the direction in which the day sequence increases. The total daily search frequency is the total search amount of target vocabulary entries in all intelligent boxes under the date corresponding to the daily sequence recorded in the big data set. For example, the daily sequence 1 is that the total daily search frequency is 1 month 1 day 0:00-1 month 2 day 0:00, the total daily search frequency and the corresponding daily sequence are mapped to the meaning of an initial daily search frequency coordinate system, the total daily search frequency is taken as an ordinate, the corresponding daily sequence is taken as an abscissa to form a coordinate point, and the description is carried out in the initial daily search frequency coordinate system.

Further, the fitted straight line is as follows:

S6, acquiring a time period movie resource library corresponding to a plurality of value movie and television entries, sequentially extracting intelligent boxes from the plurality of intelligent boxes, intercepting an initial analysis data set of the intelligent boxes based on a preset time period to obtain a time period search data set, analyzing the time period search data set to obtain a user search catalog, wherein the time period movie and television resource library comprises a plurality of movie and television resources, the movie and television resources correspond to the value movie and television entries one by one, and the user search catalog comprises zero, one or a plurality of search entries.

Further, the time-period video resource library is a set formed by video resources corresponding to a plurality of value video entries, and the time-period video resource library is supplied to the intelligent box units, so that each intelligent box in the intelligent box units can watch the video resources on a television. The preset period is a manually set period of time, and is used for carrying out new prompt on a film of a user, the period search data set is an initial analysis data set under the preset period of time, for example, the initial analysis data set is 30 days in the past, and the preset period of time is 7 days, and the period search data set is a set of initial analysis data extracted from the initial analysis data set for 7 days in the past.

Specifically, the user search catalog is an entry and a frequency of user search in a preset period, the analysis period searches the data set to obtain the user search catalog and the analysis big data set, and the steps of obtaining the optimized word frequency sequence are similar and can achieve the same effect, which is not described herein. The search term is a term in a user search catalog, and is a term searched by a user within a preset time period, which is obtained by analyzing the time period search data set.

And S7, if the fact that the video resources corresponding to the search terms in the user search directory exist in the time period video resource library is confirmed, initiating a new video prompt based on the search terms to the user by using the intelligent box, and completing intelligent box data processing based on edge calculation based on the new video prompt.

For example, the preset period is 7 days, when the intelligent box is detected to exist movie A in the user search catalog within the past 7 days, and movie A also exists in the period movie resource library, the intelligent box is utilized to prompt the user that [ movie A of interest is new ].

FIG. 2 is a functional block diagram of an edge computing-based smart box and a data processing system thereof according to an embodiment of the present invention.

The edge computing-based smart box and the data processing system 100 of the present invention may be installed in an electronic device. Depending on the implementation, the intelligent box based on edge computing and the data processing system 100 thereof may include a system acquisition module 101, an initial analysis data set acquisition module 102, a value movie entry acquisition module 103, and an intelligent box prompt module 104. The module of the invention, which may also be referred to as a unit, refers to a series of computer program segments, which are stored in the memory of the electronic device, capable of being executed by the processor of the electronic device and of performing a fixed function.

The system acquisition module 101 is configured to acquire an edge computing-intelligent box analysis system, where the edge computing-intelligent box analysis system includes an edge computing unit, a data analysis unit, and an intelligent box unit, where the intelligent box unit includes a plurality of intelligent boxes;

The initial analysis data set obtaining module 102 is configured to sequentially extract intelligent boxes from an intelligent box unit, and perform operations on all the extracted intelligent boxes, wherein the operations are performed on the basis of receiving a log authorization instruction from a user by the intelligent box, obtaining a history search data set of the intelligent box in a pre-constructed history period according to the log authorization instruction, sending the history search data set to the edge computing unit, and performing preprocessing operation on the history search data set by using the edge computing unit that receives the history search data set to obtain an initial analysis data set;

The value movie entry obtaining module 103 is configured to summarize initial analysis data sets corresponding to a plurality of intelligent boxes to obtain a big data set, analyze the big data set by using a data analysis unit to obtain an optimized word frequency sequence, where the big data set includes a plurality of big data, the optimized word frequency sequence includes a plurality of optimized word frequency groups, the plurality of optimized word frequency groups are ordered according to a sequence from big to small frequency, obtain a sliding frequency extraction group, and analyze the optimized word frequency sequence based on a pre-constructed search trend evaluation method and the sliding frequency extraction group to obtain a plurality of value movie entries, where the sliding frequency extraction group includes a preset number of blank groups;

The intelligent box prompting module 104 is configured to obtain a time-period movie resource library corresponding to a plurality of value movie and television terms, sequentially extract intelligent boxes from the plurality of intelligent boxes, intercept an initial analysis dataset of the intelligent boxes based on a preset time period, obtain a time-period search dataset, analyze the time-period search dataset, and obtain a user search catalog, where the time-period movie resource library includes a plurality of movie and television resources and corresponds to the value movie and television terms one by one, the user search catalog includes zero, one or more search terms, and if it is confirmed that movie and television resources corresponding to the search terms in the user search catalog exist in the time-period movie and television resource library, initiate a new prompt on a movie based on the search terms to a user by using the intelligent boxes, and complete intelligent box data processing based on edge calculation based on the new prompt on the movie and television.

In detail, the modules in the edge-based intelligent box and the data processing system 100 in the embodiment of the present invention use the same technical means as the edge-based intelligent box and the data processing method in fig. 1, and can produce the same technical effects, which are not described herein.

Fig. 3 is a schematic structural diagram of an electronic device for implementing an edge-computing-based intelligent box and a data processing method thereof according to an embodiment of the present invention.

The electronic device 1 may comprise a processor 10, a memory 11 and a bus 12, and may further comprise a computer program stored in the memory 11 and executable on the processor 10, such as a smart box based on edge calculations and a data processing method program thereof.

The memory 11 includes at least one type of readable storage medium, including flash memory, a mobile hard disk, a multimedia card, a card memory (e.g., SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, etc. The memory 11 may in some embodiments be an internal storage unit of the electronic device 1, such as a removable hard disk of the electronic device 1. The memory 11 may in other embodiments also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a smart memory card (SMART MEDIA CARD, SMC), a Secure Digital (SD) card, a flash memory card (FLASH CARD) or the like, which are provided on the electronic device 1. Further, the memory 11 further comprises an internal storage unit of the electronic device 1, and also comprises an external storage device. The memory 11 may be used not only for storing application software installed in the electronic device 1 and various types of data, such as a smart box based on edge calculation and codes of a data processing method program thereof, but also for temporarily storing data that has been output or is to be output.

The processor 10 may be comprised of integrated circuits in some embodiments, for example, a single packaged integrated circuit, or may be comprised of multiple integrated circuits packaged with the same or different functions, including one or more central processing units (Central Processing unit, CPU), microprocessors, digital processing chips, graphics processors, combinations of various control chips, and the like. The processor 10 is a Control Unit (Control Unit) of the electronic device, connects respective parts of the entire electronic device using various interfaces and lines, executes or executes programs or modules (e.g., an edge-calculation-based smart box and a data processing method program thereof, etc.) stored in the memory 11, and invokes data stored in the memory 11 to perform various functions of the electronic device 1 and process the data.

The bus 12 may be a peripheral component interconnect standard (PERIPHERAL COMPONENT INTERCONNECT, PCI) bus, or an extended industry standard architecture (extended industry standard architecture, EISA) bus, among others. The bus 12 may be divided into an address bus, a data bus, a control bus, etc. The bus 12 is arranged to enable a connection communication between the memory 11 and at least one processor 10 etc.

Fig. 3 shows only an electronic device with components, it being understood by a person skilled in the art that the structure shown in fig. 3 does not constitute a limitation of the electronic device 1, and may comprise fewer or more components than shown, or may combine certain components, or may be arranged in different components.

For example, although not shown, the electronic device 1 may further include a power source (such as a battery) for supplying power to the respective components, and preferably, the power source may be logically connected to the at least one processor 10 through a power management system, so as to perform functions of charge management, discharge management, and power consumption management through the power management system. The power supply may also include one or more of any of a direct current or alternating current power supply, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, and the like. The electronic device 1 may further include various sensors, bluetooth modules, wi-Fi modules, etc., which will not be described herein.

Further, the electronic device 1 may also comprise a network interface, optionally the network interface may comprise a wired interface and/or a wireless interface (e.g. WI-FI interface, bluetooth interface, etc.), typically used for establishing a communication connection between the electronic device 1 and other electronic devices.

The electronic device 1 may optionally further comprise a user interface, which may be a Display, an input unit, such as a Keyboard (Keyboard), or a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, or the like. The display may also be referred to as a display screen or display unit, as appropriate, for displaying information processed in the electronic device 1 and for displaying a visual user interface.

The smart box based on edge computation and its data processing method program stored in the memory 11 of the electronic device 1 are a combination of instructions, which when run in the processor 10, can implement:

Specifically, the specific implementation method of the above instructions by the processor 10 may refer to descriptions of related steps in the corresponding embodiments of fig. 1 to 3, which are not repeated herein.

Further, the modules/units integrated in the electronic device 1 may be stored in a computer readable storage medium if implemented in the form of software functional units and sold or used as separate products. The computer readable storage medium may be volatile or nonvolatile. For example, the computer readable medium may include any entity or system capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM).

The present invention also provides a computer readable storage medium storing a computer program which, when executed by a processor of an electronic device, can implement:

In the several embodiments provided by the present invention, it should be understood that the disclosed apparatus, system and method may be implemented in other manners. For example, the system embodiments described above are merely illustrative, and there may be additional divisions of a practical implementation.

The modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, may be located in one place, or may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional module in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units can be realized in a form of hardware or a form of hardware and a form of software functional modules.

It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof.

Finally, it should be noted that the above-mentioned embodiments are merely for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made to the technical solution of the present invention without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A method for processing data of an intelligent box based on edge computation, the method comprising:

2. The edge computing-based data processing method of claim 1, wherein the obtaining a history search dataset of the smart box in a pre-constructed history period according to the log authorization instruction comprises:

3. The data processing method of an edge computing-based intelligent box according to claim 2, wherein the performing a preprocessing operation on the historical search data set by using the edge computing unit that receives the historical search data set to obtain an initial analysis data set comprises:

4. The method for processing data of an intelligent box based on edge computation according to claim 3, wherein the analyzing the big data set by the data analysis unit to obtain the optimized word frequency sequence comprises:

the following operations are executed on big data in the big data set:

5. The method for processing data of an intelligent box based on edge computation of claim 4, wherein said performing a recursive operation on the optimized word data set to obtain the optimized word frequency sequence comprises:

6. The method for processing data of an intelligent box based on edge calculation as claimed in claim 5, wherein the step of obtaining the sliding frequency extraction group, and analyzing the optimized word frequency sequence based on the pre-constructed search trend evaluation method and the sliding frequency extraction group to obtain a plurality of value movie and television entries comprises the steps of:

7. The method for processing data of an intelligent box based on edge computing as claimed in claim 6, wherein the determining whether the vocabulary entry group to be analyzed is a pre-constructed value vocabulary entry group, if the vocabulary entry group to be analyzed is a value vocabulary entry group, includes:

8. The method for processing data of the intelligent box based on edge calculation according to claim 7, wherein the obtaining a daily search frequency graph based on the date of the ascent, the date of the expiration of the data, and the target term comprises:

9. The edge-computing-based intelligent box data processing method according to claim 8, wherein the fitted straight line is as follows:

,

10. A data processing system for an edge computing-based smart box, the system comprising: