CN117235380A - Cultural relic digital cloud exhibition whole-network popularity analysis system - Google Patents
Cultural relic digital cloud exhibition whole-network popularity analysis system Download PDFInfo
- Publication number
- CN117235380A CN117235380A CN202311291310.9A CN202311291310A CN117235380A CN 117235380 A CN117235380 A CN 117235380A CN 202311291310 A CN202311291310 A CN 202311291310A CN 117235380 A CN117235380 A CN 117235380A
- Authority
- CN
- China
- Prior art keywords
- data
- popularity
- keyword
- quantization
- browsing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 31
- 238000012545 processing Methods 0.000 claims abstract description 53
- 238000012216 screening Methods 0.000 claims abstract description 43
- 238000013139 quantization Methods 0.000 claims description 66
- 239000011159 matrix material Substances 0.000 claims description 34
- 238000004364 calculation method Methods 0.000 claims description 18
- 239000013598 vector Substances 0.000 claims description 17
- 238000001914 filtration Methods 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 4
- 230000009286 beneficial effect Effects 0.000 description 8
- 238000000034 method Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000001747 exhibiting effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 239000003153 chemical reaction reagent Substances 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000007480 spreading Effects 0.000 description 1
- 238000003892 spreading Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The invention provides a full-network popularity analysis system for cultural relic digital cloud exhibition, which belongs to the technical field of popularity analysis, and comprises a data screening module, a related word determining module and a popularity analysis module, wherein effective data related to the cultural relic digital cloud exhibition is extracted through a network social platform, then a keyword set of the cultural relic digital cloud exhibition is expanded through a vocabulary search engine, corresponding effective data are expanded, the maximum popularity and the minimum popularity of the related field of the cultural relic digital cloud exhibition are obtained according to the processing result of the obtained effective data in the keyword set, and the popularity of the full-network digital cloud exhibition of the cultural relic is determined, so that the analysis of the knowledge of the cultural relic digital cloud exhibition by all people using the network social platform is realized.
Description
Technical Field
The invention relates to the technical field of popularity analysis, in particular to a system for analyzing popularity of a cultural relic digital cloud exhibition whole network.
Background
In recent years, along with the development of science and technology, the way of understanding the cultural relics is not only limited to field viewing, news picture understanding and related people teaching, but also digital cloud exhibition is used as a display platform to digitize the cultural relics, and then online display is performed, so that the cultural relics are facilitated to be transmitted in a lossless, detailed and real manner while the cultural relics are convenient to view, but due to the fact that the network digital platform is numerous, the audience has great changes, is educated and used, is also used for advertising, namely whether the cultural relics are known by the public, and is also unknown to a certain extent, so that popularization analysis is needed for understanding the knowledge of the cultural relics by the public.
Therefore, the invention provides a system for analyzing the popularity of the cultural relic digital cloud exhibition whole network.
Disclosure of Invention
The invention provides a full-network popularity analysis system for a cultural relic digital cloud exhibition, which is used for extracting effective data related to the cultural relic digital cloud exhibition through an acquisition network social platform, expanding a keyword set of the cultural relic digital cloud exhibition through a vocabulary search engine, expanding corresponding effective data at the same time, obtaining the maximum popularity and the minimum popularity of the cultural relic digital cloud exhibition related field according to the processing result of the obtained effective data in the keyword set, determining the popularity of the full-network cultural relic digital cloud exhibition, and realizing the analysis of understanding conditions of the cultural relic digital cloud exhibition by all people using the network social platform.
The invention provides a system for analyzing the popularity of a cultural relic digital cloud exhibition whole network, which comprises the following components:
and a data screening module: extracting all data related to the digital cloud exhibition of the cultural relics based on a network social platform, and carrying out data screening on all data according to an effective browsing screening rule to obtain effective data;
the related word determining module: searching words related to the number cloud exhibition of the cultural relics from a resource database based on a word search engine to expand a keyword set, and performing field disassembly on the keyword set to determine a current word set of the related field;
popularity analysis module: carrying out combination processing and correlation processing on the effective data and the current word sets in the related fields, and acquiring the maximum popularity based on the combination processing result and the minimum popularity based on the correlation processing result;
the popularity based on the whole network is determined based on the maximum popularity and the minimum popularity of each related field.
The invention provides a cultural relic digital cloud exhibition whole network popularity analysis system, which is characterized in that a data screening module comprises:
a data acquisition unit: primary related data acquisition is carried out based on a social network platform by taking the cultural relic digital cloud exhibition and corresponding synonyms as a first keyword set;
pretreatment unit: preprocessing all primary related data to obtain first related data;
and a valid data screening unit: and effectively screening the first related data of the corresponding data types according to the data types of the first related data and the effective screening conditions of each data type to obtain effective data of the corresponding data types.
The invention provides a cultural relic digital cloud exhibition whole network popularity analysis system, an effective data screening unit, comprising:
frequency of occurrence block: counting the occurrence frequency of each first keyword in all primary related data in the first keyword set, and judging whether the occurrence frequency is larger than or equal to the occurrence threshold value of the corresponding first keyword;
and (3) judging: if the occurrence frequency of the corresponding first keyword is greater than or equal to an occurrence threshold value, judging the importance of the position of the corresponding first keyword in all primary related data to obtain primary effectiveness of the corresponding first keyword under different data types, and marking the corresponding first keyword;
article screening block: screening all first articles without any mark from all primary related data, and obtaining second articles which meet the filtering condition and belong to different data types to obtain the article effectiveness under the same data type, wherein the filtering condition is related to the real browsing quantity;
condition determination block: and determining the effective screening condition of the corresponding data type according to the primary effectiveness of all the first keywords related to the same data type and the article effectiveness.
The invention provides a system for analyzing the popularity of a cultural relic digital cloud exhibition whole network, which comprises a related word determining module, a data processing module and a data processing module, wherein the related word determining module comprises:
related vocabulary matching unit: controlling a vocabulary search engine to search related vocabularies in a resource database according to cultural relics and/or digital cloud exhibition, wherein the related vocabularies comprise: hypernyms, hyponyms and synonyms;
classification unit: expanding the first keyword set according to the related vocabulary to obtain a second keyword set, and performing field classification on the second keyword set to obtain an initial word set of the related field;
a data acquisition unit: acquiring second related data of the related field from the network social platform according to the initial word set of the related field;
quantization processing unit: performing quantization processing on all kinds of effective data to obtain data quantization values of each data type, and simultaneously, processing all second related data to obtain extended quantization values of the second related data in the related field;
a judging unit: judging whether the initial word set in the related field is successfully expanded or not according to the data quantization value of the effective data corresponding to the data type matched with the related field and the expansion quantization value of the second related data;
if the expansion is successful, the initial word set of the related field is regarded as the current word set;
if the expansion is unsuccessful, constructing the first N1 vocabularies with the front occurrence weights in the initial vocabulary set of the related field to obtain the current vocabulary set.
The invention provides a cultural relic digital cloud span whole network popularity analysis system, which comprises a quantization processing unit, a data processing unit and a data processing unit, wherein the quantization processing unit comprises:
index determination block: determining channel sources of each data type based on the network social platform, and determining an initial quantization index of each channel source;
index search block: searching the matched quantization indexes of the residual channel sources according to the initial quantization index of each channel source;
matrix building block: constructing an index vector of each channel source, and constructing a data matrix of a corresponding data type according to the data configuration condition of each index element in the index vector;
matrix comparison block: comparing the data matrix under the same data type with the data matrix obtained by constructing all effective data to obtain a difference matrix;
the desired calculation block: performing expected calculation on the difference matrix to obtain an expected value;
when the expected value reaches the expected requirement, reserving an index vector corresponding to the channel source;
mode matching block: and on the basis of all quantization indexes in all reserved vectors, matching from an index-quantization mapping table to obtain a quantization mode, and carrying out quantization processing on effective data under corresponding data types.
The invention provides a cultural relic digital cloud exhibition whole network popularity analysis system, wherein the judging unit comprises:
wherein g1 i1 A data quantization value representing the i1 st valid data in the corresponding related art; g2 i2 Representing an extended quantized value corresponding to the i2 nd second related data in the related art; n1 represents the number of data quantized values in the corresponding related field; n2 represents the number of extended quantized values in the corresponding related field; p1 represents a judgment result;
when P1 is larger than 0, judging that the expansion is successful;
otherwise, judging that the expansion fails.
The invention provides a popularity analysis system of a cultural relic digital cloud exhibition whole network, which comprises:
strike determination unit: carrying out processing on the current word set and the effective data in the same related field to obtain a plurality of second keywords, respectively counting the browsing quantity of each second keyword in different historical time periods, and constructing to obtain a historical browsing trend;
maximum calculation unit: obtaining the maximum popularity in the related field according to the maximum browsing value and the duration of the maximum browsing value in the historical browsing trend of each second keyword;
minimum calculation unit: performing related processing on the current word set and the effective data in the same related field to obtain a plurality of third keywords, and obtaining the minimum popularity in the related field according to the browsing time period and the browsing total amount of each third keyword, wherein the browsing time period is larger than a preset browsing value in the historical browsing trend;
and a comprehensive calculation unit: the popularity based on the whole network is determined based on the maximum popularity and the minimum popularity of each related field.
The invention provides a cultural relic digital cloud exhibition whole network popularity analysis system, which comprises a comprehensive calculation unit, a data acquisition unit and a data analysis unit, wherein the comprehensive calculation unit comprises:
wherein W is j1 A popularity weight indicating the j1 st related art; p (P) max.j1 Represents the maximum popularity of the j1 st related art; p (P) min.j1 Representing the minimum popularity of the j1 st related art; m1 represents total data of the related art; δ1 j1 A fine-tuning presence function representing the j1 st related art; m2 represents all δ1 j1 The number of the intermediate values is 1; q1 is the popularity of the whole network.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims thereof as well as the appended drawings.
The technical scheme of the invention is further described in detail through the drawings and the embodiments.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
fig. 1 is a block diagram of a system for analyzing popularity of a cultural relic digital cloud span in an embodiment of the invention.
Detailed Description
The preferred embodiments of the present invention will be described below with reference to the accompanying drawings, it being understood that the preferred embodiments described herein are for illustration and explanation of the present invention only, and are not intended to limit the present invention.
Example 1:
the embodiment of the invention provides a system for analyzing the popularity of a cultural relic digital cloud exhibition whole network, which is shown in fig. 1 and comprises the following steps:
and a data screening module: extracting all data related to the digital cloud exhibition of the cultural relics based on a network social platform, and carrying out data screening on all data according to an effective browsing screening rule to obtain effective data;
the related word determining module: searching words related to the number cloud exhibition of the cultural relics from a resource database based on a word search engine to expand a keyword set, and performing field disassembly on the keyword set to determine a current word set of the related field;
popularity analysis module: carrying out combination processing and correlation processing on the effective data and the current word sets in the related fields, and acquiring the maximum popularity based on the combination processing result and the minimum popularity based on the correlation processing result;
the popularity based on the whole network is determined based on the maximum popularity and the minimum popularity of each related field.
In this embodiment, the network social platform includes a variety of different platforms, such as Facebook, twitter, instagram, youTube, wechet.
In the embodiment, the cultural relic digital cloud exhibition is an innovative way for exhibiting and spreading cultural heritage by utilizing digital technology and a virtual exhibiting platform.
In this embodiment, the effective browsing screening rule sets the occurrence frequency, primary validity and article validity of the corresponding primary related data according to the different kinds of first keywords.
In this embodiment, the vocabulary search engines include an online dictionary, a synonym and anti-ambiguous search engine, a translation search engine, a language learning application, and a vocabulary learning tool.
In this embodiment, the process of expanding the keyword set is to search related vocabularies of the cultural relics and the digital cloud exhibition according to a vocabulary search engine, add Guan Cihui to the first keyword set to obtain a second keyword set, classify the second keyword set in the field, collect second related data according to the second keyword set, quantize the effective data of the first related data and the effective data of the second related data, and judge the expansion result according to the quantized result.
In this embodiment, the effective data is obtained by performing a preliminary screening according to the relationship between the occurrence frequency and the occurrence threshold of the first keyword, and setting the effective screening condition of the corresponding data type according to the article effectiveness and the primary effectiveness, thereby screening the primary related data.
In this embodiment, the domain splitting is to divide the second keyword set into domains, for example, the domain to which the cultural relics belong is a historical culture.
In this embodiment, the keywords contained in the current word set are related words in the same field.
In this embodiment, the merging and processing are processes of merging, sorting and analyzing the effective data with the related art.
In this embodiment, the correlation process is that the valid data is associated and integrated with the current word set in the related field, and a connection between the valid data and the current word set is established, for example, a document description in the valid data is associated with a specific term in the current word set, or a document image is associated with a specific style or period.
The working principle and the beneficial effects of the technical scheme are as follows: extracting effective data related to the cultural relic digital cloud exhibition by the network social platform, expanding a keyword set of the cultural relic digital cloud exhibition by the vocabulary search engine, expanding corresponding effective data, obtaining the maximum popularity and the minimum popularity of the cultural relic digital cloud exhibition related field according to the processing result of the obtained effective data on the keyword set and the related processing result, determining the popularity of the cultural relic digital cloud exhibition in the whole network, and analyzing the knowledge of people using the network social platform on the cultural relic digital cloud exhibition.
Example 2:
the embodiment of the invention provides a system for analyzing the popularity of a cultural relic digital cloud exhibition whole network, and a data screening module, which comprises the following components:
a data acquisition unit: primary related data acquisition is carried out on the basis of a network social platform by taking the cultural relic digital cloud exhibition and corresponding synonyms as a first keyword set;
pretreatment unit: preprocessing all primary related data to obtain first related data;
and a valid data screening unit: and effectively screening the first related data of the corresponding data types according to the data types of the first related data and the effective screening conditions of each data type to obtain first effective data of the corresponding data types.
In this embodiment, the primary related data includes browsing amount and release time of the article corresponding to the data, a position and browsing time distribution of the first keyword set in the search term, and a search amount of each network social platform.
In this embodiment, preprocessing includes text cleaning, word segmentation, stop word removal, and high frequency word removal of the primary related data.
In this embodiment, the first keyword set is a digital cloud span of an cultural relic and a set of keywords thereof, such as a digital cultural relic cloud span.
In this embodiment, the first related data is primary related data corresponding to each keyword after retrieval.
In this embodiment, the data category relates to a category of natural language text, log file, electronic book, news draft, comments and feedback, document data, and the like.
In this embodiment, the effective screening conditions include frequency of occurrence, primary effectiveness, and article effectiveness for the first keyword in the corresponding primary related data.
In this embodiment, the first valid data is first relevant data that meets the valid screening criteria.
The working principle and the beneficial effects of the technical scheme are as follows: after the obtained primary related data are preprocessed through the acquisition of the related data of the first keyword set, the first related data are screened according to different effective screening conditions set according to different data types, and finally effective data corresponding to the data types are obtained, so that analysis of the knowledge of the cultural relics and the digital cloud exhibition by all people using the network social platform is realized.
Example 3:
the embodiment of the invention provides a cultural relic digital cloud exhibition whole network popularity analysis system, an effective data screening unit comprises:
frequency of occurrence block: counting the occurrence frequency of each first keyword in all primary related data in the first keyword set, and judging whether the occurrence frequency is larger than or equal to the occurrence threshold value of the corresponding first keyword;
and (3) judging: if the occurrence frequency of the corresponding first keyword is greater than or equal to an occurrence threshold value, judging the importance of the position of the corresponding first keyword in all primary related data to obtain primary effectiveness of the corresponding first keyword under different data types, and marking the corresponding first keyword;
article screening block: screening all first articles without any mark from all primary related data, and obtaining second articles which meet the filtering condition and belong to different data types to obtain the article effectiveness under the same data type, wherein the filtering condition is related to the real browsing quantity;
condition determination block: and determining the effective screening condition of the corresponding data type according to the primary effectiveness of all the first keywords related to the same data type and the article effectiveness.
In this embodiment, the occurrence frequency is determined based on the article data corresponding to each keyword.
In this embodiment, the occurrence threshold is determined according to the article type of the article to which the first keyword corresponds.
In this embodiment, the importance of the position is the position where the keyword corresponding sentence is located in the entire article, where the position includes a subject, an object, a table, a complement, and the like, and the importance is sequentially reduced.
In this embodiment, the primary validity is an average value of the primary validity of the first keyword under the same data type=the importance of all the positions of the first keyword under the same data type according to the determination result of the positions of all the corresponding sentences of the first keyword in the article.
In this embodiment, the article validity is a determination of the validity degree of the obtained related article of the first keyword, for example, the validity degree approaches to 0 in 1990 and 2020, that is, the higher the browsing degree is, the higher the corresponding article validity is.
The working principle and the beneficial effects of the technical scheme are as follows: and carrying out preliminary screening according to the relation between the occurrence frequency of the first keywords and the occurrence threshold value, and setting effective screening conditions of corresponding data types through article effectiveness and primary effectiveness, so as to realize analysis of the cultural relic digital cloud exhibition understanding conditions of all people using the network social platform.
Example 4:
the embodiment of the invention provides a system for analyzing the popularity of a cultural relic digital cloud exhibition whole network, which comprises a related word determining module, a data processing module and a data processing module, wherein the related word determining module comprises the following components:
related vocabulary matching unit: controlling a vocabulary search engine to search related vocabularies in a resource database according to cultural relics and/or digital cloud exhibition, wherein the related vocabularies comprise: hypernyms, hyponyms and synonyms;
classification unit: expanding the first keyword set according to the related vocabulary to obtain a second keyword set, and performing field classification on the second keyword set to obtain an initial word set of the related field;
a data acquisition unit: acquiring second related data of the related field from the network social platform according to the initial word set of the related field;
quantization processing unit: performing quantization processing on all kinds of effective data to obtain data quantization values of each data type, and simultaneously, processing all second related data to obtain extended quantization values of the second related data in the related field;
a judging unit: judging whether the initial word set in the related field is successfully expanded or not according to the data quantization value of the effective data corresponding to the data type matched with the related field and the expansion quantization value of the second related data;
if the expansion is successful, the initial word set of the related field is regarded as the current word set;
if the expansion is unsuccessful, constructing the first N1 vocabularies with the front occurrence weights in the initial vocabulary set of the related field to obtain the current vocabulary set.
In this embodiment, after the meaning and definition of the keyword are analyzed, the vocabulary search engine matches the related vocabulary corresponding to the keyword, for example, the upper word of the cultural relic is cultural heritage, historical goods, cultural goods, archaeological remains and historical heritage, the lower word is ancient cultural relic, artwork, cultural relic and cultural relic exhibition, and the synonym is ancient and heritage.
In this embodiment, the cultural relics and/or the digital cloud exhibition refer to the related vocabulary of each of the cultural relics and the digital cloud exhibition and the related vocabulary of the cultural relics and the digital cloud exhibition simultaneously exist, for example, the upper words of the digital cloud exhibition of the cultural relics are digitalized for the cultural relics, the lower words are digital cultural heritage, and the synonyms are digital cultural relics for the cultural relics.
In this embodiment, the resource database is a database of related words and different combinations of related words, which are predetermined.
In this embodiment, the initial set of words is a set of words after a different domain division of the second set of keywords, wherein the related domain includes cultural heritage management, museum, information science, computer science, art history, cultural anthropology, digital anthropology, education, and cultural travel.
In this embodiment, the second related data is data of the second keyword set collected at the network social platform under the corresponding domain.
In this embodiment, the quantization process determines an initial quantization index according to a channel source of a data type, searches for a matching quantization index, and constructs an index vector for each channel according to the obtained index, thereby obtaining a data matrix corresponding to the data type.
In this embodiment, a first keyword set is constructed based on the vocabulary 1 and the vocabulary 2, and when the vocabulary 3 (related vocabulary) exists, it is necessary to obtain an expanded word related to the vocabulary 3 to expand the first keyword set, so as to obtain a second keyword set.
The working principle and the beneficial effects of the technical scheme are as follows: searching related vocabularies of the cultural relics and the digital cloud exhibition by a vocabulary search engine, adding Guan Cihui into a first keyword set to obtain a second keyword set, carrying out field classification on the second keyword set, collecting second related data according to the second keyword set, carrying out quantization processing on effective data of the first related data and effective data of the second related data, judging whether the second keyword set is successfully established according to a quantization processing result, and realizing acquisition and analysis of all keywords and data of the cultural relics digital cloud platform and the possible fields thereof and analysis of knowledge of the cultural relics digital cloud exhibition by all people using a network social platform.
Example 5:
the embodiment of the invention provides a system for analyzing the popularity of a cultural relic digital cloud exhibition whole network, which comprises a quantization processing unit, a data processing unit and a data processing unit, wherein the quantization processing unit comprises:
index determination block: determining channel sources of each data type based on the network social platform, and determining an initial quantization index of each channel source;
index search block: searching the matched quantization indexes of the residual channel sources according to the initial quantization index of each channel source;
matrix building block: constructing an index vector of each channel source, and constructing a data matrix of a corresponding data type according to the data configuration condition of each index element in the index vector;
matrix comparison block: comparing the data matrix under the same data type with the data matrix obtained by constructing all effective data to obtain a difference matrix;
the desired calculation block: performing expected calculation on the difference matrix to obtain an expected value;
when the expected value reaches the expected requirement, reserving an index vector corresponding to the channel source;
mode matching block: and on the basis of all quantization indexes in all reserved vectors, matching from an index-quantization mapping table to obtain a quantization mode, and carrying out quantization processing on effective data under corresponding data types.
In this embodiment, the channel sources of the network social platform include search engines, direct access, recommended links, social media sharing, mobile applications, email invitations, advertising and promotion, search and browsing functions and social connections, that is, the sources of different data types are different, for example, the sources of data type 1 are: source 1, source 2, source of data types: source a1, source a2.
In this embodiment, the initial quantization index is assigned per channel itself, and is a vocabulary effect index, a vocabulary storage slot position index, a vocabulary type index, a user participation index, etc. for the source.
In this embodiment, the data configuration situation is a situation where specific data is collected, including relevant data such as system operation, user activity, and the like.
In this embodiment, the index vector= [ match quantization index 1 match quantization index 2. ];
when there is no data in a certain position of the data matrix, 0 is used to replace the data, and the data configuration condition is various vocabulary data related to the corresponding element.
In this embodiment, the number of rows and columns of the data matrix constructed by the valid data is equal to the number of columns and rows of the data matrix constructed by the valid data, and the two matrices are subtracted to obtain a difference matrix.
In this embodiment of the present invention, the process is performed,
wherein Q11 represents an expected value; h2 represents the number of columns of the difference matrix; h1 represents a row of the difference matrix; H10H 10 h1 Representing the number of elements of 0 in the h1 row in the difference matrix; H20H 20 h2 Representing the number of elements 0 in the h2 column in the difference matrix; ave h1 Representing the average value of the h1 th row element in the difference matrix; ave h2 Representing the average value of the h2 column element in the difference matrix;representing the variance of the h1 st row element in the difference matrix; />Representing the variance of the h2 th column element in the difference matrix; min represents the minimum sign.
In this embodiment, the desired value is less than 0.6.
In this embodiment, the index-quantization mapping table is a tool for associating system indexes with reagent quantization data, and includes various indexes, quantization methods, data sources, calculation formulas, time ranges and other information related to each index, and the purpose of the quantization method is to perform numerical normalization processing on data under different indexes.
The working principle and the beneficial effects of the technical scheme are as follows: determining corresponding initial quantization indexes and matching quantization indexes according to channel sources of each data type, generating index vectors and data matrixes, calculating the data matrixes to obtain reserved index vectors, and analyzing the knowledge of people using a network social platform on the cultural relic digital cloud exhibition according to quantization modes of the reserved index vectors on all effective data.
Example 6:
the embodiment of the invention provides a system for analyzing the popularity of a cultural relic digital cloud exhibition whole network, wherein the judging unit comprises:
wherein,g1 i1 a data quantization value representing the i1 st valid data in the corresponding related art; g2 i2 Representing an extended quantized value corresponding to the i2 nd second related data in the related art; n1 represents the number of data quantized values in the corresponding related field; n2 represents the number of extended quantized values in the corresponding related field; p1 represents a judgment result;
when P1 is larger than 0, judging that the expansion is successful;
otherwise, judging that the expansion fails.
The working principle and the beneficial effects of the technical scheme are as follows: and determining a final judgment result according to the data quantization value of the effective data in the related field and the expansion quantization value of the second related data, realizing the quantization of the effective data, judging whether the keyword set expansion is successful or not according to the quantization result, and therefore, realizing the analysis of the knowledge of people using the network social platform on the cultural relics digital cloud exhibition.
Example 7:
the embodiment of the invention provides a popularity analysis system of a cultural relic digital cloud exhibition whole network, which comprises:
strike determination unit: carrying out processing on the current word set and the effective data in the same related field to obtain a plurality of second keywords, respectively counting the browsing quantity of each second keyword in different historical time periods, and constructing to obtain a historical browsing trend;
maximum calculation unit: obtaining the maximum popularity in the related field according to the maximum browsing value and the duration of the maximum browsing value in the historical browsing trend of each second keyword;
minimum calculation unit: performing related processing on the current word set and the effective data in the same related field to obtain a plurality of third keywords, and obtaining the minimum popularity in the related field according to the browsing time period and the browsing total amount of each third keyword, wherein the browsing time period is larger than a preset browsing value in the historical browsing trend;
and a comprehensive calculation unit: the popularity based on the whole network is determined based on the maximum popularity and the minimum popularity of each related field.
In this embodiment, the history browsing trend is a browsing curve formed by the browsing numbers of different network social platforms within the effective period of the corresponding text information, and according to the curve, whether the browsing trend is seen by more people or by fewer people can be analyzed.
In this embodiment, the maximum popularity is calculated based on the maximum browsing amount and the duration of the maximum browsing amount, P max ＝L max /Z1+(C1/Z1)/L y Wherein L is max Is the maximum browsing amount; c1 is the duration of the maximum browsing volume; z1 is the total browsing duration in the browsing trend; l (L) y Is a preset browsing value;
in this embodiment, the minimum popularity is calculated based on the browsing time period greater than the preset browsing value in the history of browsing and the total browsing amount,wherein P is min Is the least popular; t2 is the duration of a browsing time period which is greater than a preset browsing value in the history browsing trend; l (L) z To browse the total.
In this embodiment, the determination of the popularity of the whole network is obtained by performing a functional correlation operation on the maximum popularity and the minimum popularity of the relevant field.
The working principle and the beneficial effects of the technical scheme are as follows: and obtaining a second keyword according to the combined processing result of the current word set and the effective data, determining a historical browsing trend, determining the maximum popularity according to the historical browsing trend, obtaining a third keyword according to the related processing result of the current word set and the effective data, determining the minimum popularity of the related field, and obtaining the whole network popularity, so that analysis of the knowledge of the digital cloud exhibition of the cultural relics by all people using the network social platform is realized.
Example 8:
an embodiment of the present invention provides a system for analyzing popularity of a cultural relic digital cloud span, according to claim 7, wherein the comprehensive calculating unit includes:
wherein W is j1 A popularity weight indicating the j1 st related art; p (P) max.j1 Represents the maximum popularity of the j1 st related art; p (P) min.j1 Representing the minimum popularity of the j1 st related art; m1 represents total data of the related art; δ1 j1 A fine-tuning presence function representing the j1 st related art; m2 represents all δ1 j1 The number of the intermediate values is 1; q1 is the popularity of the whole network.
The working principle and the beneficial effects of the technical scheme are as follows: and determining the full-network popularity of the cultural relic digital cloud disk according to the popularity weight and the related popularity corresponding to the related fields, so as to realize analysis of knowledge of the cultural relic digital cloud exhibition by all people using the network social platform.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (8)
1. The utility model provides a historical relic digital cloud exhibition full-network popularity analysis system which characterized in that includes:
and a data screening module: extracting all data related to the digital cloud exhibition of the cultural relics based on a network social platform, and carrying out data screening on all data according to an effective browsing screening rule to obtain effective data;
the related word determining module: searching words related to the number cloud exhibition of the cultural relics from a resource database based on a word search engine to expand a keyword set, and performing field disassembly on the keyword set to determine a current word set of the related field;
popularity analysis module: carrying out combination processing and correlation processing on the effective data and the current word sets in the related fields, and acquiring the maximum popularity based on the combination processing result and the minimum popularity based on the correlation processing result;
the popularity based on the whole network is determined based on the maximum popularity and the minimum popularity of each related field.
2. The system for analyzing the popularity of a cultural relic digital cloud span-wise network according to claim 1, wherein the data screening module comprises:
a data acquisition unit: primary related data acquisition is carried out based on a social network platform by taking the cultural relic digital cloud exhibition and corresponding synonyms as a first keyword set;
pretreatment unit: preprocessing all primary related data to obtain first related data;
and a valid data screening unit: and effectively screening the first related data of the corresponding data types according to the data types of the first related data and the effective screening conditions of each data type to obtain effective data of the corresponding data types.
3. The cultural relic digital cloud span-wise whole network popularity analysis system of claim 2, wherein the effective data screening unit comprises:
frequency of occurrence block: counting the occurrence frequency of each first keyword in all primary related data in the first keyword set, and judging whether the occurrence frequency is larger than or equal to the occurrence threshold value of the corresponding first keyword;
and (3) judging: if the occurrence frequency of the corresponding first keyword is greater than or equal to an occurrence threshold value, judging the importance of the position of the corresponding first keyword in all primary related data to obtain primary effectiveness of the corresponding first keyword under different data types, and marking the corresponding first keyword;
article screening block: screening all first articles without any mark from all primary related data, and obtaining second articles which meet the filtering condition and belong to different data types to obtain the article effectiveness under the same data type, wherein the filtering condition is related to the real browsing quantity;
condition determination block: and determining the effective screening condition of the corresponding data type according to the primary effectiveness of all the first keywords related to the same data type and the article effectiveness.
4. The system for analyzing the popularity of the digital cloud exhibition of the cultural relics according to claim 2, wherein the related term determining module comprises:
related vocabulary matching unit: controlling a vocabulary search engine to search related vocabularies in a resource database according to cultural relics and/or digital cloud exhibition, wherein the related vocabularies comprise: hypernyms, hyponyms and synonyms;
classification unit: expanding the first keyword set according to the related vocabulary to obtain a second keyword set, and performing field classification on the second keyword set to obtain an initial word set of the related field;
a data acquisition unit: acquiring second related data of the related field from the network social platform according to the initial word set of the related field;
quantization processing unit: performing quantization processing on all kinds of effective data to obtain data quantization values of each data type, and simultaneously, processing all second related data to obtain extended quantization values of the second related data in the related field;
a judging unit: judging whether the initial word set in the related field is successfully expanded or not according to the data quantization value of the effective data corresponding to the data type matched with the related field and the expansion quantization value of the second related data;
if the expansion is successful, the initial word set of the related field is regarded as the current word set;
if the expansion is unsuccessful, constructing the first N1 vocabularies with the front occurrence weights in the initial vocabulary set of the related field to obtain the current vocabulary set.
5. The system for analyzing the popularity of a cultural relic digital cloud span-wise network according to claim 4, wherein the quantization processing unit comprises:
index determination block: determining channel sources of each data type based on the network social platform, and determining an initial quantization index of each channel source;
index search block: searching the matched quantization indexes of the residual channel sources according to the initial quantization index of each channel source;
matrix building block: constructing an index vector of each channel source, and constructing a data matrix of a corresponding data type according to the data configuration condition of each index element in the index vector;
matrix comparison block: comparing the data matrix under the same data type with the data matrix obtained by constructing all effective data to obtain a difference matrix;
the desired calculation block: performing expected calculation on the difference matrix to obtain an expected value;
when the expected value reaches the expected requirement, reserving an index vector corresponding to the channel source;
mode matching block: and on the basis of all quantization indexes in all reserved vectors, matching from an index-quantization mapping table to obtain a quantization mode, and carrying out quantization processing on effective data under corresponding data types.
6. The system for analyzing the popularity of a cultural relic digital cloud span according to claim 4, wherein the judging unit comprises:
wherein g1 i1 A data quantization value representing the i1 st valid data in the corresponding related art; g2 i2 Representing an extended quantized value corresponding to the i2 nd second related data in the related art; n1 represents the number of data quantized values in the corresponding related field; n2 represents the number of extended quantized values in the corresponding related field; p1 represents a judgment result;
when P1 is larger than 0, judging that the expansion is successful;
otherwise, judging that the expansion fails.
7. The system of claim 1, wherein the popularity analysis module comprises:
strike determination unit: carrying out processing on the current word set and the effective data in the same related field to obtain a plurality of second keywords, respectively counting the browsing quantity of each second keyword in different historical time periods, and constructing to obtain a historical browsing trend;
maximum calculation unit: obtaining the maximum popularity in the related field according to the maximum browsing value and the duration of the maximum browsing value in the historical browsing trend of each second keyword;
minimum calculation unit: performing related processing on the current word set and the effective data in the same related field to obtain a plurality of third keywords, and obtaining the minimum popularity in the related field according to the browsing time period and the browsing total amount of each third keyword, wherein the browsing time period is larger than a preset browsing value in the historical browsing trend;
and a comprehensive calculation unit: the popularity based on the whole network is determined based on the maximum popularity and the minimum popularity of each related field.
8. The system for analyzing the popularity of a cultural relic digital cloud span-wise network according to claim 7, wherein the comprehensive calculating unit comprises:
wherein W is j1 A popularity weight indicating the j1 st related art; p (P) max.j1 Represents the maximum popularity of the j1 st related art; p (P) min.j1 Represent the firstj1 minimum popularity of related fields; m1 represents total data of the related art; δ1 j1 A fine-tuning presence function representing the j1 st related art; m2 represents all δ1 j1 The number of the intermediate values is 1; q1 is the popularity of the whole network.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311291310.9A CN117235380B (en) | 2023-10-07 | Cultural relic digital cloud exhibition whole-network popularity analysis system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311291310.9A CN117235380B (en) | 2023-10-07 | Cultural relic digital cloud exhibition whole-network popularity analysis system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117235380A true CN117235380A (en) | 2023-12-15 |
| CN117235380B CN117235380B (en) | 2024-05-14 |
Family
ID=
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106649367A (en) * | 2015-10-30 | 2017-05-10 | 北京国双科技有限公司 | Method and device for detecting popularization degree of keyword |
| CN106777354A (en) * | 2017-01-17 | 2017-05-31 | 腾讯科技（深圳）有限公司 | Promotion message freshness determines method and device |
| CN109829091A (en) * | 2018-08-28 | 2019-05-31 | 上海雅高文化传播有限公司 | Assessment method, computer storage medium and the terminal of electronic works prevalence |
| CN110704613A (en) * | 2019-08-23 | 2020-01-17 | 上海科技发展有限公司 | Vocabulary database construction and query method, database system, equipment and medium |
| CN111859092A (en) * | 2020-07-29 | 2020-10-30 | 苏州思必驰信息科技有限公司 | Text corpus amplification method and device, electronic equipment and storage medium |
| CN114020867A (en) * | 2021-11-04 | 2022-02-08 | 山东库睿科技有限公司 | Method, device, equipment and medium for expanding search terms |
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106649367A (en) * | 2015-10-30 | 2017-05-10 | 北京国双科技有限公司 | Method and device for detecting popularization degree of keyword |
| CN106777354A (en) * | 2017-01-17 | 2017-05-31 | 腾讯科技（深圳）有限公司 | Promotion message freshness determines method and device |
| CN109829091A (en) * | 2018-08-28 | 2019-05-31 | 上海雅高文化传播有限公司 | Assessment method, computer storage medium and the terminal of electronic works prevalence |
| CN110704613A (en) * | 2019-08-23 | 2020-01-17 | 上海科技发展有限公司 | Vocabulary database construction and query method, database system, equipment and medium |
| CN111859092A (en) * | 2020-07-29 | 2020-10-30 | 苏州思必驰信息科技有限公司 | Text corpus amplification method and device, electronic equipment and storage medium |
| CN114020867A (en) * | 2021-11-04 | 2022-02-08 | 山东库睿科技有限公司 | Method, device, equipment and medium for expanding search terms |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110008311B (en) | Product information safety risk monitoring method based on semantic analysis | |
| CN106570708B (en) | Management method and system of intelligent customer service knowledge base | |
| CN109543178B (en) | Method and system for constructing judicial text label system | |
| US20210056571A1 (en) | Determining of summary of user-generated content and recommendation of user-generated content | |
| CN111737495A (en) | Middle-high-end talent intelligent recommendation system and method based on domain self-classification | |
| CN107862070B (en) | Online classroom discussion short text instant grouping method and system based on text clustering | |
| CN112035658B (en) | Enterprise public opinion monitoring method based on deep learning | |
| CN112667794A (en) | Intelligent question-answer matching method and system based on twin network BERT model | |
| CN105095187A (en) | Search intention identification method and device | |
| CN111104526A (en) | Financial label extraction method and system based on keyword semantics | |
| US10366117B2 (en) | Computer-implemented systems and methods for taxonomy development | |
| CN110110225B (en) | Online education recommendation model based on user behavior data analysis and construction method | |
| US10387805B2 (en) | System and method for ranking news feeds | |
| CN103309869B (en) | Method and system for recommending display keyword of data object | |
| CN104199965A (en) | Semantic information retrieval method | |
| CN110287314B (en) | Long text reliability assessment method and system based on unsupervised clustering | |
| CN112559684A (en) | Keyword extraction and information retrieval method | |
| CN113886604A (en) | Job knowledge map generation method and system | |
| CN110910175A (en) | Tourist ticket product portrait generation method | |
| CN110110220A (en) | Merge the recommended models of social networks and user's evaluation | |
| CN116010552A (en) | Engineering cost data analysis system and method based on keyword word library | |
| CN110310012B (en) | Data analysis method, device, equipment and computer readable storage medium | |
| CN105354184A (en) | Method for using optimized vector space model to automatically classify document | |
| CN104572915A (en) | User event relevance calculation method based on content environment enhancement | |
| CN117235380B (en) | Cultural relic digital cloud exhibition whole-network popularity analysis system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |