CN114925286A - Public opinion data processing method and device - Google Patents
Public opinion data processing method and device Download PDFInfo
- Publication number
- CN114925286A CN114925286A CN202210850838.4A CN202210850838A CN114925286A CN 114925286 A CN114925286 A CN 114925286A CN 202210850838 A CN202210850838 A CN 202210850838A CN 114925286 A CN114925286 A CN 114925286A
- Authority
- CN
- China
- Prior art keywords
- information
- public opinion
- data
- data storage
- content
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/901—Indexing; Data structures therefor; Storage structures
- G06F16/9027—Trees
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/906—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a public opinion data processing method and device, comprising the following steps: clustering all first public opinion information according to first keywords in the first public opinion information to obtain a plurality of first information sets; establishing a first tree graph corresponding to a first keyword according to the preset keyword corresponding to the first keyword, and taking the preset keyword as a root node of the first tree graph; establishing a plurality of first child nodes according to the first information category; generating a corresponding first grandchild node and a first data storage unit according to the first information content of each piece of first public opinion information, and forming a first data storage space according to all the first data storage units; and updating the first tree diagram and the first data storage space according to the second information type and the second information content of the second public opinion information to obtain a second tree diagram and a second data storage space. The invention can quickly and efficiently remove and store public sentiment data.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a public opinion data processing method and device.
Background
Public opinion monitoring integrates an internet information acquisition technology and an information intelligent processing technology, and information requirements of a user such as network public opinion monitoring and news topic tracking are met by automatically grabbing internet mass information, automatically classifying and clustering, topic detection and topic focusing, so that analysis results such as briefings, reports and charts are formed, and analysis basis is provided for a client to comprehensively master the thought dynamics of the public and make correct public opinion guidance.
Public opinion data is stored on the premise of public opinion monitoring, and in the prior art, quick and efficient duplicate removal and storage of the public opinion data cannot be realized.
Disclosure of Invention
The embodiment of the invention provides a public opinion data processing method and device, which can be used for quickly and efficiently removing and storing public opinion data.
In a first aspect of the embodiments of the present invention, a public opinion data processing method is provided, including:
the method comprises the steps of capturing public opinion data at a plurality of target positions, wherein the public opinion data at least comprise first public opinion information, clustering all the first public opinion information according to first keywords in the first public opinion information to obtain a plurality of first information sets, and each first information set is provided with corresponding preset keywords;
establishing a first tree graph corresponding to a preset keyword corresponding to the first keyword according to the preset keyword, and taking the preset keyword as a root node of the first tree graph;
acquiring all first information types of first public opinion information in a first information set, establishing a plurality of first child nodes according to the first information types, wherein each child node corresponds to one first information type, and connecting the first child nodes with the root node;
generating a corresponding first grandchild node and a corresponding first data storage unit according to first information content of each first public opinion information, connecting the first grandchild node with the corresponding first child node according to a first information type of each first public opinion information, storing the first public opinion information to the corresponding first data storage unit, and forming a first data storage space according to all the first data storage units;
and when judging that the second public opinion information corresponding to the key word in the dendrogram is captured, updating the first dendrogram and the first data storage space according to the second information type and the second information content of the second public opinion information to obtain a second dendrogram and a second data storage space.
Optionally, in a possible implementation manner of the first aspect, the capturing public opinion data at a plurality of target locations, the public opinion data including at least one first public opinion information, clustering all the first public opinion information according to a first keyword in the first public opinion information to obtain a plurality of first information sets, each first information set having a corresponding keyword, includes:
the method comprises the steps of obtaining a pre-configured public opinion key phrase, and generating a corresponding public opinion information set according to the public opinion key phrase, wherein the public opinion key phrase comprises at least one preset keyword;
comparing a first keyword in the first public opinion information with preset keywords in a public opinion keyword group, classifying the first public opinion information corresponding to any one preset keyword into a corresponding public opinion information set to obtain a plurality of first information sets, wherein the keyword corresponding to the first information set is the preset keyword.
Optionally, in a possible implementation manner of the first aspect, the establishing, according to the keyword, a first tree graph corresponding to the keyword, and using the first keyword as a root node of the first tree graph includes:
establishing a first tree graph corresponding to the first information set;
extracting all preset keywords corresponding to the first information set, establishing 1 root node in the first dendrogram, and filling the preset keywords to the root node.
Optionally, in a possible implementation manner of the first aspect, the obtaining all first information types of first public opinion information in the first information set, establishing a plurality of first child nodes according to the first information types, where each child node corresponds to one first information type, and connecting the first child nodes with the root node includes:
the first information type of the first public opinion information is any one of character type, image type or audio type and video type;
and establishing first child nodes corresponding to all first information types of the first public opinion information, and respectively connecting all the first child nodes with the root node.
Optionally, in a possible implementation manner of the first aspect, the generating, according to the first information content of each first public opinion information, a corresponding first grandchild node and a first data storage unit, connecting the first grandchild node and the corresponding first child node according to the first information category of each first public opinion information, storing the first public opinion information in the corresponding first data storage unit, and forming a first data storage space according to all the first data storage units includes:
acquiring first information content of each piece of first public opinion information, wherein the first information content is any one of character content, image content, audio content and video content;
respectively establishing a first grandchild node and a first data storage unit corresponding to first information content, and associating the first grandchild node with the first data storage unit through a data calling path, so that the first information content in the first data storage unit is called based on the data calling path when the corresponding first grandchild node is triggered;
generating a corresponding first data identifier according to a first information type of each first public opinion information, and storing the first data identifier in a corresponding first data storage unit;
and counting all the first data storage units to generate corresponding first data storage spaces.
Optionally, in a possible implementation manner of the first aspect, the generating a corresponding first data identifier according to the first information category of each first public opinion information, and storing the first data identifier in a corresponding first data storage unit includes:
if the first information content of the first public opinion information is judged to be text content or image content, acquiring a character string corresponding to the first public opinion information in the text type or the image type, and performing hash operation on the character string to obtain a first hash value;
and taking the first hash value as a first data identifier of first public opinion information of text content or image content.
Optionally, in a possible implementation manner of the first aspect, the generating a corresponding first data identifier according to the first information category of each first public opinion information, and storing the first data identifier in a corresponding first data storage unit includes:
if the first information type of the first public opinion information is judged to be audio content or video content, acquiring a first termination time value and a first information data quantity value of the audio content or the video content;
shifting the first termination time value according to a preset time period to obtain a termination time period, and shifting the first information data quantity value according to a preset data quantity value to obtain an information data interval value;
and taking the termination time period and the information data interval value as a first data identifier of first public sentiment information of the audio content or the video content.
Optionally, in a possible implementation manner of the first aspect, when it is determined that the first public opinion information corresponding to the keyword in the dendrogram is captured, the updating process is performed on the first dendrogram and the first data storage space according to a second information type and a second information content of the second public opinion information to obtain a second dendrogram and a second data storage space, including:
if the second public opinion information is judged to be text content or image content, extracting a character string corresponding to the second public opinion information, and performing hash operation on the character string to obtain a second hash value;
traversing a first hash value of a first data identifier in a first data storage unit corresponding to the text content or the image content, and if the first hash value is judged to be the same as the second hash value, not storing the second public opinion information;
if the first hash value is different from the second hash value, establishing a second grandchild node and a second data storage unit corresponding to second public opinion information, and storing the second public opinion information into the second data storage unit;
and updating the first dendrogram based on the second grandchild node to obtain a second dendrogram, and updating the first data storage space based on the second data storage unit to obtain a second data storage space.
Optionally, in a possible implementation manner of the first aspect, when it is determined that the second public opinion information corresponding to the keyword in the dendrogram is captured, the updating, according to the second information type and the second information content of the second public opinion information, the first dendrogram and the first data storage space, the second dendrogram and the second data storage space are obtained, including:
if the second public opinion information is judged to be audio content or video content, extracting a second termination time value and a second information data quantity value in the second public opinion information;
traversing the termination time period and the information data interval value of a first data identifier in a first data storage unit corresponding to the audio content or the video content, and if the second termination time value is judged to be in the termination time period and the second information data value is judged to be in the information data interval value, not storing the second public opinion information;
if the second termination time value is judged not to be within the termination time period or the second information data quantity value is judged not to be within the information data interval value, establishing a second grandchild node and a second data storage unit corresponding to the second public opinion information, and storing the second public opinion information into the second data storage unit;
and updating the first dendrogram based on the second grandchild node to obtain a second dendrogram, and updating the first data storage space based on the second data storage unit to obtain a second data storage space.
In a second aspect of the embodiments of the present invention, a public opinion data processing apparatus is provided, including:
the system comprises a clustering module, a searching module and a searching module, wherein the clustering module is used for capturing public opinion data at a plurality of target positions, the public opinion data at least comprises first public opinion information, and all the first public opinion information is clustered according to first keywords in the first public opinion information to obtain a plurality of first information sets, and each first information set has corresponding keywords;
the root node establishing module is used for establishing a first dendrogram corresponding to the keyword according to the keyword, and taking the first keyword as a root node of the first dendrogram;
the child node establishing module is used for acquiring all first information types of first public opinion information in a first information set, establishing a plurality of first child nodes according to the first information types, wherein each child node corresponds to one first information type, and connecting the first child nodes with the root node;
the grandchild node establishing module is used for generating a corresponding first grandchild node and a first data storage unit according to the first information content of each first public opinion information, connecting the first grandchild node with a corresponding first child node according to the first information type of each first public opinion information, storing the first public opinion information to the corresponding first data storage unit, and forming a first data storage space according to all the first data storage units;
and the updating module is used for updating the first dendrogram and the first data storage space according to a second information type and a second information content of the second public opinion information to obtain a second dendrogram and a second data storage space when judging that the second public opinion information corresponding to the keyword in the dendrogram is captured.
A third aspect of the embodiments of the present invention provides a storage medium, in which a computer program is stored, and the computer program is used for implementing the method according to the first aspect of the present invention and various possible designs of the first aspect when the computer program is executed by a processor.
Has the advantages that:
1. according to the scheme, the captured public opinion data are classified once based on the public opinion keyword group to obtain a plurality of first information sets so as to classify and store the corresponding public opinion data, when the subsequent duplicate removal comparison is carried out, the corresponding information sets can be directly determined based on the keywords, and then the corresponding information sets are directly compared with the data in the information sets, so that the data processing amount is reduced, and the duplicate removal efficiency is improved without traversing all the stored data; in addition, a tree diagram corresponding to the first information set is constructed, public sentiment data in the same information set are stored in a secondary classification mode according to the data types, when duplicate removal comparison is subsequently carried out, a corresponding data storage unit can be directly determined based on the text type, and then the public sentiment data can be directly compared with the data in the corresponding data storage unit, data of all the data storage units in the first information set do not need to be traversed, data processing amount is further reduced, and duplicate removal efficiency is further improved; simultaneously, this scheme can improve the storage efficiency of public opinion data through above-mentioned mode.
2. The scheme adopts different duplicate removal modes aiming at different data types. The first is that aiming at the text content or the image content, the scheme can convert the character string corresponding to the text content or the image content into a unique hash value, and the unique hash value is utilized to efficiently and accurately realize the duplicate removal of the text content or the image content; secondly, aiming at audio content or video content, the scheme can obtain a termination time value and an information data quantity value based on the characteristics of the audio content or the video content, and can efficiently and accurately realize the duplicate removal of the audio content or the video content by combining the termination time value and the information data quantity value, and compared with the manual audit in the prior art, the scheme has low data processing amount and high efficiency; in addition, the scheme also considers that the time length or the data volume between the same videos or audios may have errors, so that the first termination time value is shifted according to the preset time period to obtain the termination time period, the first information data volume value is shifted according to the preset data volume value to obtain the information data interval value, and the audio content and the video content are accurately and effectively subjected to deduplication processing by using the termination time period and the information data interval value;
3. according to the scheme, each public opinion data is stored, the nodes and the data storage units of the corresponding dendrograms are automatically updated, and accurate deduplication and storage can be directly performed on the basis of the new dendrograms when the deduplication and storage are performed next time; in addition, the scheme utilizes the dendrogram to store data in a classified manner, compared with messy storage in the prior art, when a user inquires public opinion data, the positioning of the public opinion data can be rapidly and effectively realized, the inquiry efficiency is improved, and meanwhile, the user can conveniently manage the public opinion data.
Drawings
Fig. 1 is a flowchart illustrating a public opinion data processing method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a tree diagram according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a public opinion data processing device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
The terms "first," "second," "third," "fourth," and the like in the description and in the claims, as well as in the drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in other sequences than those illustrated or described herein.
It should be understood that, in various embodiments of the present invention, the sequence numbers of the processes do not mean the execution sequence, and the execution sequence of the processes should be determined by the functions and the internal logic of the processes, and should not constitute any limitation on the implementation process of the embodiments of the present invention.
It should be understood that in the present application, "comprising" and "having" and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be understood that, in the present invention, "a plurality" means two or more. "and/or" is only an association relationship describing an associated object, and means that there may be three relationships, for example, a and/or B, and may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. "comprises A, B and C" and "comprises A, B, C" means that all three of A, B, C comprise, "comprises A, B or C" means that one of A, B, C comprises, "comprises A, B and/or C" means that any 1 or any 2 or 3 of A, B, C comprises.
It should be understood that in the present invention, "B corresponding to a", "a corresponds to B", or "B corresponds to a" means that B is associated with a, and B can be determined from a. Determining B from a does not mean determining B from a alone, but may be determined from a and/or other information. And the matching of A and B means that the similarity of A and B is greater than or equal to a preset threshold value.
As used herein, "if" may be interpreted as "at … …" or "at … …" or "in response to a determination" or "in response to a detection", depending on the context.
The technical means of the present invention will be described in detail with reference to specific examples. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments.
Referring to fig. 1, which is a flowchart illustrating a public opinion data processing method according to an embodiment of the present invention, an execution main body of the method shown in fig. 1 may be a software and/or hardware device. The execution subject of the present application may include, but is not limited to, at least one of: user equipment, network equipment, etc. The user equipment may include, but is not limited to, a computer, a smart phone, a Personal Digital Assistant (PDA), the above mentioned electronic equipment, and the like. The network device may include, but is not limited to, a single network server, a server group of multiple network servers, or a cloud of numerous computers or network servers based on cloud computing, wherein cloud computing is one type of distributed computing, a super virtual computer consisting of a cluster of loosely coupled computers. The present embodiment does not limit this. The public opinion data processing method comprises steps S1 to S5, and specifically comprises the following steps:
and S1, capturing public sentiment data at a plurality of target positions, wherein the public sentiment data at least comprise first public sentiment information, and clustering all the first public sentiment information according to first keywords in the first public sentiment information to obtain a plurality of first information sets, and each first information set is provided with corresponding preset keywords.
It can be understood that the invention first captures the public sentiment data at a plurality of target positions, and receives the public sentiment data, wherein the target positions can be artificially set to obtain the target data.
The scheme can process the accessed first public opinion information, and utilizes the first keywords in the first public opinion information to cluster all the first public opinion information to obtain a plurality of first information sets, wherein each first information set is provided with corresponding preset keywords. Through the mode, the first public opinion information accessed can be classified by utilizing the keywords.
In some embodiments, S1 (capturing public opinion data at a plurality of target locations, the public opinion data including at least one first public opinion information, clustering all the first public opinion information according to first keywords in the first public opinion information to obtain a plurality of first information sets, each first information set having corresponding keywords) includes S11-S12:
s11, acquiring a pre-configured public opinion key phrase, and generating a corresponding public opinion information set according to the public opinion key phrase, wherein the public opinion key phrase comprises at least one preset keyword.
According to the scheme, a plurality of public opinion key word groups are preset, wherein the public opinion key word groups are 'A market + temperature', and are 'Lisan + concert', and the like, and meanwhile, a corresponding public opinion information set is generated according to the public opinion key word groups.
S12, comparing the first keyword in the first public opinion information with the preset keyword in the public opinion keyword group, and classifying the first public opinion information corresponding to any one of the preset keywords into a corresponding public opinion information set to obtain a plurality of first information sets, where the keyword corresponding to the first information set is the preset keyword.
According to the scheme, after the first public opinion information is received, the first keywords in the first public opinion information are compared with the preset keywords in the public opinion keyword groups, and then the first public opinion information corresponding to any one preset keyword is classified into the corresponding public opinion information sets to obtain a plurality of first information sets.
Illustratively, the first public opinion information is 'li open singing meeting cheer', the public opinion key word group is 'li three + singing meeting', the corresponding public opinion information set is a public opinion information set a, wherein the key words comprise 'li three' and 'singing meeting', and then the scheme classifies the first public opinion information 'li open singing meeting cheer' into the public opinion information set a.
S2, establishing a first tree graph corresponding to the first keyword according to the preset keyword corresponding to the first keyword, and taking the preset keyword as a root node of the first tree graph.
According to the scheme, a first tree graph corresponding to the preset keywords is established, and the root nodes of the first tree graph are the preset keywords.
Illustratively, referring to fig. 2, the root node of the first tree is "lie three + concert".
In some embodiments, S2 (the establishing a first tree corresponding to the keyword according to the keyword, with the first keyword as a root node of the first tree) includes S21-S22:
s21, establishing a first tree diagram corresponding to the first information set.
Referring to fig. 2, the present solution establishes a first tree corresponding to a first information set. It will be appreciated that the dendrogram will have corresponding nodes, and that the dendrogram for this scheme has root nodes, child nodes, and grandchild nodes.
S22, extracting all preset keywords corresponding to the first information set, establishing 1 root node in the first tree diagram, and filling the preset keywords to the root node.
Illustratively, all preset keywords 'Lisan + concerts' corresponding to the first information set are extracted, 1 root node is established in the first tree diagram, and the preset keywords 'Lisan + concerts' are filled into the root nodes.
S3, obtaining all first information types of first public sentiment information in a first information set, establishing a plurality of first child nodes according to the first information types, wherein each child node corresponds to one first information type, and connecting the first child nodes with the root node.
According to the scheme, the corresponding first sub-nodes are established according to the information types, all first information types of first public opinion information in the first information set are obtained firstly, and a plurality of first sub-nodes are established according to the first information types.
In some embodiments, S3 (obtaining all first information categories of first public opinion information in the first information set, establishing a plurality of first sub-nodes according to the first information categories, where each sub-node corresponds to a first information category, and connecting the first sub-nodes with the root node), includes:
the first information type of the first public opinion information is any one of character type, image type or audio type and video type;
and establishing first child nodes corresponding to all first information types of the first public opinion information, and respectively connecting all the first child nodes with the root node.
For example, all the first information categories of the first public opinion information in the first information set include a text category, an image category or an audio category, and a video category, and there are 4 first sub-nodes corresponding to the first information set.
After the first child node is established, the scheme connects the first child node with the root node to form a tree diagram.
The scheme can classify the first public opinion information which is accessed in according to the information types through the embodiment.
And S4, generating a corresponding first grandchild node and a corresponding first data storage unit according to the first information content of each first public opinion information, connecting the first grandchild node with the corresponding first child node according to the first information type of each first public opinion information, storing the first public opinion information in the corresponding first data storage unit, and forming a first data storage space according to all the first data storage units.
In order to store the first public opinion information, the scheme generates a corresponding first grandchild node and a first data storage unit according to the first information content of each first public opinion information, and then stores corresponding data by using the first data storage unit.
According to the scheme, the first information type of each first public opinion information is connected with the corresponding first child node through the first grandchild node, and then the first public opinion information is stored in the corresponding first data storage unit.
In addition, according to the scheme, a first data storage space is formed according to all the first data storage units, the first data storage units are integrated, and each kind of similar first public opinion information can be stored in the corresponding first data storage space.
In some embodiments, S4 (the generating a corresponding first grandchild node, a first data storage unit according to the first information content of each first public opinion information, connecting the first grandchild node with a corresponding first child node according to the first information kind of each first public opinion information, storing the first public opinion information to the corresponding first data storage unit, forming a first data storage space according to all the first data storage units), includes S41-S44:
and S41, acquiring first information content of each piece of first public opinion information, wherein the first information content is any one of character content, image content, audio content and video content.
It can be understood that, according to the scheme, the first public opinion information is analyzed, the first information content accessed to the first public opinion information is obtained, and the content type of the first information content is obtained. For example, if the first information content is text information, the corresponding first information content is text content.
And S42, establishing a first grandchild node and a first data storage unit corresponding to the first information content respectively, and associating the first grandchild node with the first data storage unit through a data calling path, so that when the corresponding first grandchild node is triggered, the first information content in the first data storage unit is called based on the data calling path.
According to the scheme, a first grandchild node and a first data storage unit corresponding to first information content are established, a data calling path is established at the same time, the first grandchild node is associated with the first data storage unit, and a user can call storage content in the first data storage unit through the data calling path.
It can be understood that, according to the present solution, when the corresponding first grandchild node is triggered, the first information content in the first data storage unit may be called by using the data calling path.
And S43, generating corresponding first data identifications according to the first information types of the first public opinion information, and storing the first data identifications in corresponding first data storage units.
The scheme also can utilize the first information type of each first public opinion information to generate a corresponding first data identification, and the first data identification is utilized to label each corresponding first public opinion information. Meanwhile, the scheme stores the first data identifier in the corresponding first data storage unit.
According to the scheme, different ways of generating the first data identifier are adopted according to different first information types of the first public opinion information, which is specifically referred to as the following.
Aiming at the fact that the first information content is text content or image content:
in some embodiments, S43 (the generating of the corresponding first data identifier according to the first information category of each first public opinion information, storing the first data identifier in the corresponding first data storage unit) includes a 431-a 432:
and A431, if the first information content of the first public opinion information is judged to be the text content or the image content, acquiring a character string corresponding to the first public opinion information in the text type or the image type, and performing hash operation on the character string to obtain a first hash value.
It can be understood that, when the first information content is a text content or an image content, the scheme may analyze the text content or the image content to obtain a character string corresponding to the first public opinion information in the text type or the image type, and then perform a hash operation on the character string to obtain a first hash value.
It should be noted that, if the text content or the image content is different, the character strings obtained by analysis are different, and the first hash values obtained by performing hash operation on the character strings are also different, so that each different text content or image content has a different first hash value, and during subsequent deduplication, the first hash values can be used for comparison deduplication.
The hash operation on the character string to obtain the first hash value is prior art, and is not described herein again.
And A432, using the first hash value as a first data identifier of first public opinion information of text content or image content.
According to the scheme, after the first hash value is obtained through calculation, the first hash value is used as the first data identification of the first public opinion information.
Aiming at the first information content being audio content or video content:
in other embodiments, S43 (the generating a corresponding first data identifier according to the first information category of each first public opinion information, storing the first data identifier in a corresponding first data storage unit) includes B431-B433:
b431, if the first information type of the first public opinion information is determined to be audio content or video content, obtaining a first termination time value and a first information data value of the audio content or the video content.
According to the scheme, when the first information type is audio content or video content, a first termination time value and a first information data quantity value of the audio content or the video content are obtained.
Illustratively, the first information type is video content, the length of the video content is 1 minute 10S, and the size is 1500KB, and the corresponding first end time value is 1 minute 10S, and the first information data amount value is 1500 KB.
And B432, offsetting the first termination time value according to a preset time period to obtain a termination time period, and offsetting the first information data quantity value according to a preset data quantity value to obtain an information data interval value.
In order to reduce the influence of errors, the scheme offsets the first termination time value according to a preset time period to obtain a termination time period, and offsets the first information data quantity value according to a preset data quantity value to obtain an information data interval value.
Illustratively, the first end time value is 1 minute 10S, the first information data amount value is 1500KB, the corresponding end time period is 1 minute 09S to 1 minute 11S, and the information data interval value is 1490KB to 1500 KB.
And B433, using the ending time period and the information data interval value as a first data identifier of the first public opinion information of the audio content or the video content.
When the termination time period and the information data interval value are obtained, the scheme obtains the first data identifier by using the termination time period and the information data interval value.
It will be appreciated that if the values of the expiration time period and the information data interval are different if they are not the same audio or video, then the corresponding values of the information data interval will be different if the audio or video content is different even if the expiration time period is the same. According to the scheme, the unique first data identification corresponding to the same data is obtained by combining the termination time period and the information data interval value.
Although a small amount of data may be deleted by mistake by using the termination time period and the information data interval value, the probability in this case is extremely low and can be ignored after long-term data operation discovery.
And S44, counting all the first data storage units to generate corresponding first data storage spaces.
According to the scheme, a plurality of first data storage spaces are provided, and each first data storage space corresponds to a plurality of first data storage units.
And S5, when judging that the second public opinion information corresponding to the keyword in the tree-shaped graph is captured, updating the first tree-shaped graph and the first data storage space according to the second information type and the second information content of the second public opinion information to obtain a second tree-shaped graph and a second data storage space.
The scheme can capture second public opinion information in real time, analyze the second public opinion information to obtain a second information type and second information content of the second public opinion information, and update the first tree diagram and the first data storage space to obtain a second tree diagram and a second data storage space.
It can be understood that the scheme can capture the public sentiment data in real time, then update the dendrogram in real time, and realize the classified storage of the public sentiment data based on the dendrogram.
In some embodiments, S5 (the updating process of the first dendrogram and the first data storage space according to the second information type and the second information content of the second public opinion information to obtain the second dendrogram and the second data storage space when determining that the second public opinion information corresponding to the keyword in the dendrogram is captured) includes S51-S54:
and S51, if the second public opinion information is judged to be text content or image content, extracting a character string corresponding to the second public opinion information, and performing hash operation on the character string to obtain a second hash value.
In the scheme, in order to judge whether the accessed second public opinion information is repeated with the stored public opinion information, the second public opinion information of the text content or the image content is analyzed to obtain a character string corresponding to the second public opinion information, and then the character string is subjected to hash operation to obtain a second hash value.
And S52, traversing a first hash value of a first data identifier in a first data storage unit corresponding to the text content or the image content, and if the first hash value is judged to be the same as the second hash value, not storing the second public opinion information.
It can be understood that, after the second hash value is obtained, the second hash value is compared with the first hash value, and if the first hash value is the same as the second hash value, it indicates that the second public opinion information to be stored currently is repeated with the public opinion information already stored, the second public opinion information is not stored in the present scheme.
And S53, if the first hash value is different from the second hash value, establishing a second grandchild node and a second data storage unit corresponding to second public opinion information, and storing the second public opinion information into the second data storage unit.
It can be understood that, if the first hash value is different from the second hash value, it indicates that there is no public opinion information in the current storage space that is duplicated with the second public opinion information, and the second public opinion information needs to be stored. According to the scheme, a second grandchild node and a second data storage unit corresponding to the second public opinion information are established, the dendrogram is updated, and then the second public opinion information is stored into the second data storage unit.
And S54, updating the first dendrogram based on the second grandchild node to obtain a second dendrogram, and updating the first data storage space based on the second data storage unit to obtain a second data storage space.
It can be understood that, the present solution will add the second grandchild node to the first tree map, and update the first tree map into the second tree map; meanwhile, the second data storage unit is added into the first data storage space, and the second data storage space is obtained through updating.
And all second public opinion information in a second data storage unit in the second data storage space is called and displayed under the control of calling instructions of workers. And receiving public opinion repeated data input by a worker to all second public opinion information in the second data storage unit, wherein the public opinion repeated data comprises repeated public opinion repeated information corresponding to the second public opinion information and the repeated public opinion repeated amount of each type of the public opinion repeated information.
And acquiring a second information data quantity value and a second termination time value of all second public opinion information corresponding to each public opinion repeated information. And under the condition of extracting the repeated public sentiment information, the maximum second information data value, the minimum second information data value, the maximum second termination time value and the minimum second termination time value in the plurality of second public sentiment information.
If the second information data magnitude value larger than the maximum value of the information data interval value exists, the maximum second information data magnitude value is differed from the maximum value of the information data interval value to obtain an increased change amplitude value; and if the second information data magnitude value smaller than the minimum value of the information data interval value exists, the minimum second information data magnitude value is differed from the minimum value of the information data interval value to obtain a reduced variation amplitude value, and the increased variation amplitude value and the reduced variation amplitude value are added to obtain a data adjustment amplitude interval value corresponding to each public sentiment repeated information.
Obtaining the maximum data adjustment range interval value in a plurality of public opinion repeated information as a target data adjustment range interval value, determining an information data interval value corresponding to the target data adjustment range interval value, determining a data adjustment proportion coefficient according to the ratio of the target data adjustment range interval value and the information data interval value, adjusting the information data interval value in a first data identifier of all audio content or video content according to the data adjustment proportion coefficient, calculating the data adjustment proportion coefficient and the adjusted information data interval value by the following formula,
wherein, the first and the second end of the pipe are connected with each other,
the scaling factor is adjusted for the data,
is the largest value of the second information data quantity,
is the maximum value of the information data interval value,
is the largest value of the second information data quantity,
is the minimum value of the information data interval values,
the scaling factor is adjusted for the data,
adjusting the proportionality coefficient for the maximum data in all public opinion repeated information,
adjusting the information data interval value corresponding to the maximum data adjusting proportion coefficient in all public opinion repeated information,
for the maximum value of the adjusted information data interval value,
the coefficient is increased for the preset data,
for the minimum value of the adjusted information data interval value,
the coefficients are reduced for the preset data.
Through the technical scheme, after the same second public opinion information is stored, the method can calculate according to the difference relation between the data quantity values of the same second public opinion information to obtain the corresponding data adjustment proportion coefficient, and synchronously adjust the information data interval values in different first data identifications according to the corresponding data adjustment proportion coefficient, so that the method can enlarge the compared data range in the comparison process of the public opinion information of the corresponding dendrogram, and can effectively remove the same audio content and video content.
If the second termination time value larger than the maximum value of the termination time period exists, the maximum second termination time value is differed from the maximum value of the termination time period to obtain a time increase variation amplitude value; and if the second termination time value smaller than the minimum value of the termination time period exists, subtracting the minimum second termination time value from the minimum value of the termination time period to obtain the amplitude reduction value. And adding the increasing change amplitude value and the decreasing change amplitude value to obtain a time adjustment amplitude interval value corresponding to each public sentiment repeated message.
Acquiring the maximum time adjustment amplitude interval value in a plurality of public opinion repeated information as a target time adjustment amplitude interval value, determining a termination time period corresponding to the target time adjustment amplitude interval value, determining a time period adjustment proportion coefficient according to the target time adjustment amplitude interval value and the ratio of the termination time period, adjusting the termination time period in the first data identification of all audio content or video content according to the time period adjustment proportion coefficient, calculating the time period adjustment proportion coefficient and the adjusted termination time period by the following formulas,
wherein the content of the first and second substances,
the scaling factor is adjusted for the time period,
is the largest value of the second termination time instant,
for the maximum value of the termination period of time,
the second end-time value being the minimum value,
for the minimum value of the termination period of time,
adjusting the ratio for the time periodThe coefficients of which are such that,
adjusting the proportionality coefficient for the maximum time section in all public opinion repeated information,
adjusting the termination time period corresponding to the scaling factor for the maximum time period in all public opinion repeated information,
for the maximum value of the adjusted termination period,
the coefficient is increased for a preset time,
to be the minimum value of the adjusted termination period,
the coefficient is reduced for a preset time.
Through the technical scheme, after the same second public opinion information is stored, the method can calculate according to the difference relation between the times of the same second public opinion information to obtain the corresponding time adjustment proportion coefficient, and synchronously adjust the termination time period values in different first data identifications according to the corresponding time adjustment proportion coefficient, so that the comparison termination time range can be expanded in the comparison process of the public opinion information of the corresponding dendrograms, and the same audio content and video content can be effectively removed. And then realize according to user's feedback result, carry out the training that lasts to the screening mode of second public opinion information, reach the effect of avoiding carrying out the repeated storage to the same public opinion information.
Referring to fig. 3, which is a schematic structural diagram of a public opinion data processing device according to an embodiment of the present invention, the public opinion data processing device includes:
the system comprises a clustering module, a searching module and a searching module, wherein the clustering module is used for capturing public sentiment data at a plurality of target positions, the public sentiment data at least comprises first public sentiment information, all the first public sentiment information is clustered according to first keywords in the first public sentiment information to obtain a plurality of first information sets, and each first information set is provided with a corresponding keyword;
the root node establishing module is used for establishing a first tree graph corresponding to the keyword according to the keyword, and taking the first keyword as a root node of the first tree graph;
the child node establishing module is used for acquiring all first information types of first public opinion information in a first information set, establishing a plurality of first child nodes according to the first information types, wherein each child node corresponds to one first information type, and connecting the first child nodes with the root node;
the grandchild node establishing module is used for generating a corresponding first grandchild node and a first data storage unit according to the first information content of each piece of first public opinion information, connecting the first grandchild node with a corresponding first child node according to the first information type of each piece of first public opinion information, storing the first public opinion information to the corresponding first data storage unit, and forming a first data storage space according to all the first data storage units;
and the updating module is used for updating the first tree-shaped graph and the first data storage space according to the second information type and the second information content of the second public opinion information when judging that the second public opinion information corresponding to the key words in the tree-shaped graph is captured, so as to obtain a second tree-shaped graph and a second data storage space.
The apparatus in the embodiment shown in fig. 3 can be correspondingly used to perform the steps in the method embodiment shown in fig. 1, and the implementation principle and technical effect are similar, which are not described herein again.
The present invention also provides a storage medium, in which a computer program is stored, and the computer program is used for realizing the methods provided by the various embodiments described above when being executed by a processor.
The storage medium may be a computer storage medium or a communication medium. Communication media includes any medium that facilitates transfer of a computer program from one place to another. Computer storage media may be any available media that can be accessed by a general purpose or special purpose computer. For example, a storage medium is coupled to the processor such that the processor can read information from, and write information to, the storage medium. Of course, the storage medium may also be integral to the processor. The processor and the storage medium may reside in an Application Specific Integrated Circuits (ASIC). Additionally, the ASIC may reside in user equipment. Of course, the processor and the storage medium may reside as discrete components in a communication device. The storage medium may be read-only memory (ROM), random-access memory (RAM), CD-ROMs, magnetic tapes, floppy disks, optical data storage devices, and the like.
The present invention also provides a program product comprising execution instructions stored in a storage medium. The at least one processor of the device may read the execution instructions from the storage medium, and the execution of the execution instructions by the at least one processor causes the device to implement the methods provided by the various embodiments described above.
In the above embodiments of the terminal or the server, it should be understood that the Processor may be a Central Processing Unit (CPU), other general-purpose processors, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the present invention may be embodied directly in a hardware processor, or in a combination of the hardware and software modules within the processor.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. A public opinion data processing method is characterized by comprising the following steps:
the method comprises the steps of capturing public opinion data at a plurality of target positions, wherein the public opinion data at least comprise first public opinion information, clustering all the first public opinion information according to first keywords in the first public opinion information to obtain a plurality of first information sets, and each first information set is provided with corresponding preset keywords;
establishing a first dendrogram corresponding to a preset keyword according to the first keyword, wherein the preset keyword is used as a root node of the first dendrogram;
acquiring all first information types of first public sentiment information in a first information set, establishing a plurality of first child nodes according to the first information types, wherein each child node corresponds to one first information type, and connecting the first child nodes with the root node;
generating a corresponding first grandchild node and a corresponding first data storage unit according to first information content of each first public opinion information, connecting the first grandchild node with the corresponding first child node according to a first information type of each first public opinion information, storing the first public opinion information to the corresponding first data storage unit, and forming a first data storage space according to all the first data storage units;
and when judging that second public opinion information corresponding to the keywords in the dendrogram is captured, updating the first dendrogram and the first data storage space according to the second information type and the second information content of the second public opinion information to obtain a second dendrogram and a second data storage space.
2. The public opinion data processing method according to claim 1, characterized in that,
the public opinion data at a plurality of target positions are captured, the public opinion data at least comprises first public opinion information, all the first public opinion information is clustered according to first keywords in the first public opinion information to obtain a plurality of first information sets, and each first information set has corresponding keywords, and the method comprises the following steps:
the method comprises the steps of obtaining a pre-configured public opinion key phrase, and generating a corresponding public opinion information set according to the public opinion key phrase, wherein the public opinion key phrase comprises at least one preset keyword;
comparing a first keyword in the first public opinion information with preset keywords in a public opinion keyword group, classifying the first public opinion information corresponding to any one preset keyword into a corresponding public opinion information set to obtain a plurality of first information sets, wherein the keyword corresponding to the first information set is the preset keyword.
3. The public opinion data processing method according to claim 2, characterized in that,
the establishing of the first tree graph corresponding to the keyword according to the keyword, and the taking of the first keyword as a root node of the first tree graph comprise:
establishing a first tree diagram corresponding to the first information set;
extracting all preset keywords corresponding to the first information set, establishing 1 root node in the first tree diagram, and filling the preset keywords to the root node.
4. The public opinion data processing method according to claim 3, characterized in that,
the method for acquiring all first information types of first public opinion information in a first information set includes the steps of establishing a plurality of first child nodes according to the first information types, wherein each child node corresponds to one first information type, and connecting the first child nodes with a root node, and includes:
the first information type of the first public opinion information is any one of character type, image type or audio type and video type;
and establishing first child nodes corresponding to all first information types of the first public opinion information, and respectively connecting all the first child nodes with the root node.
5. The public opinion data processing method according to claim 3, characterized in that,
the generating of a corresponding first grandchild node and a first data storage unit according to a first information content of each first public opinion information, connecting the first grandchild node with a corresponding first child node according to a first information type of each first public opinion information, storing the first public opinion information in the corresponding first data storage unit, and forming a first data storage space according to all the first data storage units includes:
acquiring first information content of each piece of first public opinion information, wherein the first information content is any one of character content, image content, audio content and video content;
respectively establishing a first grandchild node and a first data storage unit corresponding to first information content, and associating the first grandchild node with the first data storage unit through a data calling path, so that the first information content in the first data storage unit is called based on the data calling path when the corresponding first grandchild node is triggered;
generating a corresponding first data identifier according to a first information type of each first public opinion information, and storing the first data identifier in a corresponding first data storage unit;
and counting all the first data storage units to generate corresponding first data storage spaces.
6. The public opinion data processing method according to claim 5, characterized in that,
the generating of a corresponding first data identifier according to a first information category of each first public opinion information, storing the first data identifier in a corresponding first data storage unit, includes:
if the first information content of the first public opinion information is judged to be text content or image content, acquiring a character string corresponding to the first public opinion information in the text type or the image type, and performing hash operation on the character string to obtain a first hash value;
and taking the first hash value as a first data identifier of first public opinion information of text content or image content.
7. The public opinion data processing method according to claim 5, characterized in that,
the method for generating corresponding first data identification according to a first information type of each first public opinion information and storing the first data identification in a corresponding first data storage unit comprises the following steps:
if the first information type of the first public opinion information is judged to be audio content or video content, acquiring a first termination time value and a first information data quantity value of the audio content or the video content;
shifting the first termination time value according to a preset time period to obtain a termination time period, and shifting the first information data quantity value according to a preset data quantity value to obtain an information data interval value;
and taking the termination time period and the information data interval value as a first data identifier of first public sentiment information of audio content or video content.
8. The public opinion data processing method according to claim 6, characterized in that,
when the second public opinion information corresponding to the keyword in the dendrogram is captured, the first dendrogram and the first data storage space are updated according to the second information type and the second information content of the second public opinion information to obtain a second dendrogram and a second data storage space, and the method comprises the following steps:
if the second public opinion information is judged to be text content or image content, extracting a character string corresponding to the second public opinion information, and performing hash operation on the character string to obtain a second hash value;
traversing a first hash value of a first data identifier in a first data storage unit corresponding to the text content or the image content, and if the first hash value is judged to be the same as the second hash value, not storing the second public opinion information;
if the first hash value is different from the second hash value, establishing a second grandchild node and a second data storage unit corresponding to second public opinion information, and storing the second public opinion information into the second data storage unit;
and updating the first dendrogram based on the second grandchild node to obtain a second dendrogram, and updating the first data storage space based on the second data storage unit to obtain a second data storage space.
9. The public opinion data processing method according to claim 7, characterized in that,
when the second public opinion information corresponding to the keyword in the dendrogram is captured, the first dendrogram and the first data storage space are updated according to the second information type and the second information content of the second public opinion information to obtain a second dendrogram and a second data storage space, and the method comprises the following steps:
if the second public opinion information is judged to be audio content or video content, extracting a second termination time value and a second information data quantity value in the second public opinion information;
traversing a termination time period and an information data interval value of a first data identifier in a first data storage unit corresponding to the audio content or the video content, and if the second termination time value is judged to be in the termination time period and a second information data value is judged to be in the information data interval value, not storing the second public opinion information;
if the second termination time value is judged not to be within the termination time period or the second information data quantity value is judged not to be within the information data interval value, establishing a second grandchild node and a second data storage unit corresponding to the second public opinion information, and storing the second public opinion information into the second data storage unit;
and updating the first dendrogram based on the second grandchild node to obtain a second dendrogram, and updating the first data storage space based on the second data storage unit to obtain a second data storage space.
10. The utility model provides a public opinion data processing apparatus which characterized in that includes:
the system comprises a clustering module, a searching module and a searching module, wherein the clustering module is used for capturing public sentiment data at a plurality of target positions, the public sentiment data at least comprises first public sentiment information, all the first public sentiment information is clustered according to first keywords in the first public sentiment information to obtain a plurality of first information sets, and each first information set is provided with a corresponding keyword;
the root node establishing module is used for establishing a first tree graph corresponding to the keyword according to the keyword, and taking the first keyword as a root node of the first tree graph;
the child node establishing module is used for acquiring all first information types of first public sentiment information in a first information set, establishing a plurality of first child nodes according to the first information types, wherein each child node corresponds to one first information type, and connecting the first child nodes with the root node;
the grandchild node establishing module is used for generating a corresponding first grandchild node and a first data storage unit according to the first information content of each piece of first public opinion information, connecting the first grandchild node with a corresponding first child node according to the first information type of each piece of first public opinion information, storing the first public opinion information to the corresponding first data storage unit, and forming a first data storage space according to all the first data storage units;
and the updating module is used for updating the first tree-shaped graph and the first data storage space according to the second information type and the second information content of the second public opinion information when judging that the second public opinion information corresponding to the key words in the tree-shaped graph is captured, so as to obtain a second tree-shaped graph and a second data storage space.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210850838.4A CN114925286B (en) | 2022-07-20 | 2022-07-20 | Public opinion data processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210850838.4A CN114925286B (en) | 2022-07-20 | 2022-07-20 | Public opinion data processing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114925286A true CN114925286A (en) | 2022-08-19 |
| CN114925286B CN114925286B (en) | 2022-10-14 |
Family
ID=82815955
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210850838.4A Active CN114925286B (en) | 2022-07-20 | 2022-07-20 | Public opinion data processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114925286B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116737992A (en) * | 2023-08-15 | 2023-09-12 | 明麦(南京)科技有限公司 | Public opinion monitoring data processing method and processing system |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105045919A (en) * | 2015-08-24 | 2015-11-11 | 北京云知声信息技术有限公司 | Information output method and apparatus |
| CN108154384A (en) * | 2011-07-13 | 2018-06-12 | 阿里巴巴集团控股有限公司 | Advertisement placement method, advertisement releasing server and advertisement delivery system |
-
2022
- 2022-07-20 CN CN202210850838.4A patent/CN114925286B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108154384A (en) * | 2011-07-13 | 2018-06-12 | 阿里巴巴集团控股有限公司 | Advertisement placement method, advertisement releasing server and advertisement delivery system |
| CN105045919A (en) * | 2015-08-24 | 2015-11-11 | 北京云知声信息技术有限公司 | Information output method and apparatus |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116737992A (en) * | 2023-08-15 | 2023-09-12 | 明麦(南京)科技有限公司 | Public opinion monitoring data processing method and processing system |
| CN116737992B (en) * | 2023-08-15 | 2023-10-13 | 明麦(南京)科技有限公司 | Public opinion monitoring data processing method and processing system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114925286B (en) | 2022-10-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109033387B (en) | Internet of things searching system and method fusing multi-source data and storage medium | |
| CN106156127B (en) | Method and device for selecting data content to push to terminal | |
| US20230334089A1 (en) | Entity recognition from an image | |
| WO2020207074A1 (en) | Information pushing method and device | |
| CN111460153B (en) | Hot topic extraction method, device, terminal equipment and storage medium | |
| US20130159311A1 (en) | System and methods for generation of a concept based database | |
| CN111353106B (en) | Recommendation method and device, electronic equipment and storage medium | |
| CN114925286B (en) | Public opinion data processing method and device | |
| CN108536680B (en) | Method and device for acquiring house property information | |
| WO2020135756A1 (en) | Video segment extraction method, apparatus and device, and computer-readable storage medium | |
| CN115600128A (en) | Semi-supervised encrypted traffic classification method and device and storage medium | |
| CN114625918A (en) | Video recommendation method, device, equipment, storage medium and program product | |
| CN113268630B (en) | Audio retrieval method, device and medium | |
| CN111444364B (en) | Image detection method and device | |
| CN111752922A (en) | Method and device for establishing knowledge database and realizing knowledge query | |
| CN114510564A (en) | Video knowledge graph generation method and device | |
| CN112115281A (en) | Data retrieval method, device and storage medium | |
| CN108280772B (en) | Story context generation method based on event association in social network | |
| CN115858815A (en) | Method for determining mapping information, advertisement recommendation method, device, equipment and medium | |
| CN113157742A (en) | Data lake management method and system for intelligent bus | |
| CN117688136B (en) | Combined retrieval optimization method and system based on artificial intelligence | |
| CN111246124A (en) | Multimedia digital fusion method and device | |
| CN117828382B (en) | Network interface clustering method and device based on URL | |
| CN112506959B (en) | Data scheduling method and device for intelligent ship database retrieval and retrieval system | |
| CN117235289B (en) | Processing method of field map model facing to scenerized decision requirement |
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 | ||
| GR01 | Patent grant |