CN112527861A - Personnel portrait analysis method based on big data real-time analysis - Google Patents
Personnel portrait analysis method based on big data real-time analysis Download PDFInfo
- Publication number
- CN112527861A CN112527861A CN202011424474.0A CN202011424474A CN112527861A CN 112527861 A CN112527861 A CN 112527861A CN 202011424474 A CN202011424474 A CN 202011424474A CN 112527861 A CN112527861 A CN 112527861A
- Authority
- CN
- China
- Prior art keywords
- personnel
- data
- portrait
- analyzed
- label
- 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.)
- Withdrawn
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
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2455—Query execution
- G06F16/24568—Data stream processing; Continuous queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/27—Replication, distribution or synchronisation of data between databases or within a distributed database system; Distributed database system architectures therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/283—Multi-dimensional databases or data warehouses, e.g. MOLAP or ROLAP
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/285—Clustering or classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Abstract
The invention relates to the technical field of big data analysis, and provides a personnel portrait analysis method based on big data real-time analysis, which comprises the following steps: step 100, obtaining a large amount of samples of personnel static data and personnel dynamic data, classifying the data according to four label dimensions of natural attributes, behavior attributes, habits and hobbies and personnel relations, and establishing a personnel portrait label model; step 200, acquiring personnel static data and personnel dynamic data of personnel to be analyzed, calculating personnel portrait labels of all the personnel to be analyzed, and establishing personnel files in a big data search engine; step 300, calculating a risk value of each person to be analyzed; and step 400, searching the personnel portrait label and/or the risk value of the target personnel through the keyword to obtain the whole personnel portrait of the target personnel. The personnel static data and the personnel dynamic data can be accurately analyzed and evaluated to obtain personnel portrait labels, and the real-time performance and the comprehensiveness of personnel analysis can be improved.
Description
Technical Field
The invention relates to the technical field of big data analysis, in particular to a personnel portrait analysis method based on big data real-time analysis.
Background
The floating population of present community continues to increase, and community discrepancy personnel mobility is big, and personnel's identity is difficult to master, and the current scheme is on information acquisition's basis to establish personnel's information archives on the market, provides personnel's information inquiry function.
In the field of the existing community security, for personnel management, the existing scheme is generally to comprehensively establish personnel archives including personnel basic information, personnel community activity data and the like through acquiring static data and dynamic data of personnel, so that subsequent inquiry is facilitated. The method stays in simple recording and query of data, the value of the data is not fully mined, and the understanding of people stays on the surface, so that the multidimensional attribute of people cannot be deeply understood.
Disclosure of Invention
The invention mainly solves the problems that the description and evaluation of people by the conventional community security management technology stays in static data and dynamic real-time analysis cannot be realized, and provides a personnel portrait analysis method based on big data real-time analysis, so that personnel static data and personnel dynamic data are accurately analyzed and evaluated to obtain personnel portrait labels, and the real-time performance and comprehensiveness of personnel analysis can be improved.
The invention provides a personnel portrait analysis method based on big data real-time analysis, which comprises the following processes:
step 100, obtaining a large amount of samples of personnel static data and personnel dynamic data, classifying the data according to four label dimensions of natural attributes, behavior attributes, habits and hobbies and personnel relations, and establishing a personnel portrait label model;
step 200, acquiring static personnel data and dynamic personnel data of personnel to be analyzed, calculating personnel portrait labels of all the personnel to be analyzed, and establishing a personnel file in a big data search engine, wherein the steps specifically include step 201 to step 205:
step 201, acquiring static personnel data and dynamic personnel data of a person to be analyzed, and determining a unique identifier of the person to be analyzed according to the static personnel data;
202, classifying and placing personnel dynamic data of a to-be-analyzed person into a data pipeline kafka in real time according to four label dimensions of natural attributes, behavior attributes, habits and hobbies and personnel relations by utilizing a streaming real-time analysis processing technology, extracting a unique identifier of the to-be-analyzed person, adding the unique identifier into an accumulator, and broadcasting the unique identifier into the data pipeline kafka;
step 203, taking out personnel dynamic data corresponding to the unique identification of the personnel to be analyzed in batch from the data pipeline kafka, matching the personnel dynamic data with personnel portrait label models in the database, and obtaining the personnel portrait labels by the personnel to be analyzed when the personnel dynamic data meets one or more personnel portrait labels in the personnel portrait label models;
step 204, combining and storing the personnel static data, the personnel dynamic data and the personnel portrait labels of the personnel to be analyzed in a big data search engine;
step 205, according to the method from step 201 to step 204, calculating the personnel portrait labels of all the personnel to be analyzed in sequence, and establishing a personnel file in a big data search engine.
Further, the people portrayal labels of natural attributes include, but are not limited to: male, female, nationality;
person representation tags for behavioral attributes include, but are not limited to: night-out in daytime, walking people, frequent trip, driving people, normal living, normal trip and home;
people portrayal labels of habitual interest include, but are not limited to: door card door opening families, APP door opening families, remote door opening families, AI door opening families and other door opening families;
people portrayal tags of social relationships include, but are not limited to: live with family, group, normal social, solitary, general family, dislike of social, live with tenant, family of dingke.
Further, after step 200, the method further includes: step 300, calculating the risk value of each person to be analyzed by using the following formula:
R＝score1*weight1+score2*weight2+.....+scoren*weightn
wherein, R represents a risk value, score represents a label score, weight represents a label weight, and n represents a label number.
Further, after step 300, the method further includes: and step 400, searching the personnel portrait label and/or the risk value of the target personnel through the keyword to obtain the whole personnel portrait of the target personnel.
Compared with the prior art, the personnel portrait analysis method based on big data real-time analysis provided by the invention has the following advantages:
1. massive personnel static data and personnel dynamic data collected by the community are used as samples, and a personnel portrait label model is established according to dimensions such as natural attributes, behavior attributes, habits and hobbies, personnel relations and the like, so that the dimension and the depth of personnel analysis are improved, and all-round personnel portrait evaluation can be performed on community personnel;
2. because the personnel portrait label is established by analyzing the personnel dynamic data, the personnel dynamic data are continuously generated along with time, and the personnel portrait label is continuously updated along with time, so that the real-time performance and the effectiveness of personnel analysis are greatly improved;
3. personnel portrait labels obtained based on multi-dimensional data analysis use a label weighting formula to calculate personnel risk values, quantitative indexes of personnel evaluation are increased, potential risks can be quickly judged through the personnel risk values, and security risk evaluation efficiency is improved.
Drawings
FIG. 1 is a flow chart of an implementation of a human portrait analysis method based on big data real-time analysis according to the present invention;
FIG. 2 is a flow chart of an implementation of a process for tagging a portrait of a computer according to the present invention.
Detailed Description
In order to make the technical problems solved, technical solutions adopted and technical effects achieved by the present invention clearer, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some but not all of the relevant aspects of the present invention are shown in the drawings.
As shown in fig. 1, a method for analyzing a person portrait based on real-time analysis of big data according to an embodiment of the present invention includes:
step 100, obtaining a large amount of samples of personnel static data and personnel dynamic data, classifying the data according to four label dimensions of natural attributes, behavior attributes, habits and hobbies and personnel relations, establishing a personnel portrait label model, and storing the personnel portrait label model in a database.
The personnel static data is basic information of personnel which does not change along with time, and comprises but is not limited to name, age, gender, address and the like; the dynamic personnel data are newly added data which are continuously changed along with time, and include but not limited to entrance guard passing records, face snapshot records, vehicle passing records, mobile phone electricity enclosure records and the like.
Personnel portrait label, personnel's information labeller promptly, the information overall situation of a personnel is abstracted out perfectly, and the core work is for personnel to beat the label, and one of the important purpose of beating the label is in order to let the people understand and make things convenient for computer processing, also can do data mining work: calculating by using association rules, analyzing by using a clustering algorithm and the like. Big data processing, the operation of the computer can not be left, and the label provides a convenient mode, so that the computer can process information related to people in a programmed mode, and even people can be understood through an algorithm and a model. After the computer has the capability, the precision and the efficiency can be further improved in the application fields of search engines and the like.
According to the embodiment, the personnel portrait labels are classified and established according to four dimensions of natural attributes, behavior attributes, habit and hobbies and social relations.
People portrayal tags of natural attributes include, but are not limited to: male, female, nationality, etc.
Person representation tags for behavioral attributes include, but are not limited to: night-out in the daytime, the pedestrian, frequent trips, the car driver, normal living, normal trips, home residence and the like.
People portrayal labels of habitual interest include, but are not limited to: door card door clan, APP door clan, remote door clan, AI door clan, other door clans, etc.
People portrayal tags of social relationships include, but are not limited to: living with family, group, normal social, solitary, general family, dislike of social, living with tenant, family of dingke, etc.
Step 200, acquiring static personnel data and dynamic personnel data of the personnel to be analyzed, calculating personnel portrait labels of all the personnel to be analyzed, and establishing personnel files in a big data search engine. As shown in fig. 2, step 200 specifically includes the following steps 201 to 206:
step 201, acquiring static personnel data and dynamic personnel data of a person to be analyzed, and determining a unique identifier of the person to be analyzed according to the static personnel data.
Wherein, the unique identification includes but is not limited to people, house, car, cell phone information. The unique identification enables to confirm the identity of the person. The static personnel data are stored in the static database, the dynamic personnel data are stored in the dynamic database, and the dynamic personnel data contain personnel identity information, so that all the data of the corresponding personnel in the static database and the dynamic database can be found by using the unique identifier.
Step 202, utilizing a streaming real-time analysis processing technology, classifying and placing the personnel dynamic data of the personnel to be analyzed into the data pipeline kafka in real time according to four label dimensions of natural attributes, behavior attributes, habits, hobbies and personnel relations, extracting the unique identification of the personnel to be analyzed, adding the unique identification into an accumulator, and broadcasting the unique identification into the data pipeline kafka.
The streaming real-time analysis processing technology (Spark-streaming) is a streaming processing framework, is an extension of Spark API, and supports scalable, high-throughput, fault-tolerant real-time data streaming processing, where the real-time data may be from: kafka, Flume, Twitter, ZeroMQ, or TCP sockets, and may use complex operators of advanced functions to process streaming data. The processed data can be stored in a file system, a database and the like, and can be conveniently displayed in real time.
Kafka is an open source stream processing platform developed by the Apache software foundation, written by Scala and Java, is a high-throughput distributed publish-subscribe messaging system, and can process all action stream data of a consumer in a website. These data are typically addressed by handling logs and log aggregations due to throughput requirements. Dynamic data is loaded to the data pipeline kafka, and the data can be rapidly acquired when the data pipeline kafka is used.
Step 203, taking out the personnel dynamic data corresponding to the unique identification of the personnel to be analyzed in batch from the data pipeline kafka, matching the personnel dynamic data with the personnel portrait label model in the database, and obtaining the personnel portrait label by the personnel to be analyzed when the personnel dynamic data meets one or more personnel portrait labels in the personnel portrait label model.
This step analyzes and counts all person portrait labels obtained by the person to be analyzed.
And step 204, combining and storing the personnel static data, the personnel dynamic data and the personnel portrait labels of the personnel to be analyzed in a big data search engine.
Specifically, the personnel static data, the personnel dynamic data and the personnel portrait labels of the personnel to be analyzed are combined and written into a big data search engine elastic search in batches, so that the data can be conveniently retrieved and used in real time.
The Elasticsearch is a Lucene-based search server. It provides a distributed multi-user capable full-text search engine based on RESTful web interface. The Elasticsearch was developed in the Java language and published as open source under the Apache licensing terms, a popular enterprise level search engine. The Elasticisearch is used in cloud computing, can achieve real-time searching, and is stable, reliable, rapid, convenient to install and use. Official clients are available in Java,. NET (C #), PHP, Python, Apache Groovy, Ruby and many other languages.
Step 205, according to the method from step 201 to step 204, sequentially calculating the personnel portrait tags of all the personnel to be analyzed, and establishing a personnel file in the big data search engine elastic search.
The step is repeated in a circulating manner in steps 201 and 204, the personnel portrait labels of all the personnel to be analyzed are analyzed and calculated, and the personnel files established in the big data search engine elastic search comprise personnel static data, personnel dynamic data and personnel portrait labels.
Step 206, updating the personnel file in real time.
In this embodiment, since the dynamic personnel data are generated continuously over time, when new dynamic personnel data are acquired, the personnel to be analyzed corresponding to the dynamic personnel data are found in the elastic search through the unique identifier, whether the personnel portrait label of the new dynamic personnel data meeting the condition is the same as the personnel portrait label corresponding to the personnel to be analyzed in the established file is determined, and if the personnel portrait labels are not the same, the personnel portrait label of the personnel to be analyzed in the big data search engine is updated.
Step 300, calculating the risk value R of each person to be analyzed by using the following formula:
R＝score1*weight1+score2*weight2+.....+scoren*weightn
wherein, R represents a risk value, score represents a label score, weight represents a label weight, and n represents a label number.
In this step, a score and a weight are set for each person image tag obtained in step 200 based on the person image tag, and the score and the weight of each tag are set according to the risk and importance of the tag, for example, tags such as daytime and nighttime, key persons, etc., and the score and the weight are set higher, tags such as normal entrance and exit, normal social contact, etc., and the score and the weight are set lower, and the higher the calculated risk value R, the more dangerous the person is.
And step 400, searching the personnel portrait label and/or the risk value of the target personnel through the keyword to obtain the whole personnel portrait of the target personnel.
The method comprises the steps of screening and determining a target person to be finally searched in a fuzzy matching mode by utilizing person keyword information such as the name, the identity card number, the mobile phone number and the like of the target person, searching corresponding person dynamic data, person static data, a person portrait label and a risk value in a big data search engine ElasticSearch through a unique identifier of the target person, wherein the information is the person portrait of the person. After the search, the person image of the target person is displayed.
Taking Zhang III people in the community as an example, the establishment of the person portrait is explained by the following process:
firstly, acquiring static personnel data and dynamic personnel data related to Zhangsan from a database, wherein the static personnel data mainly comprise basic information registered by individuals and house, mobile phone and vehicle information related to Zhangsan, and the dynamic personnel data are data which are increased and changed along with time and mainly comprise entrance guard data for passing in and out, face snapshot data and the like. And analyzing and counting one by one whether the data meet the personnel portrait label according to the established personnel portrait label model, and if so, marking Zhang III with the label. For example, a daytime and nighttime label is marked by entrance guard statistics, if Zhang III in the latest period of time goes from 18 pm to 5 am, the Thang III can be marked by the label, and if the trip time in the future is changed from 9 pm to 18 pm, the Thang III cancels the Thang label and becomes a normal trip label. And by analogy, all the labels are analyzed and counted to form a person portrait label with three pages.
Secondly, calculating the risk value of Zhang III by the formula: and calculating a risk value R (score 1 weight1+ score2 weight2+. the + score weight, + score weight is label weight, and calculating the risk value of Zhang III according to the personnel image labels and the weight already obtained by Zhang III.
And finally, displaying the personnel portrait labels and the risk values of the third sheet to form a final personnel portrait of the third sheet.
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: modifications of the technical solutions described in the embodiments or equivalent replacements of some or all technical features may be made without departing from the scope of the technical solutions of the embodiments of the present invention.
Claims (4)
1. A personnel portrait analysis method based on big data real-time analysis is characterized by comprising the following processes:
step 100, obtaining a large amount of samples of personnel static data and personnel dynamic data, classifying the data according to four label dimensions of natural attributes, behavior attributes, habits and hobbies and personnel relations, and establishing a personnel portrait label model;
step 200, acquiring static personnel data and dynamic personnel data of personnel to be analyzed, calculating personnel portrait labels of all the personnel to be analyzed, and establishing a personnel file in a big data search engine, wherein the steps specifically include step 201 to step 205:
step 201, acquiring static personnel data and dynamic personnel data of a person to be analyzed, and determining a unique identifier of the person to be analyzed according to the static personnel data;
202, classifying and placing personnel dynamic data of a to-be-analyzed person into a data pipeline kafka in real time according to four label dimensions of natural attributes, behavior attributes, habits and hobbies and personnel relations by utilizing a streaming real-time analysis processing technology, extracting a unique identifier of the to-be-analyzed person, adding the unique identifier into an accumulator, and broadcasting the unique identifier into the data pipeline kafka;
step 203, taking out personnel dynamic data corresponding to the unique identification of the personnel to be analyzed in batch from the data pipeline kafka, matching the personnel dynamic data with personnel portrait label models in the database, and obtaining the personnel portrait labels by the personnel to be analyzed when the personnel dynamic data meets one or more personnel portrait labels in the personnel portrait label models;
step 204, combining and storing the personnel static data, the personnel dynamic data and the personnel portrait labels of the personnel to be analyzed in a big data search engine;
step 205, according to the method from step 201 to step 204, calculating the personnel portrait labels of all the personnel to be analyzed in sequence, and establishing a personnel file in a big data search engine.
2. The people portrait analysis method based on big data real-time analysis according to claim 1, wherein the people portrait tags of natural attributes include but are not limited to: male, female, nationality;
person representation tags for behavioral attributes include, but are not limited to: night-out in daytime, walking people, frequent trip, driving people, normal living, normal trip and home;
people portrayal labels of habitual interest include, but are not limited to: door card door opening families, APP door opening families, remote door opening families, AI door opening families and other door opening families;
people portrayal tags of social relationships include, but are not limited to: live with family, group, normal social, solitary, general family, dislike of social, live with tenant, family of dingke.
3. The personnel image analysis method based on big data real-time analysis according to claim 1 or 2, characterized in that after step 200, it further comprises: step 300, calculating the risk value of each person to be analyzed by using the following formula:
R＝score1*weight1+score2*weight2+.....+scoren*weightn
wherein, R represents a risk value, score represents a label score, weight represents a label weight, and n represents a label number.
4. The human portrait analysis method based on big data real-time analysis of claim 3, further comprising, after the step 300: and step 400, searching the personnel portrait label and/or the risk value of the target personnel through the keyword to obtain the whole personnel portrait of the target personnel.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011424474.0A CN112527861A (en) | 2020-12-09 | 2020-12-09 | Personnel portrait analysis method based on big data real-time analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011424474.0A CN112527861A (en) | 2020-12-09 | 2020-12-09 | Personnel portrait analysis method based on big data real-time analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112527861A true CN112527861A (en) | 2021-03-19 |
Family
ID=74998243
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011424474.0A Withdrawn CN112527861A (en) | 2020-12-09 | 2020-12-09 | Personnel portrait analysis method based on big data real-time analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112527861A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115409433A (en) * | 2022-11-02 | 2022-11-29 | 成都宏恒信息科技有限公司 | Depth NLP-based method and device for analyzing portrait of key community personnel |
-
2020
- 2020-12-09 CN CN202011424474.0A patent/CN112527861A/en not_active Withdrawn
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115409433A (en) * | 2022-11-02 | 2022-11-29 | 成都宏恒信息科技有限公司 | Depth NLP-based method and device for analyzing portrait of key community personnel |
| CN115409433B (en) * | 2022-11-02 | 2023-04-07 | 成都宏恒信息科技有限公司 | Depth NLP-based method and device for analyzing important community personnel portrait |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Tabak et al. | Machine learning to classify animal species in camera trap images: Applications in ecology | |
| CN107577688B (en) | Original article influence analysis system based on media information acquisition | |
| CN107229708B (en) | Personalized travel service big data application system and method | |
| Balaanand et al. | An enhanced graph-based semi-supervised learning algorithm to detect fake users on Twitter | |
| CN111831636A (en) | Data processing method, device, computer system and readable storage medium | |
| CN106462807A (en) | Learning multimedia semantics from large-scale unstructured data | |
| CN110019703B (en) | Data marking method and device and intelligent question-answering method and system | |
| WO2023108980A1 (en) | Information push method and device based on text adversarial sample | |
| US20080147631A1 (en) | Method and system for collecting and retrieving information from web sites | |
| CN111696656B (en) | Doctor evaluation method and device of Internet medical platform | |
| CN110737821B (en) | Similar event query method, device, storage medium and terminal equipment | |
| Goncalves et al. | Gathering alumni information from a web social network | |
| CN111159763A (en) | System and method for analyzing portrait of law-related personnel group | |
| CN114491084A (en) | Self-encoder-based relational network information mining method, device and equipment | |
| CN105389714B (en) | Method for identifying user characteristics from behavior data | |
| CN112527861A (en) | Personnel portrait analysis method based on big data real-time analysis | |
| CN112395513A (en) | Public opinion transmission power analysis method | |
| Hu et al. | A faq finding process in open source project forums | |
| CN116521729A (en) | Information classification searching method and device based on elastic search | |
| CN112685618A (en) | User feature identification method and device, computing equipment and computer storage medium | |
| CN110069691A (en) | For handling the method and apparatus for clicking behavioral data | |
| CN109902129A (en) | Insurance agent's classifying method and relevant device based on big data analysis | |
| Esuli et al. | Traj2user: exploiting embeddings for computing similarity of users mobile behavior | |
| Sari Aslam et al. | Trip purpose identification using pairwise constraints based semi-supervised clustering | |
| Tsai et al. | Object architected design and efficient dynamic adjustment mechanism of distributed web crawlers |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210319 |
|
| WW01 | Invention patent application withdrawn after publication |