CN112395482A - Food safety incident early warning platform - Google Patents

Food safety incident early warning platform Download PDF

Info

Publication number
CN112395482A
CN112395482A CN202011227796.6A CN202011227796A CN112395482A CN 112395482 A CN112395482 A CN 112395482A CN 202011227796 A CN202011227796 A CN 202011227796A CN 112395482 A CN112395482 A CN 112395482A
Authority
CN
China
Prior art keywords
module
early warning
food
judging
data
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
Application number
CN202011227796.6A
Other languages
Chinese (zh)
Other versions
CN112395482B (en
Inventor
段大高
王东
刘峥
张轩
曹若湘
宁芳
孟璐璐
张炎
韩忠明
邵开建
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Center for Disease Prevention and Control
Beijing Technology and Business University
Original Assignee
Beijing Center for Disease Prevention and Control
Beijing Technology and Business University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Center for Disease Prevention and Control, Beijing Technology and Business University filed Critical Beijing Center for Disease Prevention and Control
Priority to CN202011227796.6A priority Critical patent/CN112395482B/en
Publication of CN112395482A publication Critical patent/CN112395482A/en
Application granted granted Critical
Publication of CN112395482B publication Critical patent/CN112395482B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • G06F16/951—Indexing; Web crawling techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/279—Recognition of textual entities
    • G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/30—Semantic analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • 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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/26—Government or public services

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Artificial Intelligence (AREA)
  • Data Mining & Analysis (AREA)
  • Business, Economics & Management (AREA)
  • Biomedical Technology (AREA)
  • Molecular Biology (AREA)
  • Biophysics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Computing Systems (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Databases & Information Systems (AREA)
  • Tourism & Hospitality (AREA)
  • Educational Administration (AREA)
  • Human Resources & Organizations (AREA)
  • Marketing (AREA)
  • Primary Health Care (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • Economics (AREA)
  • Development Economics (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention relates to a food safety event early warning platform. The early warning platform includes: the system comprises a news mining module, a data management module, an early warning module and a display module, wherein the news mining module is used for collecting food data from each big news website, the data management module is used for storing the food data collected by the news mining module, the early warning module is used for calling the food data from the data management module, extracting key information according to the food data based on a machine reading understanding model of a graph neural network, and judging and evaluating food according to the key information; the display module is used for displaying the early warning information according to the evaluation result of the early warning module. The invention can early warn food safety events in time, and avoid further time expansion to cause larger casualties and property loss.

Description

Food safety incident early warning platform
Technical Field
The invention relates to the field of food safety, in particular to a food safety event early warning platform.
Background
The food safety means that the food is nontoxic and harmless, meets the existing nutritional requirements, and does not cause any acute, subacute or chronic harm to the health of human bodies. On the one hand, the food safety problem is "public health problem that toxic and harmful substances in food have an influence on human health".
On the other hand, the food safety problem influences the people's countryside, and the shadow of the three-deer event still covers the heart of people in China so far, thereby restricting the development of the domestic milk powder industry. People pay more attention to the quality of clothes and eating residences, and pay more and more attention to the problem of food safety, which practically influences the living quality of people and the safety of people and property. The goat death and reinforcement is not as good as prevention, a food safety event early warning platform is constructed, food safety events can be automatically evaluated from the acquired data, corresponding early warning is timely provided, and the method has great significance. The existing food safety early warning is mainly divided into early warning and late warning, and the early warning is difficult to realize because data of a plurality of food production processes, such as planting, breeding, slaughtering, processing, packaging, storing and the like, cannot be obtained. And the method of after-the-fact control is difficult to carry out early warning in time, thus avoiding the situation from expanding.
Disclosure of Invention
The invention aims to provide a food safety event early warning platform which can early warn food safety events in time and avoid the further expansion of time to cause greater casualties and property loss.
In order to achieve the purpose, the invention provides the following scheme:
a food safety event early warning platform, comprising: the system comprises a news mining module, a data management module, an early warning module and a display module, wherein the news mining module is used for collecting food data from each big news website, the data management module is used for storing the food data collected by the news mining module, the early warning module is used for calling the food data from the data management module, extracting key information according to the food data based on a machine reading understanding model of a graph neural network, and judging and evaluating food safety events according to the key information; the display module is used for displaying the early warning information according to the evaluation result of the early warning module.
Optionally, the early warning module includes a data processing module, a reading understanding module and an evaluation module, the data processing module is configured to convert news, which is already classified into words in the data management module, into graph structure data, the reading understanding module is configured to extract key information from the graph structure data to obtain answer data, the evaluation module is configured to determine a security event rating according to the answer data and a matching rule, and determine whether to perform early warning, and the evaluation module is connected to the presentation module.
Optionally, the reading understanding module comprises an administrative level judging module, a special area judging module, an casualty judging module and a social influence judging module, wherein the administrative level judging module, the special area judging module, the casualty judging module and the social influence judging module are respectively connected with the data processing module, the administrative level judging module is used for judging which department determines the food accident, the special area judging module is used for judging whether the food accident site is in a national or regional important event, an important conference or a campus, the casualty judging module is used for judging the casualty condition of the food accident, and the social influence judging module is used for judging the area affected by the food accident.
Optionally, the security event rating includes a primary warning, a secondary warning, a tertiary warning, and a quaternary warning.
Optionally, the reading understanding module extracts the key information by using a machine reading understanding model based on a graph neural network.
Optionally, the method further comprises: the system comprises a user management module, a user management module and a user information display module, wherein the user management module comprises a user registration login module, an administrator module and a user information display module, the user registration login module registers a system account and a login system for a user and gives corresponding authority according to the identity during registration, the management module is used for managing system information and user information for the administrator, and the user information display module is used for providing the functions of checking, increasing, deleting, modifying and checking account information for common users and administrator users.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
the food safety risk early warning system for post control by taking news as a data source utilizes the machine reading understanding model to dig out key information in the news so as to early warn food safety events in time, thereby avoiding larger casualties and property loss caused by further expanding time.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
FIG. 1 is a diagram of the structure of the food safety event early warning platform assembly according to the present invention;
fig. 2 is a schematic diagram of the machine reading understanding model composition of the invention.
Detailed Description
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 derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention aims to provide a food safety event early warning platform which can early warn food safety events in time and avoid the further expansion of time to cause greater casualties and property loss.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
The food safety event early warning platform which takes news as a data source and aims at post control utilizes a machine reading understanding model to dig out key information in the news so as to early warn food safety events in time, and further time expansion is avoided to cause greater casualties and property loss.
As shown in fig. 1, a food safety event early warning platform includes: the system comprises a news mining module 1, a data management module 2, an early warning module 3 and a display module 4, wherein the news mining module 1 is used for collecting food data from various news websites, the data management module 2 is used for storing the food data collected by the news mining module 1, and the early warning module 3 is used for calling the food data from the data management module 2, extracting key information according to the food data based on a machine reading understanding model of a graph neural network, and judging and evaluating food safety events according to the key information; the display module 4 is used for displaying the early warning information according to the evaluation result of the early warning module 3.
The news mining module 1 applies a dynamic rendering technology and an incremental technology when crawling data from various news websites.
The current webpage needs many complex operations in the browsing process, the dynamic rendering technology obtains data in the webpage through simulating complex operations such as clicking, sliding, dragging and the like, and the Splash toolkit is used for achieving the data.
The core of the incremental technology is duplicate removal, and when a part of new data is added to a website on the original basis, the crawled data can be removed, and only the new data is crawled, so that the data repetition is avoided. Taking a Chinese food safety net as an example, the safety net is provided with modules of food safety news in the places of Shi 'an Beijing, Shi' an Shanghai and the like, so that a crawler can be designed, the news of the website is crawled into a database and is subjected to conventional data preprocessing work such as word segmentation, noise reduction, duplicate removal and the like, and the function is realized by jieba word segmentation.
The data management module 2 stores the news data crawled in the data acquisition module 1 by adopting a mysql database, the authority of the data management module is divided into administrator authority and user authority, under the user authority, an operator can only check, add, delete, modify, export and search the data stored by the current user, and the administrator authority can perform the above operation on the data of all accounts.
The early warning module 3 is the core of the whole system and integrates the functions of event evaluation and early warning, the early warning module 3 comprises a data processing module 6, a reading understanding module 7 and an evaluation module 12, the data processing module 6 is used for converting news with words already divided in the data management module 2 into graph structure data, the reading understanding module 7 is used for extracting key information from the graph structure data to obtain answer data, the evaluation module 12 is used for determining the rating of a security event according to the answer data and a matching rule and judging whether to perform early warning, and the evaluation module 12 is connected with the display module 4. The reading understanding module 7 comprises an administrative level judging module 8, a special area judging module 9, an casualty judging module 10 and a social influence judging module 11, the administrative level judging module 8, the special area judging module 9, the casualty judging module 10 and the social influence judging module 11 are respectively connected with the data processing module 6, the administrative level judging module 8 is used for judging which department determines the food accident, the special area judging module 9 is used for judging whether the food accident occurrence area is in a national or regional important activity, an important conference or a campus, the casualty judging module 10 is used for judging the casualty condition of the food accident, and the social influence judging module 11 is used for judging the influence area of the food accident. The safety event rating comprises a first-level early warning, a second-level early warning, a third-level early warning and a fourth-level early warning.
The data processing module 6 is used for converting the news with well-divided words, which is transmitted in the data management module 2, into a graph structure so as to design a machine reading understanding model based on a graph neural network to carry out data mining. All words are defaulted to have relations, and a full-connection graph is constructed.
The data processed by the data processing module 6 is transmitted to the machine reading understanding module 7, a machine reading understanding model based on a graph neural network is used for extracting key information, the input of the machine reading understanding model is an article and a corresponding question, and the output of the machine reading understanding model is an answer of the question in the article.
The model comprises a word embedding layer, a text embedding layer, an attention flow layer, a full text modeling layer and a section selection layer from bottom to top. The machine reading understanding model based on the gated graph neural network has the following functions:
1. word embedding layer: the layer uses bert to obtain semantic latent vector, and obtains fixed problem latent vector U belonging to Qd×jAnd a news latent vector E E Nd×t. Where d represents the dimension of the vector and j and t represent the number of words in the question and news, respectively.
2. Text embedding layer: the article is constructed into a graph structure in the layer, words in the article are connected pairwise, namely the words represented by the nodes of the graph, and the edges represent the relationship between the words. Reusing gated graphsThe neural network learns the context relationship information of the text on the basis of the semantic vector. The output vector of the problem latent vector U after being input into the layer is Q e Q2d×jThe output vector of the news latent vector E after being input into the text is N E N2d×t。
3. Attention flow layer: the inputs of this layer are the outputs of the previous layer, i.e., Q 'and N'. By using Stj＝α(N：t，Q：j) e.R, a similarity matrix S can be obtained, wherein StjMeaning the similarity of the tth word and the jth word in the text,
Figure RE-GDA0002883914520000051
and further operating S to obtain the attention of NewstoQuery and QueryNewNews. Take NewstQuery as an example, StjRepresenting the similarity degree of the t-th word in the text and the j-th word in the question, namely, each line in S represents the similarity between the news word corresponding to the line and all the question words, and after being normalized by using softmax (), the news word is combined with the question matrix Q
Figure RE-GDA0002883914520000052
And (4) obtaining a new problem latent vector. Query to News attention is paid to the same. The resulting two-directional attention is then passed through the matrix N
Figure RE-GDA0002883914520000053
Is connected therein
Figure RE-GDA0002883914520000054
4. Full this modeling layer: the layer uses a double-layer Bi-LSTM network, the output dimension of each layer of the network is d, and the integral output is a matrix M belonging to the R2d×tEach column in the matrix contains information of words in news and problems, and contains the relation of the words in news under the condition of the problems.
5. Selecting a layer: the model needs to intercept reasonable segments as answers in the news, i.e. find the start position and the end position of the answers in the news. The probability formula for the start position index is:
Figure RE-GDA0002883914520000055
wherein
Figure RE-GDA0002883914520000061
Is a variable weight vector. When the end position is predicted, M is calculated through a layer of Bi-LSTM to output M2∈R2d×TAnd then, calculating by using the same probability formula:
Figure RE-GDA0002883914520000062
according to the regulations of relevant national departments, the condition for evaluating the early warning level is converted into four problems: 1. which department identified the incident? 2. What activity, meeting or campus the accident occurred in? 3. Casualty in accident? 4. Area of impact of accident? These four problems correspond to the administrative level determination module 8, the special area determination module 9, the casualty determination module 10, and the social influence determination module 11, respectively. The goal is for the model to give answers to these four questions for subsequent operations.
The processed news is used as an article of a training data set, the questions corresponding to the administrative level judging module 8, the special area judging module 9, the casualty judging module 10 and the social influence judging module 11 are used as the problems of the article, answers are manually input and stored in the training set, and a complete food safety event reading understanding data set is constructed and used for training a machine reading understanding model based on a graph neural network. After the model is trained, answers of the questions in the news can be automatically given according to the news and the questions. After the answers to the four questions are transmitted to the evaluation module 12, the early warning level can be determined according to the answers and early warning is performed.
The function of the evaluation module 12 is to classify food safety accidents into four early warning levels, namely, level I (mild), level II (moderate), level III (severe) and level IV (warning) according to related laws and regulations by reading answers of the understanding model to the four questions. After the answers of the reading understanding model are extracted, the evaluation module 12 can realize the evaluation function by using simple condition judgment, namely, according to the answers of the reading understanding module 7, rules are matched to draw an early warning level. The following are evaluation judgment rules set according to national standards.
If [ (accident-affected area > ═ two towns) and (accident-affected area < two counties) ] or [ (victim > ═ 30) and (dead person ═ 0) ] or (as determined by county department). A primary warning is output.
If [ (accident-affected area > ═ two counties) and (accident-affected area < two cities) ] or [ (victim > ═ 100) or (dead >0) ], or (as determined by the city department). A secondary warning is output.
If [ (accident-affected zone > ═ two cities) and (accident-affected zone < two provinces) ] or [ (victim > ═ 100) and (deceased >0) ] or (determined by provincial departments) or [ (occurred at school) and (victim > ═ 50) ] or [ (occurred at nationwide or regional major activities, major meetings) and (victim > ═ 50) ]. Then a third level of warning is output.
If [ (accident-affected zone > < two provinces) ] and (with a further tendency to expand) ] either (beyond the provincial disposal range) or (as determined by the above-provincial department). Then a four-level warning is output.
Specific examples are as follows: for example, in the 315 evening of 2020, the hamburger king event in Nanchang city is exposed, and characters such as Nanchang city, whole city renovation and the like appear in various related news. In the early warning platform for food safety incidents, the answer to the problem (the area affected by the accident.
The display module 4 is used for displaying the early warning information. The evaluation module 12 is used for judging the answers to the problems corresponding to the administrative level judgment module 8, the special area judgment module 9, the casualty judgment module 10 and the social influence judgment module 11 to obtain the grade of the security event, and judging whether to perform early warning or not, if one of four early warning levels is met, the corresponding early warning level and the full text of the corresponding news are transmitted to the display module 4 for displaying. If the display module does not meet any one of the four early warning levels, the display module does not transmit the display module to the display module 4, namely, the early warning is not carried out.
The food safety event early warning platform of the invention also comprises: a user management module 5. Because the system is used by facing departments, organizations and individual users at all levels, the user management module 5 is added, and the use of the user is convenient. The user management module 5 comprises a user registration login module 13, an administrator module 14 and a user information presentation module 15. The user registration login module 13 registers a system account and a login system for a user, and gives a corresponding authority according to the identity during registration. If the account is a common user, the data management module 2 can only perform operations of increasing, deleting, modifying, checking and exporting data which are crawled by the account and stored in the database. If the authority is the administrator authority, the data management module 2 may perform the above operation on the data of all the accounts. The management module is used for managing system information and user information by an administrator. The user information display module 15 is used for providing the functions of checking account information and increasing, deleting, modifying and checking for common users and administrator users.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to assist understanding of the system and its core concepts; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, the present disclosure should not be construed as limiting the invention.

Claims (6)

1. A food safety incident early warning platform, comprising: the system comprises a news mining module, a data management module, an early warning module and a display module, wherein the news mining module is used for collecting food data from each big news website, the data management module is used for storing the food data collected by the news mining module, the early warning module is used for calling the food data from the data management module, extracting key information according to the food data based on a machine reading understanding model of a graph neural network, and judging and evaluating food safety events according to the key information; the display module is used for displaying the early warning information according to the evaluation result of the early warning module.
2. The food safety event early warning platform according to claim 1, wherein the early warning module comprises a data processing module, a reading understanding module and an evaluation module, the data processing module is used for converting news which is divided into words in the data management module into graph structure data, the reading understanding module is used for extracting key information from the graph structure data to obtain answer data, the evaluation module is used for determining the rating of a safety event according to the answer data and a matching rule and judging whether early warning is performed, and the evaluation module is connected with the display module.
3. The food safety incident early warning platform according to claim 2, wherein the reading understanding module comprises an administrative level judging module, a special area judging module, an injury and death judging module and a social influence judging module, the administrative level judging module, the special area judging module, the injury and death judging module and the social influence judging module are respectively connected with the data processing module, the administrative level judging module is used for judging which government has identified the food accident, the special area judging module is used for judging whether the food accident site is in national or regional major activities, major conferences or campuses, the injury and death judging module is used for judging the casualties of the food accident, and the social influence judging module is used for judging the area of influence of the food accident.
4. The food safety event early warning platform of claim 2, wherein the safety event rating comprises a primary early warning, a secondary early warning, a tertiary early warning, and a quaternary early warning.
5. The food safety event early warning platform according to claim 2, wherein the reading understanding module extracts key information by adopting a machine reading understanding model based on a graph neural network.
6. The food safety event early warning platform of claim 1, further comprising: the system comprises a user management module, a user management module and a user information display module, wherein the user management module comprises a user registration login module, an administrator module and a user information display module, the user registration login module registers a system account and a login system for a user and gives corresponding authority according to the identity during registration, the management module is used for managing system information and user information for the administrator, and the user information display module is used for providing the functions of checking, increasing, deleting, modifying and checking account information for common users and administrator users.
CN202011227796.6A 2020-11-06 2020-11-06 Food safety incident early warning platform Active CN112395482B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011227796.6A CN112395482B (en) 2020-11-06 2020-11-06 Food safety incident early warning platform

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011227796.6A CN112395482B (en) 2020-11-06 2020-11-06 Food safety incident early warning platform

Publications (2)

Publication Number Publication Date
CN112395482A true CN112395482A (en) 2021-02-23
CN112395482B CN112395482B (en) 2021-11-19

Family

ID=74598246

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011227796.6A Active CN112395482B (en) 2020-11-06 2020-11-06 Food safety incident early warning platform

Country Status (1)

Country Link
CN (1) CN112395482B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113177831A (en) * 2021-03-12 2021-07-27 西安理工大学 Financial early warning system and method constructed by applying public data
CN113554321A (en) * 2021-07-28 2021-10-26 陕西科技大学 Dairy product cold-chain logistics quality safety early warning method

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1556780A4 (en) * 2002-10-08 2006-11-15 Food Security Systems L L C System and method for identifying a food event, tracking the food product, and assessing risks and costs associated with intervention
US20110246002A1 (en) * 2010-04-02 2011-10-06 Cloudahoy Inc. Systems and methods for aircraft flight tracking and analysis
CN102609475A (en) * 2012-01-19 2012-07-25 浙江省公众信息产业有限公司 Method for monitoring content of microblog and monitoring system
CN202443496U (en) * 2011-12-29 2012-09-19 钟安清 Food safety third-party supervisory system based on SPS and HACCP
CN104077668A (en) * 2014-07-18 2014-10-01 北京创鑫汇智科技发展有限责任公司 Emergency meeting rescue and security basic information management system
CN105741216A (en) * 2016-02-06 2016-07-06 福州宏泰分析技术有限公司 Intelligent food quality security supervision system
US9443005B2 (en) * 2012-12-14 2016-09-13 Instaknow.Com, Inc. Systems and methods for natural language processing
CN110097037A (en) * 2019-05-22 2019-08-06 天津联图科技有限公司 Intelligent monitoring method, device, storage medium and electronic equipment
CN110688557A (en) * 2019-09-23 2020-01-14 中国农业大学 Food safety event-oriented early warning method
US10678233B2 (en) * 2017-08-02 2020-06-09 Strong Force Iot Portfolio 2016, Llc Systems and methods for data collection and data sharing in an industrial environment

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1556780A4 (en) * 2002-10-08 2006-11-15 Food Security Systems L L C System and method for identifying a food event, tracking the food product, and assessing risks and costs associated with intervention
US20110246002A1 (en) * 2010-04-02 2011-10-06 Cloudahoy Inc. Systems and methods for aircraft flight tracking and analysis
CN202443496U (en) * 2011-12-29 2012-09-19 钟安清 Food safety third-party supervisory system based on SPS and HACCP
CN102609475A (en) * 2012-01-19 2012-07-25 浙江省公众信息产业有限公司 Method for monitoring content of microblog and monitoring system
US9443005B2 (en) * 2012-12-14 2016-09-13 Instaknow.Com, Inc. Systems and methods for natural language processing
CN104077668A (en) * 2014-07-18 2014-10-01 北京创鑫汇智科技发展有限责任公司 Emergency meeting rescue and security basic information management system
CN105741216A (en) * 2016-02-06 2016-07-06 福州宏泰分析技术有限公司 Intelligent food quality security supervision system
US10678233B2 (en) * 2017-08-02 2020-06-09 Strong Force Iot Portfolio 2016, Llc Systems and methods for data collection and data sharing in an industrial environment
CN110097037A (en) * 2019-05-22 2019-08-06 天津联图科技有限公司 Intelligent monitoring method, device, storage medium and electronic equipment
CN110688557A (en) * 2019-09-23 2020-01-14 中国农业大学 Food safety event-oriented early warning method

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
MINJOON SEO ETC.AL: ""BI-DIRECTIONAL ATTENTION FLOW FOR MACHINE COMPREHENSION"", 《ICLR 2017》 *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113177831A (en) * 2021-03-12 2021-07-27 西安理工大学 Financial early warning system and method constructed by applying public data
CN113177831B (en) * 2021-03-12 2024-05-17 西安理工大学 Financial early warning system constructed by application of public data and early warning method
CN113554321A (en) * 2021-07-28 2021-10-26 陕西科技大学 Dairy product cold-chain logistics quality safety early warning method

Also Published As

Publication number Publication date
CN112395482B (en) 2021-11-19

Similar Documents

Publication Publication Date Title
Aparcana et al. Development of a social impact assessment methodology for recycling systems in low-income countries
Zhang et al. Social vulnerability to floods: a case study of Huaihe River Basin
CN106815293A (en) System and method for constructing knowledge graph for information analysis
Bammer et al. Repetition strain injury in Australia: medical knowledge, social movement, and de facto partisanship
CN112395482B (en) Food safety incident early warning platform
Zhang et al. A topic model based framework for identifying the distribution of demand for relief supplies using social media data
Nzeadibe et al. Beyond urban vulnerability: interrogating the social sustainability of a livelihood in the informal economy of Nigerian cities
Foong et al. Cyberbullying system detection and analysis
Li et al. Quantitative evaluation of China's disaster relief policies: a PMC index model approach
L'Abate et al. The drivers of sustainability disclosure practices in the airport industry: A legitimacy theory perspective
Han et al. Topical and emotional expressions regarding extreme weather disasters on social media: a comparison of posts from official media and the public
Farhat et al. Analyzing the scholarly footprint of ChatGPT: Mapping the progress and identifying future trends
Raisio et al. Could virtual volunteerism enhance information resilience in a nuclear emergency? The potential role of disaster knowledge workers and virtual emergent groups
Watts et al. Social network analysis of sustainable transportation organizations
Ferrante Developing an offender-based tracking system: The Western Australia INOIS project
CN111160786B (en) Building earthquake risk assessment method based on ontology
Zhu et al. Construction and application of knowledge-base in telecom fraud domain
CN115345401A (en) Six-dimensional analysis method for finding enterprise financial risk
Martín et al. Individual breaches of environmental laws in cases from public administration files
Xu et al. A Weighted Information Fusion Method Based on Sentiment Knowledge for Emergency Decision-Making Considering the Public and Experts
Habib et al. Role of Media in Coverage and Reporting of Child Abuse Cases
Egami et al. Urban problem LOD for understanding the problem structure and detecting vicious cycles
Mu et al. Construction of Knowledge Graph for Emergency Resources
Qiu et al. Police alarm address recognition and classification based on convolutional neural networks
Kolocek The human right to housing: Using ATLAS. ti to combine qualitative and quantitative methods to analyze global discourses

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