CN102248955A - Automatic alarm receiving method - Google Patents
Automatic alarm receiving method Download PDFInfo
- Publication number
- CN102248955A CN102248955A CN2011101951301A CN201110195130A CN102248955A CN 102248955 A CN102248955 A CN 102248955A CN 2011101951301 A CN2011101951301 A CN 2011101951301A CN 201110195130 A CN201110195130 A CN 201110195130A CN 102248955 A CN102248955 A CN 102248955A
- Authority
- CN
- China
- Prior art keywords
- prediction scheme
- match
- execution
- cooresponding
- successful
- 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
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides an automatic alarm receiving method, which comprises the following steps of: 1, matching a subject field in alarm information with a failure name in a history library and acquiring a successful matching plan; 2, recording information corresponding to the successful matching plan in the history library and starting the plan; and 3, recording an execution result of the plan in a status bar corresponding to the plan in the history library. In the method, the subject field in the alarm information transmitted by a locomotive and the failure name in the history library are matched to obtain the successful matching plan for realizing automatic selection and starting of the plan when the locomotive transmits the alarm information, and a reliable plan is adopted in a short period of time, so that a failure can be eliminated immediately, and safe running of the locomotive can be recovered.
Description
Technical field
The present invention relates to the locomotive failure control technology, relate in particular to the method for receiving a crime report automatically that the automatic prediction scheme of alarm message is selected and started.
Background technology
Along with the lasting acceleration of the continuous development of national economy and city, Development of China's Urbanization, Chinese Railway also in without a stop development to adapt to more passenger flow, faster speed and safer running.
Because it is various and influence greatly influence factor that the locomotive on the railway normally moves, locomotive often breaks down.When locomotive breaks down, at first need the staff to carry out specialty analysis and draw prediction scheme; eliminate fault through staff's rigorous operation then, can not more in time eliminate fault though the prediction scheme that staff's specialty analysis draws can be guaranteed the safe operation of locomotive.
Summary of the invention
At above-mentioned defective, the invention provides a kind of method of receiving a crime report automatically.
Automatically the method for receiving a crime report provided by the invention comprises:
Step 1: the subject field in the alarm message and the fault title in the history library mated and obtain the prediction scheme that the match is successful;
Step 2: the cooresponding information of prediction scheme that the match is successful is recorded in the described history library, and starts described prediction scheme;
Step 3: the execution result of described prediction scheme is recorded in the described history library and the cooresponding status bar of described prediction scheme.
The automatic selection and the startup of prediction scheme when obtaining the prediction scheme that the match is successful and realizing that locomotive sends alarm message mated in the present invention by subject field in the alarm message that locomotive is sent and the fault title in the history library, adopt the failure-free prediction scheme at short notice, thereby can eliminate fault in time, recover the safe operation of locomotive.
Description of drawings
Fig. 1 is receive a crime report the automatically diagram of circuit of method of the present invention;
Fig. 2 is the constructional drawing of forecast model decision tree of the present invention.
The specific embodiment
Further specify the technical scheme of the embodiment of the invention below in conjunction with the drawings and specific embodiments.
Fig. 1 is receive a crime report the automatically diagram of circuit of method of the present invention, and as shown in Figure 1, this method mainly may further comprise the steps:
Step 1: the subject field in the alarm message and the fault title in the history library mated and obtain the prediction scheme that the match is successful;
Step 2: the cooresponding information of prediction scheme that the match is successful is recorded in the described history library, and starts described prediction scheme;
Step 3: the execution result of described prediction scheme is recorded in the described history library and the cooresponding status bar of described prediction scheme.
The cooresponding information of the prediction scheme that the match is successful is recorded in the described history library, and start described prediction scheme, particularly, with the fault title of the prediction scheme that the match is successful, use the fault title of prediction scheme number record in history library, use in the prediction scheme numbered bin, and prediction scheme that will the match is successful is presented on the display terminal, checks for the staff; The execution result of described prediction scheme is recorded in the described prediction scheme storehouse and the cooresponding status bar of described prediction scheme, particularly, the execution result of the prediction scheme that the match is successful comprises " success ", " getting nowhere ", if execution result is " success ", then will " finish " add in the history library with the cooresponding status bar of described prediction scheme in, if execution result is " getting nowhere ", then will " not finish " add in the history library with the cooresponding status bar of described prediction scheme in.Also can be in the fault numbered bin of history library in step 2 with the fault number record, in step 3, can be added to the execution date of prediction scheme in the history library with the cooresponding dateline of this prediction scheme in.
The startup of the automatic selection of prediction scheme when obtaining the prediction scheme that the match is successful and realizing that locomotive sends alarm message is mated in the present invention by subject field in the alarm message that locomotive is sent and the fault title in the history library, adopt the failure-free prediction scheme at short notice, thereby can eliminate fault in time, recover the safe operation of locomotive.
Step 1 can specifically comprise the steps:
Step 11: go out the historical operation record that conforms to subject field in the alarm message according to fault title exact-match lookup from history library, and the record that obtains the historical operation number counts Rs, if Rs=1, then the match is successful, execution in step 2; If Rs>1, then execution in step 12; If Rs=0, then execution in step 13.
From history library, go out the historical operation record that conforms to subject field in the alarm message according to fault title exact-match lookup, belong to accurate matching process, in history library, search the situation of in historical operation, eliminating this fault by this accurate matching process, the prediction scheme that comprises use is used implementation status of prediction scheme or the like.
Historical operation in the history library has write down historical failure and has eliminated process, and this also is the main authority of real-time fault analysis.The content of historical operation record includes but not limited in the history library: fault numbering, fault title, use prediction scheme numbering, date and state, and as shown in table 1, comprise the fault title certainly in the history library, use prediction scheme numbering, state to get final product.
Table 1
The fault numbering | The fault title | Use prediction scheme numbering | Date | State |
SysA-P0-9878 | Be subjected to the electric work fault | EQ-P0-23554 | 2010-9-12 | Finish |
SysB-Win-0980 | The strong wind early warning | Sec-Win-98778 | 2010-11-21 | Finish |
Step 12: the content in the described alarm message is added that adeditive attribute and content summary carry out fuzzy matching in text library, wherein, described content summary is present in the prediction scheme storehouse, and the cooresponding prediction scheme numbering of described content summary is same as and the cooresponding use prediction scheme numbering of the cooresponding fault title of described subject field, if the match is successful, then execution in step 2;
Hypernym, hyponym, polysemant are recorded in the text library.Hypernym is meant the descriptor that conceptive extension is wider, and for example the vehicle are exactly the hypernym of train; Hyponym is meant the descriptor that conceptive intension is narrower, and for example motor-car is exactly the hyponym of train; Polysemant is the speech with several meanings that differ from one another and be mutually related.
Comprise the descriptor of describing content summary in the text library.When the distance between the common hypernym is meant the common hypernym that finds two speech, find each speech this common hypernym desired seek number of times and, even the hypernym of A is a, the hypernym of B is b, the hypernym of a is d, the hypernym of b is a, then a is the common hypernym of A and B, the number of times that finds this common hypernym to search from A is 1, and the number of times that finds this common hypernym to search from B is 2, and then the distance between the common hypernym of A and B is 1+2=3, also as: car is the hypernym of train, distance between them is 1, and train is the hypernym of motor-car, and the distance between car and the motor-car is 2 so.In fact, in text library, search the hypernym that content summary and content add adeditive attribute, when in text library, finding content summary and content to add the common hypernym of adeditive attribute, from content add adeditive attribute find number of times that this common hypernym need search and from content summary find number of times that this common hypernym need search and be exactly C2.
Have mapping relations between alarm message and the prediction scheme storehouse, alarm message is represented with C, and the prediction scheme storehouse is represented with D.Alarm message is sent by peripheral system, and alarm message includes but not limited to: message subject, message content, type of message and adeditive attribute etc., wherein message subject belongs to subject field, type of message belongs to the type of alarm field, adeditive attribute belongs to the adeditive attribute field, and message content belongs to content field; The prediction scheme storehouse includes but not limited to: content summary field, prediction scheme number field, header field.
The adeditive attribute field of content field+C of C and the content summary field of D form corresponding relation.
Step 13: described content is added the above adeditive attribute mate in described text library, if the match is successful, then execution in step 2.
Need to prove that Rs=1 means two kinds of situations: have only one with the fault title in the history library that subject field in the alarm message conforms to; With more than one of fault title in the history library that subject field in the alarm message conforms to, but be the same with the cooresponding use prediction scheme numbering of each fault title.
When Rs>1, the detailed process of execution in step 12 can be described below:
Step 121: at each content summary, search the common hypernym that described content adds the above adeditive attribute and described content summary in described text library, and obtain the number C3 of described common hypernym, if C3=0, then it fails to match; If C3>0, then execution in step 122;
Because Rs>1 o'clock, the number of the cooresponding content summary of fault title that conforms to subject field in the history library is greater than 1, so need all will add that adeditive attribute carries out fuzzy matching in text library at each content summary with content.
Step 122: obtain the distance C 2 between the described common hypernym,, then calculate the prediction scheme reference value of the cooresponding prediction scheme of qualified described content summary if C2 is not more than the 3rd threshold value; If C2 is greater than the 3rd threshold value, then execution in step 123;
Step 123: search described content and add the above adeditive attribute and the cooresponding polysemant of described content summary difference in described text library, and obtain the summation C4 of described polysemant, greater than first threshold, then it fails to match as if C4; If C4 is not more than first threshold, then execution in step 124;
Step 124: at each and the cooresponding content summary of described polysemant in the described prediction scheme storehouse, in described text library, search the common hypernym that described content adds the above adeditive attribute and described content summary, and obtain distance C 2 between the described common hypernym, if C2 is greater than second threshold value, then it fails to match; If C2 is not more than second threshold value, then execution in step 125;
Step 125: the prediction scheme reference value of calculating the cooresponding prediction scheme of qualified content summary;
Wherein, step 121-step 125 belongs to the process of fuzzy matching, and the algorithm that fuzzy matching is adopted is: (Latent Semantic Analysis is called for short: LSA), can find out a plurality of prediction schemes by this fuzzy matching latent semantic analysis.
Step 126: the described prediction scheme reference value of all that will calculate compares and selects the cooresponding prediction scheme of maximum prediction scheme reference value as the prediction scheme that the match is successful, and the match is successful, execution in step 2.
Step 126 belongs to accurate matching process, selects a prediction scheme conduct prediction scheme that the match is successful in this accurate matching process from a plurality of prediction schemes that find out by fuzzy matching.
Be accurate to by employing and fuzzy arrive accurate matching way again,, can improve the speed of coupling guaranteeing to mate under the prerequisite of particularity.
It should be noted that, content summary and content add that the common hypernym of adeditive attribute in text library might be for a plurality of, at this moment, the value of the distance between the common hypernym is a plurality of certainly, and this will select the distance between the minimum common hypernym to compare with the 3rd threshold value or second threshold value.
Can be on display terminal, to show error message to mentioning the processing mode that it fails to match in the literary composition among the present invention, remind the staff that it fails to match, thereby the alarm message that the manual analysis locomotive sends is formulated prediction scheme, to eliminate fault, guarantee the safe operation of locomotive.
First threshold, second threshold value and the 3rd threshold value all are that the staff sets according to the experience of oneself, first threshold is between 6 and 10, second threshold value is between 3 and 6, when content summary and content add that adeditive attribute is totally 148 pairs the time, the first threshold preferred value is 8, the second threshold value preferred value is 5, and in addition, the preferred value of the 3rd threshold value is 2.
Wherein, calculate prediction scheme reference value: RV=0.4*UR+0.6*PR according to following rule, wherein, RV is the prediction scheme reference value, UR is the prediction scheme frequency of utilization, PR is the accurate implementation rate of prediction scheme, UR=(summation of these prediction scheme access times/the type warning frequency) * 100%, PR=(this prediction scheme successful execution number of times/these prediction scheme access times) * 100%.By qualified content summary, can be in the prediction scheme storehouse correspondence go out the prediction scheme numbering, the use prediction scheme that statistics is consistent with this corresponding prediction scheme numbering that goes out in history library is numbered the number of times of generation, can learn this prediction scheme access times; By qualified content summary, can in the prediction scheme storehouse, correspondence go out the prediction scheme numbering, this prediction scheme numbering that goes out according to the correspondence title that can correspondence in history library be out of order, can correspondence go out type of alarm in alarm message according to the fault title, the number of this fault title of statistics can be learnt the summation of the warning frequency of the type in history library; Can in the prediction scheme storehouse, correspondence go out the prediction scheme numbering by qualified content summary, the prediction scheme numbering that goes out according to this correspondence is the corresponding state that goes out this prediction scheme in history library, and the number of times that statistics " finishing " state takes place in history library can be learnt this prediction scheme successful execution number of times.Need to prove that drawing the weight ratio of UR and PR according to experiment and business diagnosis should be between 0.60-0.75, it is comparatively accurate being preferably the result who drew at 4: 6 o'clock.
When Rs=0, the detailed process of execution in step 13 can be described below:
Step 131: search in described text library with described content and add the cooresponding descriptor of the above adeditive attribute, obtain the number R of the described descriptor that finds, if R=0, then it fails to match; If R=1, then the match is successful; If R>1, then execution in step 132;
Step 132: at each content summary in the described prediction scheme storehouse, in described text library, search the common hypernym that described content summary and described content add the above adeditive attribute, and obtain the number C3 of described common hypernym, if C3=0, then it fails to match; If C3>0, then execution in step 133;
Step 133: obtain the distance C 2 between the described common hypernym,, then calculate the prediction scheme reference value of the cooresponding prediction scheme of qualified described content summary if C2 is not more than the 3rd threshold value; If C2 is greater than the 3rd threshold value, then execution in step 134;
Step 134: search described content and add the above adeditive attribute and the cooresponding polysemant of described content summary difference in described text library, and obtain the summation C4 of described polysemant, greater than first threshold, then it fails to match as if C4; If C4 is not more than first threshold, then execution in step 135;
Step 135: at each and the cooresponding content summary of described polysemant in the described prediction scheme storehouse, in described text library, search the common hypernym that described content summary and described content add the above adeditive attribute, and obtain distance C 2 between the described common hypernym, if C2 is greater than second threshold value, then it fails to match; If C2 is not more than second threshold value, then execution in step 136;
Step 136: the prediction scheme reference value of calculating the cooresponding prediction scheme of qualified content summary;
Step 131-step 136 belongs to the fuzzy matching process, and the LSA algorithm is adopted in fuzzy matching, finds out a plurality of prediction schemes by this fuzzy matching process.
Step 137: the described prediction scheme reference value of all that will calculate compares and selects the cooresponding prediction scheme of maximum prediction scheme reference value as the prediction scheme that the match is successful, and the match is successful, execution in step 2.
Step 137 belongs to accurate matching process, selects a prediction scheme conduct prediction scheme that the match is successful in this accurate matching process from a plurality of prediction schemes that find out by the fuzzy matching process.
Equally, it should be noted that more than one situation of common hypernym that adds adeditive attribute and content summary for content, select the distance between the minimum common hypernym to compare with the 3rd threshold value or second threshold value.
The method of wherein calculating the prediction scheme reference value can repeat no more with reference to aforementioned herein.
Used the forecast model decision tree structure when adopting the LSA algorithm, specifically referring to Fig. 2, decision tree has been explained a kind of tree, and each decision tree can rely on carrying out data test cutting apart of source database.This process can recursion tree is pruned, when the class that can not cut apart again or one is independent can be applied to a certain branch, recursive procedure had just been finished, and adopted prediction model decision tree to mate apace.
It should be noted that at last: above embodiment only in order to technical scheme of the present invention to be described, is not intended to limit; Although with reference to previous embodiment the present invention is had been described in detail, those of ordinary skill in the art is to be understood that: it still can be made amendment to the technical scheme that aforementioned each embodiment put down in writing, and perhaps part technical characterictic wherein is equal to replacement; And these modifications or replacement do not make the essence of appropriate technical solution break away from the spirit and scope of various embodiments of the present invention technical scheme.
Claims (8)
1. the method for receiving a crime report automatically is characterized in that, comprising:
Step 1: subject field in the alarm message and the fault title in the history library are mated, and obtain the prediction scheme that the match is successful;
Step 2: the cooresponding information of prediction scheme that the match is successful is recorded in the described history library, and carries out described prediction scheme;
Step 3: the execution result of described prediction scheme is recorded in the described history library and the cooresponding status bar of described prediction scheme.
2. the method for receiving a crime report automatically according to claim 1 is characterized in that described step 1 comprises:
Step 11: go out the historical operation record that conforms to described subject field according to described fault title exact-match lookup from described history library, and obtain the number Rs of described historical operation record, if Rs=1, then the match is successful, execution in step 2; If Rs>1, then execution in step 12; If Rs=0, then execution in step 13;
Step 12: the content in content summary and the described alarm message is added that adeditive attribute carries out fuzzy matching in text library, wherein, described content summary is present in the prediction scheme storehouse, and the cooresponding prediction scheme numbering of described content summary is same as and the cooresponding use prediction scheme numbering of the cooresponding fault title of described subject field, if the match is successful, then execution in step 2;
Step 13: described content is added the above adeditive attribute mate in described text library, if the match is successful, then execution in step 2.
3. the method for receiving a crime report automatically according to claim 2 is characterized in that described step 12 comprises:
Step 121: at each content summary, search the common hypernym that described content adds the above adeditive attribute and described content summary in described text library, and obtain the number C3 of described common hypernym, if C3=0, then it fails to match; If C3>0, then execution in step 122;
Step 122: obtain the distance C 2 between the described common hypernym,, then calculate the prediction scheme reference value of the cooresponding prediction scheme of qualified described content summary if C2 is not more than the 3rd threshold value; If C2 is greater than the 3rd threshold value, then execution in step 123;
Step 123: search described content and add the above adeditive attribute and the cooresponding polysemant of described content summary difference in described text library, and obtain the summation C4 of described polysemant, greater than first threshold, then it fails to match as if C4; If C4 is not more than first threshold, then execution in step 124;
Step 124: at each and the cooresponding content summary of described polysemant in the described prediction scheme storehouse, in described text library, search the common hypernym that described content adds the above adeditive attribute and described content summary, and obtain distance C 2 between the described common hypernym, if C2 is greater than second threshold value, then it fails to match; If C2 is not more than second threshold value, then execution in step 125;
Step 125: the prediction scheme reference value of calculating the cooresponding prediction scheme of qualified content summary;
Step 126: the described prediction scheme reference value of all that will calculate compares and selects the cooresponding prediction scheme of maximum prediction scheme reference value as the prediction scheme that the match is successful, and the match is successful, execution in step 2.
4. the method for receiving a crime report automatically according to claim 2 is characterized in that described step 13 comprises:
Step 131: search in described text library with described content and add the cooresponding descriptor of the above adeditive attribute, obtain the number R of the described descriptor that finds, if R=0, then it fails to match; If R=1, then the match is successful; If R>1, then execution in step 132;
Step 132: at each content summary in the described prediction scheme storehouse, in described text library, search the common hypernym that described content summary and described content add the above adeditive attribute, and obtain the number C3 of described common hypernym, if C3=0, then it fails to match; If C3>0, then execution in step 133;
Step 133: obtain the distance C 2 between the described common hypernym,, then calculate the prediction scheme reference value of the cooresponding prediction scheme of qualified described content summary if C2 is not more than the 3rd threshold value; If C2 is greater than the 3rd threshold value, then execution in step 134;
Step 134: search described content and add the above adeditive attribute and the cooresponding polysemant of described content summary difference in described text library, and obtain the summation C4 of described polysemant, greater than first threshold, then it fails to match as if C4; If C4 is not more than first threshold, then execution in step 135;
Step 135: at each and the cooresponding content summary of described polysemant in the described prediction scheme storehouse, in described text library, search the common hypernym that described content summary and described content add the above adeditive attribute, and obtain distance C 2 between the described common hypernym, if C2 is greater than second threshold value, then it fails to match; If C2 is not more than second threshold value, then execution in step 136;
Step 136: the prediction scheme reference value of calculating the cooresponding prediction scheme of qualified content summary;
Step 137: the described prediction scheme reference value of all that will calculate compares and selects the cooresponding prediction scheme of maximum prediction scheme reference value as the prediction scheme that the match is successful, and the match is successful, execution in step 2.
5. according to claim 3 or the 4 described methods of receiving a crime report automatically, it is characterized in that, calculate described prediction scheme reference value: RV=0.4*UR+0.6*PR according to following rule, wherein, RV is described prediction scheme reference value, and UR is the prediction scheme frequency of utilization, and PR is the accurate implementation rate of prediction scheme, UR=(summation of these prediction scheme access times/the type warning frequency) * 100%, PR=(this prediction scheme successful execution number of times/these prediction scheme access times) * 100%.
6. according to claim 3 or the 4 described methods of receiving a crime report automatically, it is characterized in that described first threshold is 8.
7. according to claim 3 or the 4 described methods of receiving a crime report automatically, it is characterized in that described second threshold value is 5.
8. according to claim 3 or the 4 described methods of receiving a crime report automatically, it is characterized in that described the 3rd threshold value is 2.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN 201110195130 CN102248955B (en) | 2011-05-25 | 2011-07-13 | Automatic alarm receiving method |
Applications Claiming Priority (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201110136314 | 2011-05-25 | ||
CN201110136314.0 | 2011-05-25 | ||
CN 201110195130 CN102248955B (en) | 2011-05-25 | 2011-07-13 | Automatic alarm receiving method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN102248955A true CN102248955A (en) | 2011-11-23 |
CN102248955B CN102248955B (en) | 2013-02-13 |
Family
ID=44976613
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN 201110195130 Active CN102248955B (en) | 2011-05-25 | 2011-07-13 | Automatic alarm receiving method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102248955B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106155055A (en) * | 2016-07-13 | 2016-11-23 | 百度在线网络技术(北京)有限公司 | Method for early warning and device for automatic driving vehicle |
CN106274991A (en) * | 2016-08-23 | 2017-01-04 | 四川网达科技有限公司 | Railway fail analysis device and method |
CN110275992A (en) * | 2019-05-17 | 2019-09-24 | 阿里巴巴集团控股有限公司 | Emergency processing method, device, server and computer readable storage medium |
CN117572808A (en) * | 2024-01-15 | 2024-02-20 | 埃睿迪信息技术(北京)有限公司 | Equipment monitoring method, device and equipment |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101383027A (en) * | 2008-09-12 | 2009-03-11 | 同济大学 | Environmental emergency scheme generating method and system |
CN201319224Y (en) * | 2008-12-09 | 2009-09-30 | 广州市地下铁道总公司 | Simulation system for subway signal fault simulation rehearsal |
US20090282272A1 (en) * | 2008-05-08 | 2009-11-12 | Bestgen Robert J | Organizing Databases for Energy Efficiency |
CN102013083A (en) * | 2010-12-01 | 2011-04-13 | 深圳市天维尔通讯技术有限公司 | Method and system for generating emergency action plan based on pre-arranged plan |
-
2011
- 2011-07-13 CN CN 201110195130 patent/CN102248955B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090282272A1 (en) * | 2008-05-08 | 2009-11-12 | Bestgen Robert J | Organizing Databases for Energy Efficiency |
CN101383027A (en) * | 2008-09-12 | 2009-03-11 | 同济大学 | Environmental emergency scheme generating method and system |
CN201319224Y (en) * | 2008-12-09 | 2009-09-30 | 广州市地下铁道总公司 | Simulation system for subway signal fault simulation rehearsal |
CN102013083A (en) * | 2010-12-01 | 2011-04-13 | 深圳市天维尔通讯技术有限公司 | Method and system for generating emergency action plan based on pre-arranged plan |
Non-Patent Citations (2)
Title |
---|
《计算机时代》 20101231 杨珍珍 等 "基于小波变换和模糊聚类分析的交通事件信息发布系统的设计" 53-54 1-8 , 第10期 * |
杨珍珍 等: ""基于小波变换和模糊聚类分析的交通事件信息发布系统的设计"", 《计算机时代》 * |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106155055A (en) * | 2016-07-13 | 2016-11-23 | 百度在线网络技术(北京)有限公司 | Method for early warning and device for automatic driving vehicle |
CN106155055B (en) * | 2016-07-13 | 2019-05-24 | 百度在线网络技术(北京)有限公司 | Method for early warning and device for automatic driving vehicle |
CN106274991A (en) * | 2016-08-23 | 2017-01-04 | 四川网达科技有限公司 | Railway fail analysis device and method |
CN110275992A (en) * | 2019-05-17 | 2019-09-24 | 阿里巴巴集团控股有限公司 | Emergency processing method, device, server and computer readable storage medium |
CN110275992B (en) * | 2019-05-17 | 2023-08-29 | 创新先进技术有限公司 | Emergency processing method, device, server and computer readable storage medium |
CN117572808A (en) * | 2024-01-15 | 2024-02-20 | 埃睿迪信息技术(北京)有限公司 | Equipment monitoring method, device and equipment |
Also Published As
Publication number | Publication date |
---|---|
CN102248955B (en) | 2013-02-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10705863B2 (en) | IoT based method and system for processing information | |
CN113553420B (en) | Power grid fault processing rule recommendation method and system based on knowledge graph | |
CN102248955B (en) | Automatic alarm receiving method | |
CN111435366A (en) | Equipment fault diagnosis method and device and electronic equipment | |
CN112650848A (en) | Urban railway public opinion information analysis method based on text semantic related passenger evaluation | |
CN104091070A (en) | Rail transit fault diagnosis method and system based on time series analysis | |
CN103760901A (en) | Rail transit fault identification method based on association rule classifier | |
CN111209472B (en) | Railway accident fault association and accident fault cause analysis method and system | |
CN101986296A (en) | Noise data cleaning method based on semantic ontology | |
CN107340766A (en) | Power scheduling alarm signal text based on similarity sorts out and method for diagnosing faults | |
CN108803559A (en) | Vehicle trouble analysis method, device and system | |
CN112433759A (en) | Standardized maintenance terminal for train control center system and implementation method thereof | |
JP2015027229A (en) | Train operation ai system and train operation fault restoration assist method | |
CN105357118A (en) | Rule based flow classifying method and system | |
JP6630139B2 (en) | Text data processing device, coded broadcast display system, and coded broadcast display program | |
CN117041269A (en) | Real-time bidirectional synchronization system for synchronizing sub-database data | |
CN109508244B (en) | Data processing method and computer readable medium | |
JP2003505770A (en) | Method for forming and / or updating a dictionary for automatic address reading | |
CN114157553B (en) | Data processing method, device, equipment and storage medium | |
CN110688457A (en) | Steam-massage industry text information input method based on identification analysis | |
CN103945422B (en) | A kind of method and apparatus being controlled to work order | |
CN113703417B (en) | Method and device for determining test cases of full-automatic scene of train operation | |
CN112801537B (en) | Non-stop accident analysis method, system, medium and equipment for power generation enterprise | |
CN114896482A (en) | Model training and energy supplementing intention recognition method, device, equipment and medium | |
CN111585664B (en) | Transponder active message checking system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
C56 | Change in the name or address of the patentee | ||
CP03 | Change of name, title or address |
Address after: 215153, Qingcheng Mountain Road, hi tech Zone, Jiangsu, Suzhou, 350 Patentee after: Suzhou Boyuan Rongtian information Polytron Technologies Inc Address before: Kolding road high tech Zone of Suzhou City, Jiangsu province 215163 No. 2 Su Gaoxin Software Park 4 Building 4 layer Patentee before: Suzhou Boyuan Rongtian Information Technology Co.,Ltd. |