CN115358721B - Engineering supervision information supervision system and method based on big data - Google Patents
Engineering supervision information supervision system and method based on big data Download PDFInfo
- Publication number
- CN115358721B CN115358721B CN202211058255.4A CN202211058255A CN115358721B CN 115358721 B CN115358721 B CN 115358721B CN 202211058255 A CN202211058255 A CN 202211058255A CN 115358721 B CN115358721 B CN 115358721B
- Authority
- CN
- China
- Prior art keywords
- link
- implementation
- association
- condition
- early warning
- 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.)
- Active
Links
Images
Classifications
-
- 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
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/194—Calculation of difference between files
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B31/00—Predictive alarm systems characterised by extrapolation or other computation using updated historic data
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Entrepreneurship & Innovation (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Artificial Intelligence (AREA)
- Emergency Management (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention relates to the field of engineering supervision, in particular to an engineering supervision information supervision system and method based on big data, comprising a history supervision procedure acquisition module, a direct association link analysis and establishment module, a condition association link analysis and establishment module, a first time early warning model establishment module, a second time early warning module establishment module and an early warning response module; the history establishing procedure obtaining module obtains a history supervision procedure of an engineering supervision corresponding project; the direct link analysis and establishment module establishes a direct link corresponding to the implementation link; the condition association link analysis and establishment module is used for establishing a corresponding condition association link; the first time early warning model building module is used for building a first time early warning model; the second time early warning module building module is used for building a second time early warning model of the condition association link according to the condition association link analysis signal generated by the first time early warning model; the early warning response module is used for responding to the early warning signal.
Description
Technical Field
The invention relates to the technical field of engineering supervision information supervision, in particular to an engineering supervision information supervision system and method based on big data.
Background
The project supervision refers to the commission of the supervision unit with relevant qualification by the first party, and represents a specialized service activity of monitoring the project construction of the second party by the first party according to the project construction files approved by the country, laws and regulations related to the project construction, the project construction supervision contracts and other project construction contracts;
the main responsibilities of the current engineering supervision comprise supervision on the engineering progress and supervision on the engineering quality, and there are many situations on the engineering progress, such as serious hysteresis problem of engineering caused by abnormal events, direct influence of the occurrence link of the abnormal events on the next link with aging problem, etc., which are difficult problems in the engineering progress supervision process, because the information data are numerous in the engineering supervision process, and the effective data cannot be rapidly extracted for integrated analysis to cause disorder of progress when the abnormal events occur.
Disclosure of Invention
The invention aims to provide an engineering supervision information supervision system and method based on big data, so as to solve the problems in the background technology.
In order to solve the technical problems, the invention provides the following technical scheme: the engineering supervision information supervision method based on big data comprises the following steps:
step S1: the method comprises the steps of acquiring a history supervision procedure of an engineering supervision corresponding project, wherein the supervision procedure refers to an entire supervision procedure formed by different implementation procedures according to a set sequence, and the implementation procedure refers to a procedure formed by different implementation links according to the set sequence;
step S2: analyzing and establishing a direct link and a condition link corresponding to the implementation link;
step S3: judging the relation between an implementation link to which an abnormal event belongs and a direct association link in a real-time supervision process, establishing a first time early warning model based on the body processing time length and the maximum interval time length in the historical data, and outputting signals, wherein the signals comprise early warning signals and association influence time length analysis signals corresponding to the condition association links;
step S4: based on the association influence time length analysis signal corresponding to the condition association link in the step S3, judging the relation between the implementation link to which the abnormal event belongs and the condition association link in the real-time supervision process, and based on the initial plan supervision time length and the association influence time length, establishing a second time early warning model corresponding to the condition association link; the initial plan supervision time length comprises the supervision time length of an implemented link and the estimated routine establishment time length of an unemployed link which are supervised in real time;
step S5: based on the second time early warning model, acquiring a total duration threshold of the estimated engineering supervision, calculating a difference value between the second time early warning model and the total duration threshold, carrying out time early warning on all condition-related links if the difference value is greater than or equal to a preset difference value threshold, and continuing supervision if the difference value is smaller than the preset difference value threshold.
Further, step S2 includes the steps of:
acquiring end project information of an implementation link, wherein the implementation link is a main body implementation link, the end project information refers to non-independent information and independent information contained in the last step of the main body implementation link, the non-independent information refers to information with information similarity between the last step and other steps in the main body implementation link, and the independent information refers to information with zero information similarity between the last step and other steps in the main body implementation link;
marking independent information and acquiring a next implementation link of a preset sequence of the implementation links of the subject, wherein the next implementation link is an object implementation link to be analyzed; analyzing whether marked independent information exists in the object implementation link to be analyzed as a first judgment requirement, and analyzing the sequence relation between the starting time of the object implementation link to be analyzed and the ending time of the host implementation link as a second judgment requirement;
when the first judgment requirement is that the object implementation link has marked independent information, and the starting time of the object implementation link to be analyzed in the second judgment requirement is after the ending time of the subject implementation link, outputting the object implementation link to be analyzed as a direct association link. Because there is established process sequence in the engineering supervision process, the analysis of the direct association links is to judge whether the direct association links of a certain link are affected when the abnormality occurs in the certain link in terms of time schedule, the current effect means that the associated links cannot be started due to abnormal time, and the associated links have timeliness problems in the whole engineering, if the current effect is caused at this time, the early warning can be directly performed, the real-time accuracy and the high efficiency of the engineering supervision are improved, and if the time schedule effect is not caused on the direct association links, the whole schedule effect is further analyzed.
Further, step S2 further includes the following steps:
the condition association links comprise a first condition association link and a second condition association link;
obtaining the subject information of the subject implementation links in the supervision process, extracting keywords in the subject information as first keywords, enabling subsequent implementation links of the subject implementation links to be object implementation links to be processed, extracting keywords in the subject information in the object implementation links to be processed as second keywords, and recording the object implementation links to be processed, wherein the similarity of the second keywords and the first keywords is greater than or equal to a similarity threshold value, as target object implementation links;
if the target object implementation links are one and only one, enabling the target object implementation links to be first condition association links;
if the number of the target object implementation links is not one, recording the target object implementation links as second condition association links; calculating link association degree Y of a second condition association link, wherein Y=n/N, N represents the number of the same signers in a target object implementation link and a subject implementation link of the electronic signature record in the engineering supervision, and N represents the number of total signers in the target object implementation link and the subject implementation link of the electronic signature record in the engineering supervision; the condition of applying the electronic signature in the engineering supervision process relates to aspects, the electronic signature brings great convenience to the engineering supervision, and meanwhile, the signing condition of responsible personnel in each link can be recorded clearly, so that the relevant information of the electronic signature is extracted, and the data is direct, effective and clear;
and sorting the second condition association links from large to small according to the magnitude of the value of the association degree of the corresponding links to obtain a second condition association link sequence.
Further, step S3 includes the steps of:
acquiring an abnormal implementation link in the real-time supervision engineering, enabling the implementation link to be a synchronous main body implementation link, and judging whether the synchronous main body implementation link has a direct correlation link or not;
if a direct association link exists, acquiring the body processing time T1 of the abnormal event required by the synchronous main body implementation link and the maximum interval time T1 of the direct association link starting supervision in the corresponding historical data of the synchronous main body implementation link, wherein the interval time is the time interval between the ending time of the main body implementation link and the starting time of the direct association link under the condition that the abnormal event does not occur in the historical data;
establishing a first time early warning model X1 = { T1 is more than or equal to T1, and T1 is less than T1};
if x1=t1 is more than or equal to T1, outputting an early warning signal; the maximum interval time indicates the time length left in two adjacent links in the historical data, and once the time length increased by the abnormal time to be processed is longer than the interval time length, starting abnormality of the next link is caused, and then early warning can improve the real-time accuracy of the engineering supervision progress;
if x1=t1 < T1, analyzing the association influence duration corresponding to the condition association link;
if no direct association link exists, the association influence duration corresponding to the condition association link is analyzed. When the analyzed direct association link meets the condition for generating early warning, the applicability of the analysis on the abnormal event is improved, namely, the risk caused by the abnormal event can be early warned after the abnormal event occurs, and if the direct association link does not meet the early warning condition, the condition association link is analyzed so as to improve the controllability of the overall progress of engineering supervision;
further, the step S4 includes the following specific steps:
when the condition association link is a first condition association link, acquiring average association influence time length h1 of the corresponding first condition association link in the historical data; then a second time early warning model x2a= Σui+Σvj+t1+h1 is established, wherein ui represents the supervision duration of the ith implemented link, vj represents the predicted regular supervision duration of the jth unemplemented link; the conventional supervision time length represents the time length of no abnormal event in the implementation link;
when the condition association link is a second condition association link, acquiring a k-th historical average association influence time length h2k corresponding to a second condition association link sequence in the historical data, and sequencing the historical average association influence time length h2k from large to small to obtain a corresponding historical second condition association link sequence;
if the historical second condition association link sequence is identical to the second condition association link sequence, a second time early warning model X2b is built; the analysis of the condition association links is to verify the analyzability and effectiveness of links of abnormal events in the historical data on the influence time of other association links, because the association degree is based on link content, if the influence time relationship and the condition association links corresponding to the association degree have the same sequence, the analysis of the estimation on the influence time of the condition association links can be performed according to the association degree;
if the historical second condition association link sequence is not identical to the second condition association link sequence, extracting second condition association links with different corresponding links at the same position, and establishing a second time early warning model X2c= Σui+ Σvj+ Σh3k+t1, wherein h3k represents the maximum value of the influence duration of the k-th historical association corresponding to the second condition association link sequence in the historical data. When the sequences are not identical, the maximum value is extracted as a calculation condition, because the time influence caused by the abnormal event is irregular at the moment, and the progress of the engineering project is ensured not to be towered only based on the maximum value in the historical big data as a risk early warning value; after the whole progress is analyzed for early warning, supervision can be carried out on the affected links and the condition association links can be processed for early abnormal measures so as to prevent serious delay of the engineering progress, the condition association links also possibly comprise direct association links, the direct association links early warn the influence caused by the progress of the next link, and the condition association links are early warning responses to the total progress.
Further, the engineering supervision information supervision system based on big data comprises a history supervision procedure acquisition module, a direct association link analysis and establishment module, a condition association link analysis and establishment module, a first time early warning model establishment module, a second time early warning module establishment module and an early warning response module;
the history establishing procedure obtaining module is used for obtaining a history supervision procedure of the project corresponding to the engineering supervision; the supervision step is the whole supervision step composed of different implementation steps according to a predetermined sequence, and the implementation step is the step composed of different implementation links according to a predetermined sequence;
the direct link analysis and establishment module is used for establishing a direct link corresponding to the implementation link;
the condition association link analysis and establishment module is used for establishing a condition association link corresponding to the implementation link;
the first time early warning model building module is used for obtaining the body processing time length and the maximum interval time length in the historical data according to the direct association link and building a first time early warning model;
the second time early warning module building module is used for analyzing signals according to the condition association links generated by the first time early warning module, acquiring initial plan supervision time length and association influence time length, and building a second time early warning module corresponding to the condition association links;
the early warning response module is used for responding to early warning signals of the first time early warning model and the second time early warning model.
Further, the direct association link analysis and establishment module comprises a main body implementation link determination unit, an end-of-project information acquisition unit and a judgment requirement analysis unit;
the main body implementation link determining unit is used for determining main body implementation links;
the ending point information acquisition unit is used for acquiring ending point information in the main body implementation link, wherein the ending point information refers to non-independent information and independent information contained in the last step of the main body implementation link, the non-independent information refers to information with information similarity between the last step and other steps in the main body implementation link, and the independent information refers to information with zero information similarity between the last step and other steps in the main body implementation link;
the judgment requirement analysis unit is used for determining a first judgment requirement and a second judgment requirement and outputting an implementation link which simultaneously meets the first judgment requirement and the second judgment requirement as a direct correlation link.
Further, the condition association link analysis and establishment module comprises a target object implementation link determination unit, a first condition association link determination unit, a second condition association link determination unit and a link association degree analysis unit;
the target object implementation link determining unit is used for determining a target object implementation link according to the keyword similarity;
the first condition association link determining unit is used for determining a first condition association link when analyzing that one object implementation link exists and only one object implementation link exists;
the second condition association link determining unit is used for determining that the target object implementation links with the number of the target object implementation links not being one are second condition association links;
the link association degree analysis unit is used for analyzing the link association degree of the second condition association link and obtaining a second condition association link sequence.
Further, the first time early warning model building module comprises a relation judging unit and a first time early warning model analyzing unit;
the relation judging unit is used for judging whether a direct link exists in the abnormal implementation link or not;
the first time early warning model analysis unit establishes an early warning model and sets judgment conditions when the direct link condition exists, and outputs signals according to the judgment conditions; and further analyzing the condition association link when the condition of the direct association link does not exist.
Further, the second time early warning model building module comprises a type judging unit and a second time early warning model analyzing unit;
the type judging unit is used for judging the type association link to which the condition association link belongs;
the second time early warning model analysis unit is used for analyzing a second time early warning model of the corresponding type of the association link.
Compared with the prior art, the invention has the following beneficial effects: according to the method, the direct association link and the condition association link of the link to which the abnormal event belongs are analyzed, the first time early warning model corresponding to the direct association link and the second time early warning model corresponding to the condition association link are respectively established, the conditions are distinguished when the condition association link is analyzed, so that the accuracy of time early warning is improved, meanwhile, the real-time early warning of the direct influence of the abnormal event generation link on the next link with the aging problem is solved, the problem that the engineering is seriously lagged due to the analysis of the abnormal event based on the whole progress is solved, and the effective control of the time progress in the engineering supervision process is greatly improved.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a schematic diagram of a big data based engineering supervision information supervision system;
fig. 2 is a process flow diagram of a supervision engineering of the engineering supervision information supervision method based on big data.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1-2, the present invention provides the following technical solutions: the engineering supervision information supervision method based on big data comprises the following steps:
step S1: the method comprises the steps of acquiring a history supervision procedure of an engineering supervision corresponding project, wherein the supervision procedure refers to an entire supervision procedure formed by different implementation procedures according to a set sequence, and the implementation procedure refers to a procedure formed by different implementation links according to the set sequence; the frame main body engineering supervision step shown in fig. 2 includes an implementation step of ABCDEF and implementation links A1, A2, B1, B2, and Fn corresponding to the implementation step; the procedure shows the overall summary of the construction content and shows the sequence, and the links under the procedure show the specific implementation content in engineering supervision;
step S2: analyzing and establishing a direct link and a condition link corresponding to the implementation link;
step S3: judging the relation between an implementation link to which an abnormal event belongs and a direct association link in a real-time supervision process, establishing a first time early warning model based on the body processing time length and the maximum interval time length in the historical data, and outputting signals, wherein the signals comprise early warning signals and association influence time length analysis signals corresponding to the condition association links;
step S4: based on the association influence time length analysis signal corresponding to the condition association link in the step S3, judging the relation between the implementation link to which the abnormal event belongs and the condition association link in the real-time supervision process, and based on the initial plan supervision time length and the association influence time length, establishing a second time early warning model corresponding to the condition association link; the initial plan supervision time length comprises the supervision time length of an implemented link and the estimated routine establishment time length of an unemployed link which are supervised in real time;
step S5: based on the second time early warning model, acquiring a total duration threshold of the estimated engineering supervision, calculating a difference value between the second time early warning model and the total duration threshold, carrying out time early warning on all condition-related links if the difference value is greater than or equal to a preset difference value threshold, and continuing supervision if the difference value is smaller than the preset difference value threshold.
Step S2 comprises the steps of:
acquiring end project information of an implementation link, wherein the implementation link is a main body implementation link, the end project information refers to non-independent information and independent information contained in the last step of the main body implementation link, the non-independent information refers to information with information similarity between the last step and other steps in the main body implementation link, and the independent information refers to information with zero information similarity between the last step and other steps in the main body implementation link;
marking independent information and acquiring a next implementation link of a preset sequence of the implementation links of the subject, wherein the next implementation link is an object implementation link to be analyzed; analyzing whether marked independent information exists in the object implementation link to be analyzed as a first judgment requirement, and analyzing the sequence relation between the starting time of the object implementation link to be analyzed and the ending time of the host implementation link as a second judgment requirement;
when the first judgment requirement is that the object implementation link has marked independent information, and the starting time of the object implementation link to be analyzed in the second judgment requirement is after the ending time of the subject implementation link, outputting the object implementation link to be analyzed as a direct association link. Because there is established process sequence in the engineering supervision process, the analysis of the direct association links is to judge whether the direct association links of a certain link are affected when the abnormality occurs in the certain link in terms of time schedule, the current effect means that the associated links cannot be started due to abnormal time, and the associated links have timeliness problems in the whole engineering, if the current effect is caused at this time, the early warning can be directly performed, the real-time accuracy and the high efficiency of the engineering supervision are improved, and if the time schedule effect is not caused on the direct association links, the whole schedule effect is further analyzed.
Step S2 further comprises the steps of:
the condition association links comprise a first condition association link and a second condition association link;
obtaining the subject information of the subject implementation links in the supervision process, extracting keywords in the subject information as first keywords, enabling subsequent implementation links of the subject implementation links to be object implementation links to be processed, extracting keywords in the subject information in the object implementation links to be processed as second keywords, and recording the object implementation links to be processed, wherein the similarity of the second keywords and the first keywords is greater than or equal to a similarity threshold value, as target object implementation links;
if the target object implementation links are one and only one, enabling the target object implementation links to be first condition association links;
if the number of the target object implementation links is not one, recording the target object implementation links as second condition association links; calculating link association degree Y of a second condition association link, wherein Y=n/N, N represents the number of the same signers in a target object implementation link and a subject implementation link of the electronic signature record in the engineering supervision, and N represents the number of total signers in the target object implementation link and the subject implementation link of the electronic signature record in the engineering supervision; the condition of applying the electronic signature in the engineering supervision process relates to aspects, the electronic signature brings great convenience to the engineering supervision, and meanwhile, the signing condition of responsible personnel in each link can be recorded clearly, so that the relevant information of the electronic signature is extracted, and the data is direct, effective and clear;
and sorting the second condition association links from large to small according to the magnitude of the value of the association degree of the corresponding links to obtain a second condition association link sequence.
Step S3 comprises the steps of:
acquiring an abnormal implementation link in the real-time supervision engineering, enabling the implementation link to be a synchronous main body implementation link, and judging whether the synchronous main body implementation link has a direct correlation link or not;
if a direct association link exists, acquiring the body processing time T1 of the abnormal event required by the synchronous main body implementation link and the maximum interval time T1 of the direct association link starting supervision in the corresponding historical data of the synchronous main body implementation link, wherein the interval time is the time interval between the ending time of the main body implementation link and the starting time of the direct association link under the condition that the abnormal event does not occur in the historical data;
establishing a first time early warning model X1 = { T1 is more than or equal to T1, and T1 is less than T1};
if x1=t1 is more than or equal to T1, outputting an early warning signal; the maximum interval time indicates the time length left in two adjacent links in the historical data, and once the time length increased by the abnormal time to be processed is longer than the interval time length, starting abnormality of the next link is caused, and then early warning can improve the real-time accuracy of the engineering supervision progress; the body processing time length refers to the additional processing time length in the abnormal implementation link, so that the additional processing time length is equal to the delay time length on the basis of original engineering supervision; such as: the link A1 is an implementation link when the abnormality occurs, if the link A2 is judged to be a direct association link, the body processing time length is 26h, and the additional processing time length of the abnormal event is 26h; if the interval duration of the history starting supervision is 15h, 20h and 23h, the delay time of 26h exceeds the safety duration of the previous link of the interval required by the direct link, the direct influence on the direct link is caused, and an early warning signal is output.
If x1=t1 < T1, analyzing the association influence duration corresponding to the condition association link;
if no direct association link exists, the association influence duration corresponding to the condition association link is analyzed. When the analyzed direct association link meets the condition for generating early warning, the applicability of the analysis on the abnormal event is improved, namely, the risk caused by the abnormal event can be early warned after the abnormal event occurs, and if the direct association link does not meet the early warning condition, the condition association link is analyzed so as to improve the controllability of the overall progress of engineering supervision;
step S4 comprises the following specific steps:
when the condition association link is a first condition association link, acquiring average association influence time length h1 of the corresponding first condition association link in the historical data; then a second time early warning model x2a= Σui+Σvj+t1+h1 is established, wherein ui represents the supervision duration of the ith implemented link, vj represents the predicted regular supervision duration of the jth unemplemented link; the conventional supervision time length represents the time length of no abnormal event in the implementation link;
when the condition association link is a second condition association link, acquiring a k-th historical average association influence time length h2k corresponding to a second condition association link sequence in the historical data, and sequencing the historical average association influence time length h2k from large to small to obtain a corresponding historical second condition association link sequence;
if the historical second condition association link sequence is identical to the second condition association link sequence, a second time early warning model X2b is built; the analysis of the condition association links is to verify the analyzability and effectiveness of links of abnormal events in the historical data on the influence time of other association links, because the association degree is based on link content, if the influence time relationship and the condition association links corresponding to the association degree have the same sequence, the analysis of the estimation on the influence time of the condition association links can be performed according to the association degree;
if the historical second condition association link sequence is not identical to the second condition association link sequence, extracting second condition association links with different corresponding links at the same position, and establishing a second time early warning model X2c= Σui+ Σvj+ Σh3k+t1, wherein h3k represents the maximum value of the influence duration of the k-th historical association corresponding to the second condition association link sequence in the historical data. When the sequences are not identical, the maximum value is extracted as a calculation condition, because the time influence caused by the abnormal event is irregular at the moment, and the progress of the engineering project is ensured not to be towered only based on the maximum value in the historical big data as a risk early warning value; after the whole progress is analyzed for early warning, supervision can be carried out on the affected links and the condition association links can be processed for early abnormal measures so as to prevent serious delay of the engineering progress, the condition association links also possibly comprise direct association links, the direct association links early warn the influence caused by the progress of the next link, and the condition association links are early warning responses to the total progress.
The engineering supervision information supervision system based on big data comprises a history supervision procedure acquisition module, a direct association link analysis and establishment module, a condition association link analysis and establishment module, a first time early warning model establishment module, a second time early warning module establishment module and an early warning response module;
the history establishing procedure obtaining module is used for obtaining a history supervision procedure of the project corresponding to the engineering supervision; the supervision step is the whole supervision step composed of different implementation steps according to a predetermined sequence, and the implementation step is the step composed of different implementation links according to a predetermined sequence;
the direct link analysis and establishment module is used for establishing a direct link corresponding to the implementation link;
the condition association link analysis and establishment module is used for establishing a condition association link corresponding to the implementation link;
the first time early warning model building module is used for obtaining the body processing time length and the maximum interval time length in the historical data according to the direct association link and building a first time early warning model;
the second time early warning module building module is used for analyzing signals according to the condition association links generated by the first time early warning module, acquiring initial plan supervision time length and association influence time length, and building a second time early warning module corresponding to the condition association links;
the early warning response module is used for responding to early warning signals of the first time early warning model and the second time early warning model.
The direct association link analysis and establishment module comprises a main body implementation link determination unit, an end-of-range information acquisition unit and a judgment requirement analysis unit;
the main body implementation link determining unit is used for determining main body implementation links;
the ending point information acquisition unit is used for acquiring ending point information in the main body implementation link, wherein the ending point information refers to non-independent information and independent information contained in the last step of the main body implementation link, the non-independent information refers to information with information similarity between the last step and other steps in the main body implementation link, and the independent information refers to information with zero information similarity between the last step and other steps in the main body implementation link;
the judgment requirement analysis unit is used for determining a first judgment requirement and a second judgment requirement and outputting an implementation link which simultaneously meets the first judgment requirement and the second judgment requirement as a direct correlation link.
The condition association link analysis and establishment module comprises a target object implementation link determination unit, a first condition association link determination unit, a second condition association link determination unit and a link association degree analysis unit;
the target object implementation link determining unit is used for determining a target object implementation link according to the keyword similarity;
the first condition association link determining unit is used for determining a first condition association link when analyzing that one object implementation link exists and only one object implementation link exists;
the second condition association link determining unit is used for determining that the target object implementation links with the number of the target object implementation links not being one are second condition association links;
the link association degree analysis unit is used for analyzing the link association degree of the second condition association link and obtaining a second condition association link sequence.
The first time early warning model building module comprises a relation judging unit and a first time early warning model analyzing unit;
the relation judging unit is used for judging whether a direct link exists in the abnormal implementation link or not;
the first time early warning model analysis unit establishes an early warning model and sets judgment conditions when the direct link condition exists, and outputs signals according to the judgment conditions; and further analyzing the condition association link when the condition of the direct association link does not exist.
The second time early warning model building module comprises a type judging unit and a second time early warning model analyzing unit;
the type judging unit is used for judging the type association link to which the condition association link belongs;
the second time early warning model analysis unit is used for analyzing a second time early warning model of the corresponding type of the association link.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Finally, it should be noted that: the foregoing description is only a preferred embodiment of the present invention, and the present invention is not limited thereto, but it is to be understood that modifications and equivalents of some of the technical features described in the foregoing embodiments may be made by those skilled in the art, although the present invention has been described in detail with reference to the foregoing embodiments. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (6)
1. The engineering supervision information supervision method based on big data is characterized by comprising the following steps of:
step S1: the method comprises the steps of acquiring a history supervision procedure of an engineering supervision corresponding project, wherein the supervision procedure refers to an entire supervision procedure formed by different implementation procedures according to a set sequence, and the implementation procedure refers to a procedure formed by different implementation links according to the set sequence;
step S2: analyzing and establishing a direct link and a condition link corresponding to the implementation link;
the step S2 includes the steps of:
acquiring end condition information of an implementation link, wherein the implementation link is made to be a main body implementation link, the end condition information refers to non-independent information and independent information contained in a final step of the main body implementation link, the non-independent information is information with information similarity between the final step and other steps in the main body implementation link, and the independent information is information with zero information similarity between the final step and other steps in the main body implementation link;
marking independent information and acquiring a next implementation link of a preset sequence of the implementation links of the subject, wherein the next implementation link is an object implementation link to be analyzed; analyzing whether marked independent information exists in the object implementation link to be analyzed as a first judgment requirement, and analyzing the sequence relation between the starting time of the object implementation link to be analyzed and the ending time of the host implementation link as a second judgment requirement;
outputting the object implementation link to be analyzed as a direct association link when the first judgment requirement is that the marked independent information exists in the object implementation link and the starting time of the object implementation link to be analyzed in the second judgment requirement is after the ending time of the subject implementation link;
the step S2 further includes the steps of:
the condition association links comprise a first condition association link and a second condition association link;
obtaining the subject information of the subject implementation links in the supervision process, extracting keywords in the subject information as first keywords, enabling subsequent implementation links of the subject implementation links to be object implementation links to be processed, extracting keywords in the subject information in the object implementation links to be processed as second keywords, and recording the object implementation links to be processed, wherein the similarity of the second keywords and the first keywords is greater than or equal to a similarity threshold value, as target object implementation links;
if the number of the target object implementation links is one, enabling the target object implementation links to be first condition association links;
if the number of the target object implementation links is not one, recording the target object implementation links as second condition association links; calculating link association degree Y of a second condition association link, wherein Y=n/N, N represents the number of the same signers in a target object implementation link and a subject implementation link of the electronic signature record in the engineering supervision, and N represents the number of total signers in the target object implementation link and the subject implementation link of the electronic signature record in the engineering supervision;
sorting the second condition association links from large to small according to the magnitude of the value of the association degree of the corresponding links to obtain a second condition association link sequence;
step S3: judging the relation between an implementation link to which an abnormal event belongs and a direct association link in a real-time supervision process, establishing a first time early warning model based on the body processing time length and the maximum interval time length in historical data, and outputting signals, wherein the signals comprise early warning signals and association influence time length analysis signals corresponding to condition association links;
step S4: based on the association influence time length analysis signal corresponding to the condition association link in the step S3, judging the relation between the implementation link to which the abnormal event belongs and the condition association link in the real-time supervision process, and based on the initial plan supervision time length and the association influence time length, establishing a second time early warning model corresponding to the condition association link; the initial plan supervision time length comprises the supervision time length of an implemented link and the estimated routine establishment time length of an unemployed link which are supervised in real time;
step S5: based on the second time early warning model, acquiring a total duration threshold of the estimated engineering supervision, calculating a difference value between the second time early warning model and the total duration threshold, carrying out time early warning on all condition-related links if the difference value is greater than or equal to a preset difference value threshold, and continuing supervision if the difference value is smaller than the preset difference value threshold.
2. The big data-based engineering supervision information supervision method according to claim 1, wherein the method comprises the following steps: the step S3 includes the steps of:
acquiring an abnormal implementation link in a real-time supervision project, enabling the implementation link to be a synchronous main body implementation link, and judging whether the synchronous main body implementation link has a direct association link or not;
if a direct association link exists, acquiring a body processing time T1 for processing an abnormal event required by the implementation link of the synchronous main body and a maximum interval time T1 for starting supervision of the direct association link in the corresponding historical data of the implementation link of the synchronous main body, wherein the interval time is a time interval between the ending time of the implementation link of the main body and the starting time of the direct association link under the condition that no abnormal event occurs in the historical data;
establishing a first time early warning model X1 = { T1 is more than or equal to T1, and T1 is less than T1};
if x1=t1 is more than or equal to T1, outputting an early warning signal;
if x1=t1 < T1, analyzing the association influence duration corresponding to the condition association link;
if no direct association link exists, the association influence duration corresponding to the condition association link is analyzed.
3. The engineering supervision information supervision method based on big data according to claim 2, wherein: the step S4 comprises the following specific steps:
when the condition association link is a first condition association link, acquiring average association influence time length h1 of the corresponding first condition association link in the historical data; then a second time early warning model x2a= Σui+Σvj+t1+h1 is established, wherein ui represents the supervision duration of the ith implemented link, vj represents the predicted regular supervision duration of the jth unemplemented link; the conventional supervision time length represents the time length of no abnormal event in the implementation link;
when the condition association link is a second condition association link, acquiring a k-th historical average association influence time length h2k corresponding to a second condition association link sequence in the historical data, and sequencing the historical average association influence time length h2k from large to small to obtain a corresponding historical second condition association link sequence;
if the historical second condition association link sequence is identical to the second condition association link sequence, a second time early warning model X2b is built;
if the historical second condition association link sequence is not identical to the second condition association link sequence, extracting second condition association links with different corresponding links at the same position, and establishing a second time early warning model X2c= Σui+ Σvj+ Σh3k+t1, wherein h3k represents the maximum value of the influence duration of the k-th historical association corresponding to the second condition association link sequence in the historical data.
4. A big data-based engineering supervision information supervision system applying the big data-based engineering supervision information supervision method according to any one of claims 1 to 3, which is characterized by comprising a history supervision procedure acquisition module, a direct association link analysis establishment module, a condition association link analysis establishment module, a first time early warning model establishment module, a second time early warning module establishment module and an early warning response module;
the history establishing procedure obtaining module is used for obtaining a history supervision procedure of an engineering supervision corresponding project; the supervision process is an entire supervision process composed of different implementation processes according to a predetermined sequence, and the implementation processes are processes composed of different implementation links according to the predetermined sequence;
the direct link analysis and establishment module is used for establishing a direct link corresponding to the implementation link;
the direct association link analysis and establishment module comprises a main body implementation link determination unit, an end-of-process information acquisition unit and a judgment requirement analysis unit;
the main body implementation link determining unit is used for determining main body implementation links;
the ending point information obtaining unit is used for obtaining ending point information in the main body implementation link, wherein the ending point information refers to non-independent information and independent information contained in the last step of the main body implementation link, the non-independent information is information with information similarity between the last step and other steps in the main body implementation link, and the independent information is information with zero information similarity between the last step and other steps in the main body implementation link;
the judging requirement analysis unit is used for determining a first judging requirement and a second judging requirement and outputting an implementation link which simultaneously meets the first judging requirement and the second judging requirement as a direct association link;
the condition association link analysis and establishment module is used for establishing a condition association link corresponding to the implementation link;
the condition association link analysis and establishment module comprises a target object implementation link determination unit, a first condition association link determination unit, a second condition association link determination unit and a link association degree analysis unit;
the target object implementation link determining unit is used for determining a target object implementation link according to the keyword similarity;
the first condition association link determining unit is used for determining a first condition association link when analyzing that only one target object implements links;
the second condition association link determining unit is configured to determine that the target object implementation links whose number of target object implementation links is not one are second condition association links;
the link association degree analysis unit is used for analyzing the link association degree of the second condition association link and obtaining a second condition association link sequence;
the first time early warning model building module is used for obtaining the body processing time length and the maximum interval time length in the historical data according to the direct association link and building a first time early warning model;
the second time early warning module building module is used for analyzing signals according to the condition association links generated by the first time early warning module, acquiring initial plan supervision time length and association influence time length, and building a second time early warning module corresponding to the condition association links;
the early warning response module is used for responding to early warning signals of the first time early warning model and the second time early warning model.
5. The big data based engineering supervision information management system according to claim 4, wherein: the first time early warning model building module comprises a relation judging unit and a first time early warning model analyzing unit;
the relation judging unit is used for judging whether a direct link exists in the abnormal implementation link or not;
the first time early warning model analysis unit establishes an early warning model and sets judgment conditions when a direct link condition exists, and outputs signals according to the judgment conditions; and further analyzing the condition association link when the condition of the direct association link does not exist.
6. The big data based engineering supervision information management system according to claim 5, wherein: the second time early warning model building module comprises a type judging unit and a second time early warning model analyzing unit;
the type judging unit is used for judging the type association link to which the condition association link belongs;
the second time early warning model analysis unit is used for analyzing a second time early warning model of the corresponding type of the association link.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211058255.4A CN115358721B (en) | 2022-08-30 | 2022-08-30 | Engineering supervision information supervision system and method based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211058255.4A CN115358721B (en) | 2022-08-30 | 2022-08-30 | Engineering supervision information supervision system and method based on big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115358721A CN115358721A (en) | 2022-11-18 |
| CN115358721B true CN115358721B (en) | 2023-05-23 |
Family
ID=84004653
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211058255.4A Active CN115358721B (en) | 2022-08-30 | 2022-08-30 | Engineering supervision information supervision system and method based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115358721B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116233902B (en) * | 2023-03-10 | 2023-09-08 | 西安航空学院 | Wireless communication network anomaly identification system and method based on big data |
| CN116109042B (en) * | 2023-04-12 | 2023-07-28 | 青岛荣泰新型房屋工程有限公司 | Engineering implementation visual management system and method based on BIM technology |
| CN116663875B (en) * | 2023-05-11 | 2024-01-30 | 广东恒域科技股份有限公司 | Intelligent installation engineering monitoring system and method based on big data |
| CN116822925B (en) * | 2023-06-26 | 2023-12-19 | 中咨海外咨询有限公司 | Engineering project management system |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112734394A (en) * | 2021-01-18 | 2021-04-30 | 吴杰胜 | Project supervision information management method based on Internet of things |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000048073A (en) * | 1998-07-30 | 2000-02-18 | Hitachi Ltd | Device and system for aiding determination of intention at the time of disaster, for which time management rule for measure is considered |
| JP6627842B2 (en) * | 2017-10-18 | 2020-01-08 | 日本電気株式会社 | Information processing apparatus, risk prediction method, and program |
| CN110347988B (en) * | 2019-07-03 | 2023-06-30 | 广东至衡工程管理有限公司 | Template building method and system for engineering supervision |
| CN110322147A (en) * | 2019-07-04 | 2019-10-11 | 四川元丰建设项目管理有限公司 | A kind of Project Supervision approaches to IM and system |
| CN111105070B (en) * | 2019-11-20 | 2024-04-16 | 深圳市北斗智能科技有限公司 | Passenger flow early warning method and system |
| CN112163747A (en) * | 2020-09-18 | 2021-01-01 | 华航环境发展有限公司 | Construction engineering project quality management system |
-
2022
- 2022-08-30 CN CN202211058255.4A patent/CN115358721B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112734394A (en) * | 2021-01-18 | 2021-04-30 | 吴杰胜 | Project supervision information management method based on Internet of things |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115358721A (en) | 2022-11-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115358721B (en) | Engineering supervision information supervision system and method based on big data | |
| CN110647539B (en) | Prediction method and system for vehicle faults | |
| CN111652496B (en) | Running risk assessment method and device based on network security situation awareness system | |
| CN106080655B (en) | A kind of detection method, device and the train of train axle temperature exception | |
| CN107832896B (en) | Power plant equipment slow-changing fault early warning method and device | |
| CN108446864B (en) | Big data analysis-based fault early warning system and method for rail transit equipment | |
| CN116071030B (en) | Electronic signature data access safety control system based on Internet | |
| CN110287827B (en) | Bridge strain data outlier identification method based on data correlation | |
| CN113269042B (en) | Intelligent traffic management method and system based on driving vehicle violation identification | |
| CN115865649B (en) | Intelligent operation and maintenance management control method, system and storage medium | |
| CN116305052B (en) | Electronic signature data real-time safety supervision system based on artificial intelligence | |
| CN110633905A (en) | Reliability calculation method for cloud platform of intelligent vehicle | |
| CN111506635A (en) | System and method for analyzing residential electricity consumption behavior based on autoregressive naive Bayes algorithm | |
| CN113269327A (en) | Flow anomaly prediction method based on machine learning | |
| CN115357418A (en) | Microservice fault detection method and device, storage medium and computer equipment | |
| CN117171694B (en) | Distribution scene safety identification system based on AI technology | |
| CN111354496A (en) | Nuclear power plant accident online diagnosis and state tracking prediction method | |
| CN117708637A (en) | Wind turbine generator blade fault diagnosis method based on improved k-means clustering analysis | |
| CN113591909A (en) | Abnormality detection method, abnormality detection device, and storage medium for power system | |
| CN117391357B (en) | Scheduling self-checking system for power grid scheduling operation management based on big data | |
| CN111160454B (en) | Quick change signal detection method and device | |
| CN108415401A (en) | A kind of engineering truck Measuring error data managing method and system | |
| WO2021217636A1 (en) | Industrial network behavior analysis method, apparatus and system, and computer-readable medium | |
| CN117972687B (en) | Block chain-based intelligent power monitoring system | |
| CN117055537B (en) | Motorcycle electric control system fault diagnosis method based on Internet of things |
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 |