Project intelligent monitoring method, system and device based on big data analysis

Abstract

The application discloses a project intelligent monitoring method, system and equipment based on big data analysis, and the method comprises the following steps: when a preset data integration time point is reached, integrating business data received from a business terminal to obtain corresponding project data information and storing the project data information into a preset data warehouse; monitoring the project data information in the data warehouse according to a problem monitoring rule to obtain problem monitoring information, classifying the project data information, and obtaining problem monitoring data corresponding to each problem mark; adding a corresponding optimization label to the problem monitoring data according to historical optimization project information to obtain to-be-optimized data information; and optimizing and adjusting project configuration information of the to-be-optimized data information according to received optimization configuration information, and updating corresponding project data information in the data warehouse. The project intelligent monitoring method can integrate and intelligently monitor business data, quickly locate problems and add labels, and efficiently monitor and identify problems.

Description

Technical Field

[0001] This invention relates to the field of big data analytics, and in particular to a method, system, and device for intelligent project monitoring based on big data analytics. Background Technology

[0002] In actual operation, transportation companies face the challenge of difficult project management due to the large number of vehicles and the complex and ever-changing routes involved. For example, project management typically involves addressing multiple issues such as pickup delays, dispatch delays, loss-making routes, pickup batches, non-straightening of routes, pickup costs, transfer costs, city / inter-province costs, and dispatch costs. Because of the numerous issues requiring management, traditional manual management methods are inefficient, lacking accuracy in monitoring operational problems and exhibiting delayed identification, significantly impacting the service quality and market competitiveness of transportation companies. Therefore, existing project management methods fail to monitor and identify operational problems in a timely and efficient manner. Summary of the Invention

[0003] This invention provides a project intelligent monitoring method, system, and device based on big data analysis, aiming to solve the problem that existing project management methods cannot monitor and identify operational issues in a timely and efficient manner.

[0004] In a first aspect, embodiments of the present invention provide a project intelligent monitoring method based on big data analysis, wherein the method is applied in a monitoring server, the monitoring server establishing a communication connection with at least one business terminal to achieve data information transmission, and the method includes:

[0005] If the preset data integration time point is reached, the business data received from the business terminal is integrated to obtain the corresponding project data information and store it in the preset data warehouse;

[0006] The project data information in the data warehouse is monitored according to the preset problem monitoring rules in order to obtain the corresponding problem monitoring information;

[0007] The project data information is classified according to the problem monitoring information to obtain the problem monitoring data corresponding to each problem tag;

[0008] Based on the preset tagging rules and the historical optimization project information in the data warehouse, corresponding optimization tags are added to the problem monitoring data to obtain the data information to be optimized corresponding to each problem tag.

[0009] If optimization configuration information corresponding to the data information to be optimized is received, the project configuration information in the data information to be optimized is optimized and adjusted according to the optimization configuration information;

[0010] The project data information in the data warehouse corresponding to the data information to be optimized is updated based on the optimized data information.

[0011] Secondly, embodiments of the present invention also provide a project intelligent monitoring system based on big data analysis, wherein the system is configured in a monitoring server, the monitoring server establishes a communication connection with at least one business terminal to realize the transmission of data information, the monitoring server is used to execute the project intelligent monitoring method based on big data analysis as described in the first aspect above, and the monitoring server is configured with the following units:

[0012] The data integration unit is used to integrate the business data received from the business terminal when a preset data integration time point is reached, and to store the corresponding project data information in a preset data warehouse.

[0013] The problem monitoring information acquisition unit is used to monitor the project data information in the data warehouse according to the preset problem monitoring rules in order to obtain the corresponding problem monitoring information;

[0014] The classification unit is used to classify the project data information according to the problem monitoring information to obtain the problem monitoring data corresponding to each problem tag;

[0015] The optimization tag adding unit is used to add corresponding optimization tags to the problem monitoring data according to the preset tagging rules and the historical optimization project information in the data warehouse, so as to obtain the data information to be optimized corresponding to each problem tag;

[0016] An optimization and adjustment unit is used to optimize and adjust the project configuration information in the data information to be optimized according to the optimization configuration information if it receives optimization configuration information corresponding to the data information to be optimized.

[0017] The information update unit is used to update the project data information in the data warehouse corresponding to the data information to be optimized based on the optimized data information.

[0018] Thirdly, embodiments of the present invention also provide a computer device, wherein the device includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0019] Memory, used to store computer programs;

[0020] When the processor executes the program stored in the memory, it implements the steps of the project intelligent monitoring method based on big data analysis described in the first aspect above.

[0021] Fourthly, embodiments of the present invention also provide a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the project intelligent monitoring method based on big data analysis as described in the first aspect above.

[0022] This invention provides a project intelligent monitoring method, system, and device based on big data analytics. The method includes: integrating business data received from business terminals at a preset data integration time point to obtain corresponding project data information, which is then stored in a preset data warehouse; monitoring the project data information in the data warehouse according to problem monitoring rules to obtain problem monitoring information, and classifying the project data information to obtain problem monitoring data corresponding to each problem tag; adding corresponding optimization tags to the problem monitoring data based on historical optimization project information to obtain data information to be optimized; optimizing and adjusting the project configuration information in the data information to be optimized based on received optimization configuration information, and updating the corresponding project data information in the data warehouse. This project intelligent monitoring method based on big data analytics can integrate and intelligently monitor business data, thereby quickly locating problems, classifying them, and adding corresponding tags, enabling efficient monitoring and timely problem identification. Attached Figure Description

[0023] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 A flowchart illustrating the intelligent project monitoring method based on big data analysis provided in this embodiment of the invention;

[0025] Figure 2 This is a schematic diagram illustrating an application scenario of the intelligent project monitoring method based on big data analysis provided in this embodiment of the invention.

[0026] Figure 3 A schematic block diagram of a project intelligent monitoring system based on big data analysis provided in an embodiment of the present invention;

[0027] Figure 4 This is a schematic block diagram of a computer device provided in an embodiment of the present invention. Detailed Implementation

[0028] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0029] It should be understood that, when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0030] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0031] It should also be further understood that the term "and / or" as used in this specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0032] This invention application provides an embodiment of a project intelligent monitoring method based on big data analysis. This method is applied to a monitoring server, which executes stored software programs to implement the aforementioned project intelligent monitoring method based on big data analysis. Figure 2 As shown, the monitoring server 10 establishes a communication connection with at least one business terminal 20 to realize the transmission of data information. The monitoring server 10 is a server configured within the enterprise to summarize and monitor business data, such as a management server or a cluster server. The business terminal 20 is a terminal device configured inside or outside the enterprise to record and process business data, such as a desktop computer, laptop computer, tablet computer, or mobile phone. Different types of business terminals 20 can process different types of business data. For example, three different types of business terminals 20 can respectively process transportation records, customer information, and regional operation data.

[0033] like Figure 1 As shown, the method includes steps S110 to S160.

[0034] S110. If the preset data integration time point is reached, the business data received from the business terminal is integrated to obtain the corresponding project data information and store it in the preset data warehouse.

[0035] The business terminals send the generated business data to the monitoring server, which receives the business data from the terminals in real time. When a pre-set data integration point is reached, the received unintegrated business data is integrated to obtain the corresponding project data information, which is then stored in the data warehouse. The data warehouse is built to store project data information, ensuring the accuracy, completeness, and consistency of the data. If the data integration point can be determined based on the monitoring cycle, the interval between two data integration points is the monitoring cycle; for example, a monitoring cycle of 1 minute can be set.

[0036] In a specific embodiment, step S110 includes the following sub-steps: cleaning the business data of each business terminal to obtain corresponding cleaned data; converting the cleaned data according to preset conversion rules to obtain corresponding converted data; and integrating the converted data of the same project based on the project identifier to obtain corresponding project data information and storing it in the data warehouse.

[0037] Specifically, business data from each business terminal can be cleaned to obtain cleaned data. The system can check if the values ​​of key parameters in the business data are empty; if any key parameter is empty, it is excluded; if none of the key parameters in the questionable data are empty, it is used as the cleaned data for further processing. Key parameters include project identifier, transportation location information, transportation mode, and transportation status.

[0038] The cleaned data is transformed according to the transformation rules to obtain the corresponding transformed data. The transformation rules specify the standard units and formats for each parameter, allowing for unit conversion and format alignment of the parameter values ​​in the cleaned data. For example, if the standard unit for a parameter is kilograms, the values ​​measured in "tons" in the corresponding parameter will be converted to values ​​measured in "kilograms". Format alignment involves adjusting the format of the values. For instance, if the standard format for a parameter is two decimal places, the values ​​with three decimal places in the corresponding parameter will be truncated to two decimal places to achieve format alignment.

[0039] Furthermore, based on the project identifiers of each conversion data set, the conversion data for a unified project is integrated. If the project identifiers of two sets of conversion data are the same, the two sets of conversion data can be integrated. After integration, the project data information corresponding to each project identifier can be obtained, and each project identifier corresponds to a set of project data information. The obtained project data information is then stored in the data warehouse.

[0040] S120. Monitor the project data information in the data warehouse according to the preset problem monitoring rules to obtain the corresponding problem monitoring information.

[0041] Furthermore, the project data information in the data warehouse is monitored according to the problem monitoring rules to obtain the corresponding problem monitoring information, which is the judgment information obtained to determine whether there are any operational problems in the project data information.

[0042] In a specific embodiment, step S120 includes the following sub-steps: filtering the project data information in the data warehouse according to the filtering conditions in the problem monitoring rules to obtain valid data information that meets the filtering conditions; obtaining the corresponding full summary data from the valid data information according to the statistical dimensions in each of the problem monitoring rules; and judging the full summary data according to the monitoring indicators configured in each of the problem monitoring rules to obtain the corresponding problem monitoring information.

[0043] Specifically, the problem monitoring rules include filtering conditions. These conditions can be used to filter project data in the data warehouse, allowing for the identification and monitoring of valid data that meets the criteria. For example, if the filtering conditions are set to "Transportation Status" as "Completed" and "Optimization Processing Mark" as empty, then a portion of the project data can be selected as valid data based on these conditions.

[0044] Furthermore, based on the statistical dimensions set in the problem monitoring rules, the corresponding full summary data is obtained from the valid data information. The statistical dimensions include transportation location information and transportation mode. Transportation location information includes departure point and destination. If the transportation location information and transportation mode are the same, they are grouped into one category for monitoring and analysis. Therefore, the full summary data includes all valid data information and the summary information obtained after statistical analysis based on the statistical dimensions.

[0045] Furthermore, the aggregated data obtained in the above steps is evaluated based on the monitoring indicators configured in the problem monitoring rules to obtain the corresponding problem monitoring information. In practical applications, multiple problem monitoring rules can be set, each with one or more monitoring indicators. Typically, a problem monitoring rule contains multiple monitoring indicators forming a set of combined monitoring indicators. For example, the problem monitoring rules may address multiple issues such as retrieval timeout, dispatch timeout, loss-making routes, retrieval batches, non-straightening, retrieval costs, transit costs, city / inter-province costs, and dispatch costs. Each issue corresponds to a specific monitoring rule, and the focus of each issue differs, resulting in different monitoring indicator parameters for different problem monitoring rules. Pickup timeout refers to monitoring whether the pickup process of a transportation project exceeds the time limit; delivery timeout refers to monitoring whether the delivery process of a transportation project exceeds the time limit; loss-making route refers to monitoring whether the accounts receivable of a transportation project can cover transportation costs; pickup batch refers to monitoring whether the pickup batches of a transportation project meet the relevant requirements; not straightened refers to monitoring whether the vehicle routes in a transportation project are direct (whether there are unnecessary bends in the route); pickup cost refers to monitoring whether the pickup cost of a transportation project meets the relevant requirements; transshipment cost refers to monitoring whether the transshipment cost of a transportation project meets the relevant requirements; city / province cost refers to monitoring whether the cost of a transportation project during cross-city / cross-province transportation meets the relevant requirements; and delivery cost refers to monitoring whether the delivery cost of a transportation project meets the relevant requirements.

[0046] For example, a monitoring rule for the issue of "loss-making routes" can be configured with multiple monitoring indicators such as mileage, cost per kilogram, average ticket weight, transportation profit margin, and performance-based profit margin. Each monitoring indicator corresponds to a parameter judgment range. Different problem monitoring rules can set the same monitoring indicator, but the parameter judgment range for the same monitoring indicator configured in different problem monitoring rules may differ. Therefore, each problem monitoring rule can perform a monitoring analysis on the full aggregated data. It then checks whether each valid data point in the full aggregated data meets the parameter judgment range set in the monitoring indicator. If the values ​​of the corresponding parameters in the valid data all meet the parameter judgment range set in the monitoring indicator, then the valid data is considered to match the problem monitoring rule; if the value of any parameter in the valid data does not meet the parameter judgment range set in the corresponding monitoring indicator, then the valid data is considered not to match the problem monitoring rule. By obtaining the matching results of each valid data point for each problem monitoring rule, the corresponding problem monitoring information can be obtained.

[0047] In a specific embodiment, before step S120, the method further includes the following steps: obtaining project data information in the data warehouse where the optimization processing mark is not empty, as the corresponding historical project data; aggregating the historical project data according to the problem marks in the historical project data to determine the aggregated data corresponding to each problem mark; performing feature statistics on the aggregated data of each problem mark to obtain the corresponding feature statistics information; and setting the parameter judgment range of each monitoring indicator in the problem monitoring rule according to the preset parameter setting rules and the feature statistics information of each problem mark.

[0048] Before obtaining issue monitoring information, project data with non-empty "optimization processing flags" in the data warehouse can be retrieved to obtain corresponding historical project data. If the "optimization processing flag" is not empty, its value is either "optimized" or "cannot be optimized." Historical project data also includes corresponding issue flags, which are tags added to the project data based on the aforementioned issue monitoring information. Historical project data can be aggregated based on these issue flags to obtain aggregated data corresponding to each issue flag. The aggregated data for each issue flag is also categorized and statistically analyzed according to statistical dimensions. Furthermore, feature statistics are performed on the aggregated data for each issue flag to obtain corresponding feature statistical information.

[0049] Specifically, for numerical parameters, based on the monitoring indicators configured in the monitoring rules corresponding to the problem markers, feature statistics are performed on the aggregated data categorized by statistical dimensions corresponding to the problem markers. For aggregated data corresponding to the problem markers and statistically analyzed according to different statistical dimensions, feature statistics are performed on the aggregated data for each statistical dimension using the monitoring indicators configured in the corresponding problem monitoring rules. In other words, the numerical values ​​of the corresponding parameters in the aggregated data are statistically analyzed based on the monitoring indicators to obtain numerical statistical information such as the numerical range, mean, and standard deviation of each monitoring indicator. The numerical statistical information of each monitoring indicator for a given problem monitoring rule is then used as the feature statistical information corresponding to that problem monitoring rule. Each problem monitoring rule corresponds to a problem marker, thus the feature statistical information corresponding to each problem marker can be obtained.

[0050] For non-numerical parameters, the proportion of matching information in each parameter can be counted as the corresponding feature statistics. A parameter can be matched with multiple pieces of information. For example, the parameter "transit city" can be matched with "1", "2", "3", etc.

[0051] Based on the parameter setting rules and the characteristic statistical information of each issue marker, the parameter judgment intervals of each monitoring indicator in the issue monitoring rules corresponding to each issue marker are reset, which means updating the parameter judgment intervals of each monitoring indicator in the issue monitoring rules. For non-numerical parameters, the matching information with the highest proportion of a certain monitoring indicator in the issue monitoring rules is obtained, and the matching keyword for that monitoring indicator is configured; then, during subsequent monitoring and analysis, it can be determined whether the corresponding parameter in the project data information matches the matching keyword.

[0052] In a specific embodiment, setting the parameter judgment interval for each monitoring indicator in the problem monitoring rule according to preset parameter setting rules and feature statistical information of each problem marker includes: obtaining feature comparison information between the feature statistical information of each problem marker and the feature statistical information corresponding to the project data information of the missing problem marker; determining the parameter judgment interval for the monitoring indicator corresponding to each problem marker according to the parameter setting rules and the feature comparison information; and setting the parameter judgment interval for each monitoring indicator in the problem monitoring rule according to the determined parameter judgment interval. The parameter judgment interval is reset based on historical project data, thereby improving the accuracy of subsequent monitoring and identification.

[0053] Since numerical parameters need to be precisely set to their specific numerical range, the process of setting the parameter judgment interval for monitoring indicators includes obtaining the feature statistics information corresponding to the project data information of the missing problem marker, and obtaining the feature comparison information between the feature statistics information of the problem marker and the feature statistics information of the missing problem marker; then, each monitoring indicator in the problem monitoring rule corresponds to a feature comparison information, and the parameter judgment interval of each monitoring indicator is determined according to the parameter setting rules and the feature comparison information of each monitoring indicator.

[0054] For example, in the feature statistics of a problem marker, the numerical range corresponding to a monitoring indicator is [a1, b1], the mean is c1, and the standard deviation is d1; in the feature statistics of a missing problem marker, the numerical range corresponding to the monitoring indicator is [a2, b2], the mean is c2, and the standard deviation is d2. By comparing the two sets of feature statistics for the same monitoring indicator, feature comparison information can be obtained.

[0055] Further, determine the corresponding bridging interval based on the feature comparison information. If c1 ≥ c2 and b2 > a1, determine the bridging interval as [a1, b2]; if c1 ≥ c2 and b2 < a1, determine the bridging interval as [b2, a1]; if c2 > c1 and b1 > a2, determine the bridging interval as [a2, b1]; if c2 > c1 and b1 < a2, determine the bridging interval as [b1, a2]; if c1 ≥ c2 and b2 = a1, determine the corresponding boundary value as a1; if c2 ≥ c1 and b1 = a2, determine the corresponding boundary value as b1.

[0056] Judge whether there is a bridging interval according to the parameter setting rule. If there is no bridging interval, directly determine the parameter judgment interval corresponding to the feature statistical information of the problem mark according to the boundary value. For example, determine the parameter judgment interval as the upper limit value or the lower limit value of the numerical interval corresponding to the boundary value and the feature statistical information of the problem mark. If the boundary value is a1 or b1, then correspondingly determine the parameter judgment interval as [a1, b1]; this situation is extremely special and has a very low probability of occurrence. More often, there is a bridging interval. If there is a bridging interval, calculate the boundary value corresponding to the bridging interval according to the setting function in the parameter setting rule. For example, the setting function can be expressed as:

[0057] (1);

[0058] Based on the upper limit value or the lower limit value of the numerical interval corresponding to the obtained boundary value and the feature statistical information of the problem mark, the parameter judgment interval can be determined. If c1 ≥ c2, determine the parameter judgment interval as [f1, b1] according to the upper limit value of the corresponding numerical interval and the boundary value; if c2 > c1, determine the parameter judgment interval as [a1, f2] according to the lower limit value of the corresponding numerical interval and the boundary value. Set the parameter judgment interval of the corresponding monitoring index in the problem monitoring rule according to the obtained parameter judgment interval, that is, correspondingly update the upper limit value and the lower limit value of the original parameter judgment interval.

[0059] S130. Classify the project data information according to the problem monitoring information to obtain the problem monitoring data corresponding to each problem mark.

[0060] Further, classify the project data information according to the problem monitoring information. The project data information matching the problem monitoring rule in the problem monitoring information can be used to generate a problem mark corresponding to the problem monitoring rule and add it to the project data information for easy classification. The project data information with the added problem mark can be used as the problem monitoring data. The project data information matching different problem monitoring rules can generate different problem marks; then, the problem monitoring data corresponding to each problem mark can be classified and obtained according to the added problem marks.

[0061] S140. According to the preset marking rules and the historical optimization project information in the data warehouse, add corresponding optimization tags to the problem monitoring data to obtain the data information to be optimized corresponding to each problem tag.

[0062] Furthermore, based on pre-defined tagging rules and historical optimization project data in the data warehouse, corresponding optimization tags are added to the problem monitoring data obtained in the above steps, resulting in the data information to be optimized corresponding to each problem tag. The problem monitoring data with added optimization tags can then be used as the data information to be optimized, which can be displayed to the monitoring administrator (the user of the monitoring server).

[0063] In a specific embodiment, step S140 includes the following sub-steps: obtaining target project data corresponding to each problem marker in the historical optimization project information; determining the project data information in the data warehouse with preset marker values ​​as historical optimization project information; obtaining optimization feature information corresponding to the target project data of each problem marker according to the optimization items in the marking rules; obtaining monitoring data features corresponding to the problem monitoring data of each problem marker according to the optimization items; performing feature matching between the monitoring data features of the problem monitoring data and the corresponding optimization feature information according to the feature matching model in the marking rules to obtain the optimization probability corresponding to each problem monitoring data; adding the optimization probability of each problem monitoring data as the corresponding optimization label to obtain the added problem monitoring data as the corresponding data information to be optimized.

[0064] The specific process of adding optimization tags includes: first, filtering the project data information in the data warehouse marked with preset tags for optimization processing, and obtaining the corresponding project data information to determine the historical optimization project information. For example, the preset tag can be set to "optimized". Next, the target project data corresponding to each issue tag in the historical optimization project information is obtained. Since the historical optimization project information has been monitored and analyzed, each historical optimization project information contains the corresponding issue tag (the premise for determining whether optimization processing can be performed is that issue tags have been added to the project data information). Therefore, the historical optimization project information contained in each issue tag constitutes the target project data corresponding to each issue tag.

[0065] The optimization feature information corresponding to the target project data of each problem label is obtained according to the optimization items set in the labeling rules. The target project data of each problem label is classified and statistically analyzed according to statistical dimensions. After classification and statistical analysis, a set of optimization feature information is obtained for each subcategory of target project data. For example, if the transportation location information in one statistical dimension is "Beijing (departure point) - Shanghai (destination)" and the transportation mode is road transportation, then this statistical dimension can be classified into a subcategory of target project data; if the transportation location information in another statistical dimension is "Wuhan (departure point) - Guangzhou (destination)" and the transportation mode is rail transportation, then this statistical dimension can also be classified into a subcategory of target project data. Multiple optimization items can be set in the labeling rules, and each optimization item can obtain a value from the target project data of a subcategory; for example, optimization items can be kilometers, cost per kilogram, average ticket weight, transportation time, average transportation speed, altitude difference, and highway ratio, etc. Based on the optimization item, the value corresponding to each target project data and the optimization item is obtained from the target project data of a subcategory of each problem label, and the average value is calculated; obtaining the average value corresponding to each optimization item yields the corresponding optimization feature information.

[0066] Based on the optimization items set in the marking rules, the monitoring data features corresponding to the problem monitoring data marked with problems are obtained. Specifically, the values ​​corresponding to each optimization item are obtained from the problem monitoring data based on the optimization items, thereby obtaining the corresponding monitoring data features.

[0067] Furthermore, based on the feature matching model set in the labeling rules, feature matching is performed on the monitoring data features of the problem monitoring data and the corresponding optimization feature information. Specifically, based on the problem labels and corresponding statistical dimensions added to the problem monitoring data, a set of optimization feature information with the same problem label and the same statistical dimension is obtained for feature matching. The labeling rules define multiple feature matching models, each corresponding to a problem label and a statistical dimension. Each feature matching model contains multiple input nodes, one output node, and one or more intermediate layers. The number of input nodes is equal to the total number of optimization items. The ratio of each feature value in a set of monitoring data features to the corresponding feature value in a set of optimization feature information is calculated, which is the feature ratio corresponding to each optimization item. The feature ratio of each optimization item can then be input into an input node. The output node is used to output the optimization probability value. The intermediate layer contains multiple intermediate nodes, and each intermediate node in the intermediate layer establishes an association function with the nodes in the previous and next layers. The input information of the association function is the node value of the node in the previous layer, and the output information of the association function is the node value of the node in the next layer. The association function also has association parameters configured.

[0068] The optimization probability is the predicted probability that the current problem monitoring data can be optimized. The higher the optimization probability, the greater the probability that the problem monitoring data can be optimized. The optimization probability of each problem monitoring data is used as a corresponding optimization label and added to the corresponding problem monitoring data, thus making the added problem monitoring data the corresponding data information to be optimized.

[0069] Before use, an initial model can be built and trained using positive and negative samples. Positive samples are the feature information of individual project data marked as "optimized" in the data warehouse, while negative samples are the feature information of individual project data marked as "non-optimizable." The process of obtaining the feature information of individual project data is the same as the process of obtaining the monitoring data features mentioned above. The feature ratio between two positive samples with the same problem label and the same statistical dimension is input into the initial model, or the feature ratio between one positive sample and one negative sample with the same problem label and the same statistical dimension is input into the initial model, and the initial model outputs the corresponding optimization probability value. If the input is two positive samples, the target probability value is "1"; if the input is one positive sample and one negative sample, the target probability value is "0". Based on the probability difference between the output optimization probability value and the target probability value, the loss coefficient corresponding to the probability difference is further calculated using the loss function. Gradient descent is performed on each correlation parameter in the initial model based on the preset learning rate and loss coefficient to obtain the optimized value of each correlation parameter. The correlation parameters in the initial model are then updated based on the optimized value. One update of each correlation parameter in the initial model is equivalent to one training of the initial model. After multiple iterations of training, a feature matching model specifically designed for feature matching analysis on the same problem label and the same statistical dimension can be obtained.

[0070] Furthermore, the input weights of each input node in the initial model can be adjusted accordingly for optimized and non-optimized feature information with the same problem label and the same statistical dimension. Non-optimized feature information refers to the feature information corresponding to the data information of items marked as "unoptimizable" in the data warehouse. The specific process for obtaining non-optimized feature information is the same as the specific process for obtaining optimized feature information. Based on the difference between the average values ​​of the same optimization item in the optimized and non-optimized feature information, the input weights of each input node are set accordingly. Since each optimization item corresponds to one input node, the input weights of the input nodes can be set according to the difference between the two average values ​​of each optimization item. For example, the weight coefficients are obtained using formula (2):

[0071] (2);

[0072] Where s1 and s2 are the average values ​​of the optimized term, optimized feature information, and non-optimized feature information, respectively; q is the calculated input weight; and e is the base of the natural logarithm. By configuring the input weights using the above method, the accuracy of the trained feature matching model in feature matching analysis can be further improved.

[0073] In a specific embodiment, after performing feature matching between the monitoring data features of the problem monitoring data and the corresponding optimization feature information according to the feature matching model in the labeling rules to obtain the optimization probability corresponding to each problem monitoring data, the method further includes: obtaining alternative optimization strategies from the target project data corresponding to the problem monitoring data; combining the optimization probability and alternative optimization strategies corresponding to the problem monitoring data into corresponding optimization tags and adding them to obtain the added problem monitoring data as the corresponding data information to be optimized.

[0074] Furthermore, alternative optimization strategies can be obtained from the target project data corresponding to the problem monitoring data. Specifically, after each target project data undergoes optimization processing, a corresponding optimization strategy is generated based on the optimization process. One or more sets of optimization strategies with the highest usage frequency can be obtained from the target project data that share the same problem label and statistical dimension as the problem monitoring data, serving as corresponding alternative optimization strategies. For example, optimization strategies for each target project data can be obtained and sorted, with strategies ranking higher based on usage frequency. If three strategies are obtained, the top three ranked optimization strategies can be selected as alternative optimization strategies. These alternative optimization strategies are then combined with the optimization probabilities corresponding to the problem monitoring data to generate corresponding optimization tags, which are then added to the problem monitoring data, thus obtaining the data information to be optimized corresponding to the problem monitoring data.

[0075] S150. If optimization configuration information corresponding to the data information to be optimized is received, the project configuration information in the data information to be optimized is optimized and adjusted according to the optimization configuration information.

[0076] The obtained data to be optimized can be displayed on the monitoring server. The monitoring administrator can then optimize the data according to the optimization tags in each piece of data, generating optimization configuration information during the optimization process. If the monitoring server receives the generated optimization configuration information, it will adjust the project configuration information in the data to be optimized accordingly. The project configuration information includes optimization processing tags, optimization strategies, optimization target parameters, and optimization improvement effects.

[0077] S160. Update the project data information in the data warehouse corresponding to the data information to be optimized based on the optimized data information.

[0078] Based on the optimized data to be optimized, the corresponding project data in the data warehouse is updated. This includes modifying the values ​​of optimization flags and configuring optimization strategies. The updated data warehouse can then be used for the next monitoring and analysis. Cyclic monitoring based on historical project data achieves a closed-loop project monitoring system, significantly improving the efficiency and accuracy of project data monitoring.

[0079] The intelligent project monitoring method based on big data analysis disclosed in the above embodiments includes the following steps: upon reaching a preset data integration time point, integrating business data received from the business terminal to obtain corresponding project data information and storing it in a preset data warehouse; monitoring the project data information in the data warehouse according to problem monitoring rules to obtain problem monitoring information and classifying the project data information to obtain problem monitoring data corresponding to each problem tag; adding corresponding optimization tags to the problem monitoring data based on historical optimization project information to obtain data information to be optimized; optimizing and adjusting the project configuration information in the data information to be optimized according to the received optimization configuration information, and updating the corresponding project data information in the data warehouse. The above-mentioned intelligent project monitoring method based on big data analysis can integrate and intelligently monitor business data, thereby quickly locating problems, classifying them, and adding corresponding tags, enabling efficient monitoring and timely problem identification.

[0080] This invention also provides a project intelligent monitoring system based on big data analysis, such as... Figure 3 As shown, the project intelligent monitoring system 100 based on big data analysis is configured in a monitoring server, which establishes a communication connection with at least one business terminal to realize the transmission of data information. The monitoring server is used to execute any embodiment of the aforementioned project intelligent monitoring method based on big data analysis. Specifically, the above-mentioned project intelligent monitoring system includes a data integration unit 110, a problem monitoring information acquisition unit 120, a classification unit 130, an optimization tag addition unit 140, an optimization adjustment unit 150, and an information update unit 160.

[0081] The data integration unit 110 is used to integrate the business data received from the business terminal when a preset data integration time point is reached, and to store the corresponding project data information in a preset data warehouse.

[0082] The problem monitoring information acquisition unit 120 is used to monitor the project data information in the data warehouse according to the preset problem monitoring rules in order to obtain the corresponding problem monitoring information.

[0083] The classification unit 130 is used to classify the project data information according to the problem monitoring information to obtain the problem monitoring data corresponding to each problem tag.

[0084] The optimization tag adding unit 140 is used to add corresponding optimization tags to the problem monitoring data according to the preset tagging rules and the historical optimization project information in the data warehouse, so as to obtain the data information to be optimized corresponding to each problem tag.

[0085] The optimization and adjustment unit 150 is used to optimize and adjust the project configuration information in the data information to be optimized according to the optimization configuration information if it receives optimization configuration information corresponding to the data information to be optimized.

[0086] The information update unit 160 is used to update the project data information in the data warehouse corresponding to the data information to be optimized based on the optimized data information.

[0087] In the project intelligent monitoring system based on big data analysis provided in this embodiment of the invention, the monitoring server executes the aforementioned project intelligent monitoring method based on big data analysis. Upon reaching a preset data integration point, it integrates the business data received from the business terminal to obtain corresponding project data information, which is then stored in a preset data warehouse. Based on problem monitoring rules, it monitors the project data information in the data warehouse to obtain problem monitoring information and classifies the project data information to obtain problem monitoring data corresponding to each problem tag. Based on historical optimization project information, it adds corresponding optimization tags to the problem monitoring data to obtain data information to be optimized. Based on the received optimization configuration information, it optimizes and adjusts the project configuration information in the data information to be optimized and updates the corresponding project data information in the data warehouse. The aforementioned project intelligent monitoring method based on big data analysis can integrate and intelligently monitor business data, thereby quickly locating problems, classifying them, and adding corresponding tags, enabling efficient monitoring and timely problem identification.

[0088] The aforementioned control-based configuration unit can be implemented as a computer program, which can be used in, for example... Figure 4 It runs on the computer device shown.

[0089] Please see Figure 4 , Figure 4This is a schematic block diagram of a computer device provided in an embodiment of the present invention. The computer device can be a monitoring server used to execute a project intelligent monitoring method based on big data analysis to aggregate and monitor business data.

[0090] See Figure 4 The computer device 500 includes a processor 502, a memory, and a communication interface 505 connected via a communication bus 501. The memory may include a storage medium 503 and internal memory 504.

[0091] The storage medium 503 can store the operating system 5031 and the computer program 5032. When the computer program 5032 is executed, it enables the processor 502 to execute a project intelligent monitoring method based on big data analysis. The storage medium 503 can be a volatile storage medium or a non-volatile storage medium.

[0092] The processor 502 provides computing and control capabilities to support the operation of the entire computer device 500.

[0093] The internal memory 504 provides an environment for the computer program 5032 in the storage medium 503 to run. When the computer program 5032 is executed by the processor 502, the processor 502 can execute a project intelligent monitoring method based on big data analysis.

[0094] This communication interface 505 is used for network communication, such as providing data transmission. Those skilled in the art will understand that... Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present invention and does not constitute a limitation on the computer device 500 to which the present invention is applied. The specific computer device 500 may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0095] The processor 502 is used to run the computer program 5032 stored in the memory to implement the corresponding functions in the above-mentioned intelligent monitoring method for projects based on big data analysis.

[0096] Those skilled in the art will understand that Figure 4 The embodiments of the computer device shown do not constitute a limitation on the specific configuration of the computer device. In other embodiments, the computer device may include more or fewer components than illustrated, or combine certain components, or have different component arrangements. For example, in some embodiments, the computer device may include only memory and a processor. In such embodiments, the structure and function of the memory and processor are different from those shown. Figure 4 The embodiments shown are consistent and will not be repeated here.

[0097] It should be understood that, in this embodiment of the invention, the processor 502 may be a Central Processing Unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0098] In another embodiment of the invention, a computer-readable storage medium is provided. This computer-readable storage medium may be volatile or non-volatile. The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps included in the above-described intelligent project monitoring method based on big data analytics.

[0099] Those skilled in the art will readily understand that, for the sake of convenience and brevity, the specific working processes of the devices, apparatuses, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this invention.

[0100] In the embodiments provided by this invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Units with the same function may be grouped into one unit. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interfaces, devices, or units, or it may be an electrical, mechanical, or other form of connection.

[0101] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiments of the present invention, depending on actual needs.

[0102] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0103] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a computer-readable storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned computer-readable storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), magnetic disks, or optical disks.

[0104] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and these modifications or substitutions should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A project intelligent monitoring method based on big data analysis, characterized in that, The method is applied to a monitoring server, which establishes a communication connection with at least one service terminal to realize transmission of data information, and the method comprises: If a preset data integration time point is reached, service data received from the service terminal is integrated to obtain corresponding project data information, which is stored in a preset data warehouse; According to a preset problem monitoring rule, project data information in the data warehouse is monitored to obtain corresponding problem monitoring information; According to the problem monitoring information, the project data information is classified to obtain problem monitoring data corresponding to each problem label; According to a preset label rule and historical optimization project information in the data warehouse, the problem monitoring data is added with corresponding optimization labels to obtain to-be-optimized data information corresponding to each problem label; If optimization configuration information corresponding to the to-be-optimized data information is received, project configuration information in the to-be-optimized data information is optimized and adjusted according to the optimization configuration information; According to the to-be-optimized data information after optimization and adjustment, project data information corresponding to the to-be-optimized data information in the data warehouse is updated. 2.The project intelligent monitoring method based on big data analysis of claim 1, wherein, The method comprises the following steps: According to a filtering condition in the problem monitoring rule, project data information in the data warehouse is filtered to obtain effective data information satisfying the filtering condition; According to a statistical dimension in each problem monitoring rule, full-amount summary data corresponding to the effective data information is obtained; According to a monitoring index configured in each problem monitoring rule, the full-amount summary data is judged to obtain corresponding problem monitoring information. 3.The project intelligent monitoring method based on big data analysis of claim 2, wherein, Before the step of monitoring, according to a preset problem monitoring rule, project data information in the data warehouse to obtain corresponding problem monitoring information, the method further comprises the following steps: Obtain project data information with non-empty optimization processing labels in the data warehouse as corresponding historical project data; According to a problem label in the historical project data, the historical project data is aggregated to determine aggregated data corresponding to each problem label; Feature statistics of the aggregated data of each problem label are obtained to obtain corresponding feature statistical information; According to a preset parameter setting rule and feature statistical information of each problem label, parameter judgment intervals of each monitoring index in the problem monitoring rule are set. 4.The project intelligent monitoring method based on big data analysis of claim 3, wherein, The step of setting, according to a preset parameter setting rule and feature statistical information of each problem label, parameter judgment intervals of each monitoring index in the problem monitoring rule, comprises the following steps: Obtain feature comparison information between feature statistical information of each problem label and feature statistical information of project data information of a missing problem label; According to the parameter setting rule and the feature comparison information, parameter judgment intervals of monitoring indexes corresponding to each problem label are determined; According to the determined parameter judgment intervals, parameter judgment intervals of each monitoring index in the problem monitoring rule are set. 5.The project intelligent monitoring method based on big data analysis of claim 1, wherein, The adding corresponding optimization labels to the problem monitoring data according to the preset marking rule and the historical optimization project information in the data warehouse, to obtain the to-be-optimized data information corresponding to each problem label, comprises: acquiring target project data corresponding to each problem label in the historical optimization project information; the project data information with the optimization processing marked as a preset mark value in the data warehouse is determined as the historical optimization project information; acquiring optimization feature information corresponding to the target project data of each problem label according to the optimization item in the marking rule; acquiring monitoring data features corresponding to the problem monitoring data of each problem label according to the optimization item; performing feature matching on the monitoring data features of the problem monitoring data and the corresponding optimization feature information according to the feature matching model in the marking rule, to obtain an optimization probability corresponding to each problem monitoring data; adding the optimization probability of each problem monitoring data as a corresponding optimization label, to obtain the added problem monitoring data as corresponding to-be-optimized data information.

6. The project intelligent monitoring method based on big data analysis according to claim 5, characterized in that, After the feature matching on the monitoring data features of the problem monitoring data and the corresponding optimization feature information according to the feature matching model in the marking rule, to obtain an optimization probability corresponding to each problem monitoring data, the method further comprises: acquiring a candidate optimization strategy from the target project data corresponding to the problem monitoring data; combining the optimization probability and the candidate optimization strategy corresponding to the problem monitoring data into a corresponding optimization label for addition, to obtain the added problem monitoring data as corresponding to-be-optimized data information. 7.The project intelligent monitoring method based on big data analysis of claim 1, wherein, The method of integrating the business data received from the business terminal to obtain corresponding project data information and storing the project data information into a preset data warehouse, comprises: cleaning the business data of each business terminal to obtain corresponding cleaning data; converting the cleaning data according to a preset conversion rule to obtain corresponding conversion data; integrating the conversion data of the same project based on a project identifier to obtain corresponding project data information and store the project data information into the data warehouse.

8. A project intelligent monitoring system based on big data analysis, characterized in that, The system is configured in a monitoring server, the monitoring server is in communication connection with at least one business terminal to realize transmission of data information, the monitoring server is used for executing the project intelligent monitoring method based on big data analysis as claimed in any one of claims 1-7, and the system comprises: a data integration unit, configured to integrate the business data received from the business terminal to obtain corresponding project data information and store the project data information into a preset data warehouse if a preset data integration time point is reached; a problem monitoring information acquisition unit, configured to monitor the project data information in the data warehouse according to a preset problem monitoring rule to acquire corresponding problem monitoring information; a classification unit, configured to classify the project data information according to the problem monitoring information to obtain problem monitoring data corresponding to each problem label; an optimization label adding unit, configured to add corresponding optimization labels to the problem monitoring data according to a preset marking rule and historical optimization project information in the data warehouse, to obtain to-be-optimized data information corresponding to each problem label; an optimization label adding unit, configured to add corresponding optimization labels to the problem monitoring data according to a preset marking rule and historical optimization project information in the data warehouse, to obtain to-be-optimized data information corresponding to each problem label; An optimization adjustment unit is configured to, if receiving optimization configuration information corresponding to the to-be-optimized data information, perform optimization adjustment on item configuration information in the to-be-optimized data information according to the optimization configuration information. An information updating unit is configured to update item data information corresponding to the to-be-optimized data information in the data warehouse according to the to-be-optimized data information after the optimization adjustment.

9. A computer device, comprising: The device comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory complete mutual communication through the communication bus; The memory is configured to store a computer program; The processor is configured to execute the program stored on the memory, and realize the steps of the project intelligent monitoring method based on big data analysis in any one of claims 1-7.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to realize the steps of the project intelligent monitoring method based on big data analysis in any one of claims 1-7.

Images