Index monitoring and early warning method and device

Abstract

The invention discloses an index monitoring and early warning method and device, and relates to the technical field of big data. A specific embodiment of the method comprises the steps of obtaining corresponding index analysis data according to a pre-constructed evaluation index relation graph in response to monitoring that an evaluation index is abnormal; inputting the index analysis data into a trained index analysis early warning model to obtain abnormal evaluation index data; and analyzing abnormal evaluation index data according to the evaluation index relation graph, and performing index monitoring and early warning according to an analysis result. According to the embodiment, the evaluation indexes can be monitored in real time, the index analysis and early warning model is constructed according to the evaluation index relation graph, index monitoring and early warning are performed on the index analysis data, the labor cost of index monitoring and early warning can be reduced, and the efficiency and accuracy of index monitoring and early warning can be improved.

Description

Technical Field

[0001] The present invention relates to the field of big data technology, and in particular, to a method and device for monitoring and warning of indicators. Background Art

[0002] In many scenarios encountered in daily life, it is necessary to analyze, monitor, and give early warnings to indicator data. For example, in a financial system, it is necessary to analyze, monitor, and give early warnings to the losses of profit and loss data; in a business system, it is necessary to analyze, monitor, and give early warnings to system operation data, and so on. Currently, the solution for analyzing, monitoring, and warning of data is to manually collect indicator analysis data and perform analysis and warning based on empirical judgment.

[0003] In the process of implementing the present invention, the inventors found that there are at least the following problems in the prior art:

[0004] The analysis and judgment of indicator analysis data rely on subjective experience, resulting in high labor costs, low efficiency, and low accuracy of indicator monitoring and warning. Summary of the Invention

[0005] In view of this, embodiments of the present invention provide a method and device for monitoring and warning of indicators, which can monitor and evaluate indicators in real time, construct an indicator analysis and warning model according to the evaluation indicator relationship graph, perform indicator monitoring and warning on indicator analysis data, reduce the labor cost of indicator monitoring and warning, and improve the efficiency and accuracy of indicator monitoring and warning.

[0006] To achieve the above object, according to one aspect of the embodiments of the present invention, a method for monitoring and warning of indicators is provided.

[0007] A method for monitoring and warning of indicators includes: in response to detecting an abnormal evaluation indicator, obtaining corresponding indicator analysis data according to a pre-constructed evaluation indicator relationship graph; inputting the indicator analysis data into a trained indicator analysis and warning model to obtain abnormal evaluation indicator data; analyzing the abnormal evaluation indicator data according to the evaluation indicator relationship graph, and performing indicator monitoring and warning through the analysis result.

[0008] Optionally, the evaluation indicator relationship graph is constructed in the following manner: generating at least one evaluation indicator according to one or more of the regional dimension, business dimension, and product dimension; for each evaluation indicator, determining the association relationship between the evaluation indicator and other evaluation indicators; constructing the evaluation indicator relationship graph through the evaluation indicators and the association relationships.

[0009] Optionally, the index analysis and early warning model is trained in the following manner: according to the evaluation index relationship diagram, obtain index analysis data samples, and mark the index analysis data samples according to whether the evaluation indexes are abnormal to generate evaluation index data samples; based on the discrete parallel system network model, use the evaluation index data samples for model training to obtain the index analysis and early warning model.

[0010] Optionally, the abnormal evaluation index data includes abnormal evaluation indexes. Analyzing the abnormal evaluation index data according to the evaluation index relationship diagram includes: according to the evaluation index relationship diagram, determining the dimension of the abnormal evaluation index, where the dimension corresponds to one or more preset early warning types; classifying and analyzing the abnormal evaluation indexes according to the early warning types to generate an analysis result.

[0011] Optionally, the abnormal evaluation index data further includes the abnormal degree corresponding to the abnormal evaluation index. Analyzing the abnormal evaluation index data according to the evaluation index relationship diagram includes: classifying and analyzing the abnormal evaluation indexes according to the abnormal degree corresponding to the abnormal evaluation index according to the analysis rules corresponding to the preset abnormal degree levels.

[0012] Optionally, before detecting that the evaluation index is abnormal, it further includes: determining the evaluation index and performing abnormal monitoring on the evaluation index according to the abnormal judgment rule.

[0013] Optionally, obtaining the corresponding index analysis data includes: according to the index evaluation period corresponding to the service, obtaining the index analysis data within the index evaluation period when the evaluation index is detected to be abnormal as the corresponding index analysis data.

[0014] According to another aspect of the embodiments of the present invention, a device for index monitoring and early warning is provided.

[0015] A device for index monitoring and early warning includes: an index analysis data acquisition module, configured to, in response to detecting that the evaluation index is abnormal, obtain corresponding index analysis data according to a pre-constructed evaluation index relationship diagram; an abnormal evaluation index data determination module, configured to input the index analysis data into a trained index analysis and early warning model to obtain abnormal evaluation index data; an index monitoring and early warning module, configured to analyze the abnormal evaluation index data according to the evaluation index relationship diagram and perform index monitoring and early warning through the analysis result.

[0016] Optionally, it further includes an evaluation index relationship graph construction module, which is used to: generate no less than one evaluation index according to one or more of the regional dimension, business dimension, and product dimension; for each of the evaluation indexes, determine the association relationship between the evaluation index and other evaluation indexes; and construct the evaluation index relationship graph through the evaluation index and the association relationship.

[0017] Optionally, it further includes an index analysis and early warning model training module, which is used to: obtain index analysis data samples according to the evaluation index relationship graph, and mark the index analysis data samples according to whether the evaluation indexes are abnormal to generate evaluation index data samples; and perform model training using the evaluation index data samples based on the discrete parallel system network model to obtain the index analysis and early warning model.

[0018] Optionally, the abnormal evaluation index data includes abnormal evaluation indexes, and the index monitoring and early warning module is further used to: determine the dimension of the abnormal evaluation index according to the evaluation index relationship graph, where the dimension corresponds to one or more preset early warning types; and classify and analyze the abnormal evaluation indexes according to the early warning types to generate an analysis result.

[0019] Optionally, the abnormal evaluation index data further includes the abnormal degree corresponding to the abnormal evaluation index, and the index monitoring and early warning module is further used to: classify and analyze the abnormal evaluation indexes according to the analysis rules corresponding to the preset abnormal degree levels according to the abnormal degree corresponding to the abnormal evaluation index.

[0020] Optionally, it further includes an evaluation index monitoring module, which is used to: determine evaluation indexes and perform abnormal monitoring on the evaluation indexes according to the abnormal judgment rules.

[0021] Optionally, the index analysis data acquisition module is further used to: obtain the index analysis data within the index evaluation period when the monitored evaluation index is abnormal as the corresponding index analysis data according to the index evaluation period corresponding to the business.

[0022] According to another aspect of the embodiments of the present invention, an electronic device is provided.

[0023] An electronic device includes: one or more processors; a memory for storing one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method for index monitoring and early warning provided by the embodiments of the present invention.

[0024] According to another aspect of the embodiments of the present invention, a computer-readable medium is provided.

[0025] A computer-readable medium stores a computer program thereon, and when the computer program is executed by a processor, it implements the method for index monitoring and early warning provided by the embodiments of the present invention.

[0026] One embodiment of the above invention has the following advantages or beneficial effects: By responding to the detection of abnormal evaluation indicators, according to the pre-constructed evaluation index relationship diagram, obtaining the corresponding index analysis data; inputting the index analysis data into the trained index analysis and early warning model to obtain abnormal evaluation index data; according to the evaluation index relationship diagram, analyzing the abnormal evaluation index data, and through the analysis results, carrying out index monitoring and early warning. The technical solution can monitor the evaluation indicators in real time, construct an index analysis and early warning model according to the evaluation index relationship diagram, and carry out index monitoring and early warning on the index analysis data, which can reduce the labor cost of index monitoring and early warning and improve the efficiency and accuracy of index monitoring and early warning.

[0027] The further effects of the above non-conventional optional methods will be described below in combination with specific embodiments. Brief Description of the Drawings

[0028] The drawings are used to better understand the present invention and do not constitute an improper limitation to the present invention. Among them:

[0029] Figure 1 is a schematic diagram of the main steps of the method for index monitoring and early warning according to an embodiment of the present invention;

[0030] Figure 2 is a schematic flowchart of the method for index monitoring and early warning according to an embodiment of the present invention;

[0031] Figure 3 is a schematic diagram of the main modules of the device for index monitoring and early warning according to an embodiment of the present invention;

[0032] Figure 4 is an exemplary system architecture diagram to which the embodiments of the present invention can be applied;

[0033] Figure 5 is a schematic diagram of the structure of a computer system of a terminal device or a server suitable for implementing the embodiments of the present invention. Detailed Embodiments

[0034] The following describes exemplary embodiments of the present invention in conjunction with the accompanying drawings. Various details of the embodiments of the present invention are included to assist in understanding, and they should be considered merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for the sake of clarity and conciseness, the description below omits the description of well-known functions and structures.

[0035] It should be noted that in the technical solution of the present invention, in terms of the collection, gathering, update, analysis, processing, use, transmission, storage, etc. of the user's personal information, it complies with the provisions of relevant laws and regulations, is used for legal purposes, and does not violate public order and good customs. Necessary measures are taken for the user's personal information to prevent illegal access to the user's personal information data and to safeguard the security of the user's personal information, network security, and national security.

[0036] Figure 1 It is a schematic diagram of the main steps of a method for monitoring and warning indicators according to an embodiment of the present invention.

[0037] As Figure 1 shown, the method for monitoring and warning indicators according to an embodiment of the present invention mainly includes the following steps S101 to S103.

[0038] Step S101: In response to detecting an abnormal evaluation indicator, obtain corresponding indicator analysis data according to a pre-constructed evaluation indicator relationship diagram. Among them, the indicator analysis data includes multiple evaluation indicators and the evaluation indicator values corresponding to each evaluation indicator.

[0039] In one embodiment, the evaluation indicator relationship diagram can be constructed in the following manner: Generate no less than one evaluation indicator according to one or more of the regional dimension, business dimension, and product dimension; for each evaluation indicator, determine the association relationship between the evaluation indicator and other evaluation indicators; construct the evaluation indicator relationship diagram through the evaluation indicators and the association relationship.

[0040] Specifically, taking the analysis of the profit and loss situation of the financial system as an example, the evaluation indicators can include the evaluation indicators of income and the evaluation indicators of cost. The evaluation indicators of income and the evaluation indicators of cost can respectively generate multiple evaluation indicators according to one or more of the regional dimension, business dimension, and product dimension. Among them, the regional dimension can include the first-level region, second-level region, third-level region (such as business department), etc. The first-level region can include multiple second-level regions, and the second-level region can include multiple third-level regions. The business dimension includes express delivery, cold chain, medicine, supply chain, etc. The product dimension includes human resources, housing, consumables, etc. For example, the evaluation indicators of business department A can include the income evaluation indicators and cost evaluation indicators of business department A. The cost evaluation indicators of business department A can include the cost evaluation indicators of multiple business dimensions (such as express delivery cost evaluation indicator, cold chain cost evaluation indicator, medicine cost evaluation indicator, supply chain cost evaluation indicator). Each cost evaluation indicator of the business dimension can include the cost evaluation indicators of multiple product dimensions (such as human resource cost evaluation indicator, housing cost evaluation indicator, consumable cost evaluation indicator).

[0041] For each evaluation index, determine the correlation relationship between the evaluation index and other evaluation indexes. The correlation relationship of the evaluation index can be the correlation relationship between the evaluation index and the corresponding upper-level evaluation index (i.e., the evaluation index is a constituent element of the upper-level evaluation index), and the correlation relationship between the evaluation index and the corresponding multiple lower-level evaluation indexes (i.e., multiple lower-level evaluation indexes are constituent elements of the evaluation index).

[0042] In one embodiment, before detecting that the evaluation index is abnormal, it may further include: determining the evaluation index, and performing abnormal monitoring on the evaluation index according to the abnormal judgment rule.

[0043] Specifically, the evaluation index may be the total evaluation index of the first-level area, that is, all the lowest-level income evaluation indexes corresponding to the first-level area minus all the lowest-level cost evaluation indexes. The evaluation index may also be set as the total evaluation index of the second-level area, the total evaluation index of the third-level area, etc. according to business needs.

[0044] Detect the evaluation index regularly according to the preset index evaluation period (such as 1 hour, 1 day, 1 month, etc.). When the evaluation index value is lower than the preset threshold or the change value of the evaluation index value relative to the previous period exceeds the preset change threshold, it is determined that the evaluation index is abnormal.

[0045] In one embodiment, obtaining the corresponding index analysis data may include: obtaining the index analysis data within the index evaluation period when the evaluation index is detected to be abnormal as the corresponding index analysis data according to the index evaluation period corresponding to the business. For example, if the index evaluation period is 1 month, obtain the index analysis data of the most recent 1 month when the evaluation index is detected to be abnormal.

[0046] Step S102: Input the index analysis data into the trained index analysis early warning model to obtain abnormal evaluation index data.

[0047] Among them, the abnormal evaluation index data may include the abnormal evaluation index and the abnormal degree corresponding to each abnormal evaluation index.

[0048] In one embodiment, the index analysis early warning model may be trained in the following manner: obtain the index analysis data sample according to the evaluation index relationship diagram, and mark the index analysis data sample according to whether the evaluation index is abnormal to generate the evaluation index data sample; based on the discrete parallel system network model, use the evaluation index data sample for model training to obtain the index analysis early warning model.

[0049] Specifically, according to the evaluation index relationship diagram, obtain the index analysis data sample and the corresponding evaluation index, and determine whether the evaluation index value of the index analysis data sample is normal according to the evaluation index. In the case where the evaluation index value is abnormal, mark the abnormal evaluation index and the degree of abnormality in the index analysis data sample to obtain the abnormal evaluation index data sample, and generate a negative sample of the evaluation index data through the index analysis data sample and the abnormal evaluation index data sample. In the case where the evaluation index value is normal, all evaluation indexes are normal, the abnormal evaluation index data sample can be set to be empty, and a positive sample of the evaluation index data is generated through the index analysis data sample and the abnormal evaluation index data sample.

[0050] According to the evaluation index relationship diagram, use the discrete parallel system network to build a discrete parallel system network model. Among them, the discrete parallel system network can be a stochastic Petri net (a mathematical representation of a discrete parallel system). Use the index analysis data sample as the input of the discrete parallel system network model and the abnormal evaluation index data sample as the output, and train the discrete parallel system network model to obtain an index analysis warning model.

[0051] Step S103: Analyze the abnormal evaluation index data according to the evaluation index relationship diagram, and perform index monitoring and warning based on the analysis results.

[0052] In one embodiment, analyzing the abnormal evaluation index data according to the evaluation index relationship diagram may include: determining the dimension of the abnormal evaluation index according to the evaluation index relationship diagram, where the dimension corresponds to one or more preset warning types; classifying and analyzing the abnormal evaluation indexes according to the warning types to generate an analysis result.

[0053] Specifically, the warning types may include warnings related to operation personnel, warnings related to procurement personnel, warnings related to R & D personnel, etc. For example, warnings related to operation personnel may correspond to evaluation indexes such as human resources, and warnings related to procurement personnel may correspond to evaluation indexes such as consumables. Classify and analyze the abnormal evaluation indexes according to the warning types, and send the analysis results of each warning type to the relevant personnel.

[0054] In one embodiment, analyzing the abnormal evaluation index data according to the evaluation index relationship diagram may include: classifying and analyzing the abnormal evaluation indexes according to the analysis rules corresponding to the preset abnormal degree levels according to the abnormal degree corresponding to the abnormal evaluation index.

[0055] Specifically, different abnormal degree levels are preset, the abnormal evaluation indexes are classified according to the abnormal degree corresponding to the abnormal evaluation index, and the analysis is performed in the order of the severity of the abnormal degree levels.

[0056] Figure 2It is a schematic flowchart of a method for index monitoring and early warning according to an embodiment of the present invention.

[0057] As Figure 2 shown, in one embodiment, first, an evaluation index relationship graph is constructed. Based on a discrete parallel system network, a network model is built according to the evaluation indexes and association relationships in the evaluation index relationship graph, and the index analysis and early warning model is obtained by training the network model. The evaluation indexes are monitored. When an abnormal evaluation index is detected, the index analysis data within a preset period is obtained, and the index analysis data is input into the trained index analysis and early warning model to obtain abnormal evaluation index data, and classification analysis and index monitoring and early warning are performed through the abnormal evaluation index data. The embodiment of the present invention can, through the correlation analysis of index analysis data, monitor evaluation indexes in real time, and automatically warn of abnormal evaluation indexes and monitoring and early warning status of each business line.

[0058] Figure 3 It is a schematic diagram of the main modules of a device for index monitoring and early warning according to an embodiment of the present invention.

[0059] As Figure 3 shown, the device 300 for index monitoring and early warning according to an embodiment of the present invention mainly includes: an index analysis data acquisition module 301, an abnormal evaluation index data determination module 302, and an index monitoring and early warning module 303.

[0060] The index analysis data acquisition module 301 is configured to, in response to detecting an abnormal evaluation index, obtain corresponding index analysis data according to a pre-constructed evaluation index relationship graph.

[0061] The abnormal evaluation index data determination module 302 is configured to input the index analysis data into the trained index analysis and early warning model to obtain abnormal evaluation index data.

[0062] The index monitoring and early warning module 303 is configured to analyze the abnormal evaluation index data according to the evaluation index relationship graph, and perform index monitoring and early warning through the analysis result.

[0063] In one embodiment, it may further include an evaluation index relationship graph construction module (not shown in the figure), which is configured to: generate no less than one evaluation index according to one or more of the regional dimension, business dimension, and product dimension; for each evaluation index, determine the association relationship between the evaluation index and other evaluation indexes; and construct an evaluation index relationship graph through the evaluation indexes and association relationships.

[0064] In one embodiment, it further includes an index analysis and early warning model training module (not shown in the figure), which is used to: obtain index analysis data samples according to the evaluation index relationship diagram, and mark the index analysis data samples according to whether the evaluation indexes are abnormal to generate evaluation index data samples; based on the discrete parallel system network model, use the evaluation index data samples for model training to obtain the index analysis and early warning model.

[0065] In one embodiment, the abnormal evaluation index data may include abnormal evaluation indexes. The index monitoring and early warning module 303 is specifically used to: determine the dimensions of the abnormal evaluation indexes according to the evaluation index relationship diagram, and the dimensions correspond to one or more preset early warning types; classify and analyze the abnormal evaluation indexes according to the early warning types to generate an analysis result.

[0066] In one embodiment, the abnormal evaluation index data may further include the abnormal degree corresponding to the abnormal evaluation index. The index monitoring and early warning module 303 is specifically used to: classify and analyze the abnormal evaluation indexes according to the analysis rules corresponding to the preset abnormal degree levels according to the abnormal degree corresponding to the abnormal evaluation index.

[0067] In one embodiment, it further includes an evaluation index detection module (not shown in the figure), which is used to: determine the evaluation indexes and perform abnormal monitoring on the evaluation indexes according to the abnormal judgment rules.

[0068] In one embodiment, the index analysis data acquisition module 301 is specifically used to: obtain the index analysis data within the index evaluation period when the monitored evaluation index is abnormal as the corresponding index analysis data according to the index evaluation period corresponding to the service.

[0069] In addition, the specific implementation content of the index monitoring and early warning device in the embodiments of the present invention has been described in detail in the above index monitoring and early warning method, so the repeated content will not be described here.

[0070] Figure 4 An exemplary system architecture 400 to which the index monitoring and early warning method or the index monitoring and early warning device of the embodiments of the present invention can be applied is shown.

[0071] As Figure 4 shown, the system architecture 400 may include terminal devices 401, 402, 403, a network 404, and a server 405. The network 404 is used to provide a medium for communication links between the terminal devices 401, 402, 403 and the server 405. The network 404 may include various connection types, such as wired, wireless communication links, or fiber optic cables, etc.

[0072] Users can use terminal devices 401, 402, and 403 to interact with server 405 via network 404 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 401, 402, and 403, such as index monitoring and warning applications, financial applications, data analysis applications, instant messaging tools, email clients, social platform software, etc. (for example only).

[0073] Terminal devices 401, 402, and 403 can be various electronic devices with a display screen and supporting web browsing, including but not limited to smartphones, tablets, laptop computers, and desktop computers, etc.

[0074] Server 405 can be a server providing various services. For example, it can be a background management server that supports the index monitoring and warning websites browsed by users using terminal devices 401, 402, and 403 (for example only). The background management server can respond to data such as index monitoring and warning requests received. When it detects that the evaluation index is abnormal, according to the pre-constructed evaluation index relationship diagram, it obtains the corresponding index analysis data; inputs the index analysis data into the trained index analysis and warning model to obtain abnormal evaluation index data; analyzes the abnormal evaluation index data according to the evaluation index relationship diagram, and performs processing such as index monitoring and warning through the analysis results, and feeds back the processing results (such as the results of index monitoring and warning - for example only) to the terminal device.

[0075] It should be noted that the method for index monitoring and warning provided by the embodiments of the present invention is generally executed by server 405. Correspondingly, the device for index monitoring and warning is generally set in server 405.

[0076] It should be understood that Figure 4 the numbers of the terminal devices, network, and server in

[0077] are merely illustrative. According to the implementation requirements, there can be any number of terminal devices, network, and server.

[0077] Next, refer to Figure 5 which shows a schematic structural diagram of a computer system 500 of a terminal device or a server suitable for implementing the embodiments of the present invention. Figure 5 The terminal device or server shown is merely an example and should not bring any limitation to the functions and usage scope of the embodiments of the present invention.

[0078] As Figure 5As shown, computer system 500 includes a central processing unit (CPU) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage section 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the system 500 are also stored. The CPU 501, ROM 502, and RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0079] The following components are connected to the I / O interface 505: an input section 506 including a keyboard, a mouse, etc.; an output section 507 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc. and a speaker, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN card, a modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the I / O interface 505 as needed. A removable medium 511, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 510 as needed so that a computer program read from it can be installed into the storage section 508 as needed.

[0080] Specifically, according to the embodiments disclosed in the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present invention include a computer program product that includes a computer program carried on a computer-readable medium, and the computer program includes program codes for performing the methods shown in the flowcharts. In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 509, and / or installed from the removable medium 511. When the computer program is executed by the central processing unit (CPU) 501, the above functions defined in the system of the present invention are executed.

[0081] It should be noted that the computer-readable medium shown in the present invention can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the above two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, the computer-readable storage medium can be any tangible medium that contains or stores a program, and this program can be used by or in combination with an instruction execution system, apparatus, or device. And in the present invention, the computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, in which the computer-readable program code is carried. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium can also be any computer-readable medium other than the computer-readable storage medium, and this computer-readable medium can send, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted by any suitable medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0082] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagram can represent a module, a program segment, or a part of code, and the above module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order from that marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram or flowchart, and the combination of blocks in the block diagram or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0083] The modules involved in the embodiments of the present invention can be implemented in software or in hardware. The described modules can also be provided in a processor. For example, it can be described as: a processor includes a metric analysis data acquisition module, an abnormal evaluation metric data determination module, and a metric monitoring and warning module. Among them, the names of these modules do not constitute a limitation to the module itself in some cases. For example, the metric analysis data acquisition module can also be described as "a module for obtaining corresponding metric analysis data according to a pre-constructed metric evaluation relationship diagram in response to detecting an abnormal evaluation metric."

[0084] As another aspect, the present invention further provides a computer-readable medium, which can be included in the device described in the above embodiments; or can exist alone without being assembled into the device. The above computer-readable medium carries one or more programs. When the one or more programs are executed by the device, the device includes: obtaining corresponding metric analysis data according to a pre-constructed metric evaluation relationship diagram in response to detecting an abnormal evaluation metric; inputting the metric analysis data into a trained metric analysis and warning model to obtain abnormal evaluation metric data; analyzing the abnormal evaluation metric data according to the metric evaluation relationship diagram, and performing metric monitoring and warning through the analysis result.

[0085] According to the technical solution of the embodiments of the present invention, in response to detecting an abnormal evaluation metric, corresponding metric analysis data is obtained according to a pre-constructed metric evaluation relationship diagram; the metric analysis data is input into a trained metric analysis and warning model to obtain abnormal evaluation metric data; the abnormal evaluation metric data is analyzed according to the metric evaluation relationship diagram, and metric monitoring and warning are performed through the analysis result. It can monitor the evaluation metric in real time, construct a metric analysis and warning model according to the metric evaluation relationship diagram, perform metric monitoring and warning on the metric analysis data, reduce the labor cost of metric monitoring and warning, and improve the efficiency and accuracy of metric monitoring and warning.

[0086] The above specific embodiments do not limit the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can occur depending on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for monitoring and warning of indicators, characterized in that, it includes: In response to detecting that an evaluation indicator is abnormal, according to a pre-constructed evaluation indicator relationship graph, obtain corresponding indicator analysis data; Input the indicator analysis data into a trained indicator analysis warning model to obtain abnormal evaluation indicator data; According to the evaluation indicator relationship graph, analyze the abnormal evaluation indicator data, and perform indicator monitoring and warning through the analysis results.

2. The method according to claim 1, characterized in that, The evaluation indicator relationship graph is constructed in the following manner: Generate no less than one evaluation indicator according to one or more of the regional dimension, business dimension, and product dimension; For each of the evaluation indicators, determine the association relationship between the evaluation indicator and other evaluation indicators; Construct the evaluation indicator relationship graph through the evaluation indicators and the association relationships.

3. The method according to claim 1, characterized in that, The indicator analysis warning model is trained in the following manner: According to the evaluation indicator relationship graph, obtain indicator analysis data samples, and mark the indicator analysis data samples according to whether the evaluation indicators are abnormal to generate evaluation indicator data samples; Based on a discrete parallel system network model, use the evaluation indicator data samples for model training to obtain the indicator analysis warning model.

4. The method according to claim 1, characterized in that, The abnormal evaluation indicator data includes abnormal evaluation indicators, and analyzing the abnormal evaluation indicator data according to the evaluation indicator relationship graph includes: According to the evaluation indicator relationship graph, determine the dimension of the abnormal evaluation indicator, and the dimension corresponds to one or more preset warning types; Classify and analyze the abnormal evaluation indicators according to the warning types to generate analysis results.

5. The method according to claim 4, characterized in that, The abnormal evaluation indicator data further includes the abnormal degree corresponding to the abnormal evaluation indicator, and analyzing the abnormal evaluation indicator data according to the evaluation indicator relationship graph includes: According to the analysis rules corresponding to the preset abnormal degree levels, classify and analyze the abnormal evaluation indicators according to the abnormal degree corresponding to the abnormal evaluation indicators.

6. The method according to claim 1, characterized in that, Before detecting that an evaluation indicator is abnormal, it further includes: Determine the evaluation indicators, and perform abnormal monitoring on the evaluation indicators according to the abnormal judgment rules.

7. The method according to claim 1, characterized in that, Obtaining the corresponding indicator analysis data includes: According to the indicator evaluation cycle corresponding to the business, obtain the indicator analysis data within the indicator evaluation cycle when it is detected that the evaluation indicator is abnormal as the corresponding indicator analysis data.

8. An apparatus for monitoring and warning of indicators, characterized in that, it includes: An indicator analysis data acquisition module, configured to, in response to detecting that an evaluation indicator is abnormal, obtain corresponding indicator analysis data according to a pre-constructed evaluation indicator relationship graph; An abnormal evaluation indicator data determination module, configured to input the indicator analysis data into a trained indicator analysis warning model to obtain abnormal evaluation indicator data; The index monitoring and warning module is used to analyze the abnormal evaluation index data according to the evaluation index relationship diagram, and perform index monitoring and warning based on the analysis results.

9. An electronic device, characterized in that, comprising: one or more processors; a storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1-7.

10. A computer-readable medium having a computer program stored thereon, characterized in that, when the computer program is executed by a processor, the method according to any one of claims 1-7 is implemented.

Images