Intelligent agent system service efficiency abnormity early warning method and device

Abstract

The invention provides an agent system service efficiency abnormity early warning method and device. The method comprises the following steps: obtaining service efficiency data of an agent system to be early warned; combining different service efficiency indexes in the service efficiency data in pairs for correlation analysis to obtain a sequential sequence of correlation coefficients between any two service efficiency indexes, and a mean value and a standard deviation of the sequential sequence; determining an early warning result of the intelligent agent system based on the service efficiency abnormity early warning rule; wherein the early warning rule is determined according to the mean value and the standard deviation. According to the invention, the problem of low accuracy of service efficiency early warning caused by crowd intelligence, ecology and complexity of an intelligent agent system is solved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a method and device for warning abnormal service performance of an intelligent system. Background Art

[0002] The service efficiency early warning of the intelligent system is based on the historical service efficiency measurement data. By establishing the measurement and calculation model of the service efficiency of the intelligent system, the current status of the service efficiency and the changing trend of the future service efficiency are predicted. It is of great significance to fully mobilize the enthusiasm of the intelligent system and solve the problems of the single interest demand of the intelligent system, the unequal rights and responsibilities between different subjects, and the imbalance of the behavior of the service subject. As time series data, the service efficiency data of the intelligent system has a certain time correlation, and the importance of the information contained at different times varies. Therefore, making full use of the time series and difference of the service efficiency data, and overcoming the difficulty of quantity, evaluation, and optimization brought by the characteristics of the intelligent system such as crowd wisdom, ecology, and complexity, is of great research significance to improve the accuracy of the service efficiency early warning of the intelligent system. Summary of the invention

[0003] The present invention provides a method and device for warning abnormal service performance of an intelligent body system, which solves the problem of low accuracy of service performance warning caused by the crowd intelligence, ecology and complexity of the intelligent body system.

[0004] The present invention provides a service efficiency warning method for an intelligent body system, comprising: obtaining service efficiency data of an intelligent body system to be warned; performing correlation analysis on different service efficiency indicators in the service efficiency data in pairs to obtain a time series of correlation coefficients between any two service efficiency indicators, as well as a mean and a standard deviation of the time series; determining a warning result of the intelligent body system based on the service efficiency abnormality warning rule; wherein the warning rule is determined according to the mean and the standard deviation.

[0005] According to a service performance early warning method for an intelligent system provided by the present invention, the service performance data includes observation values ​​of one or more service performance indicators at each preset time interval; the service performance indicators include an operational efficiency indicator of the intelligent system, a fairness indicator of the intelligent system, an objective performance indicator of the intelligent system, a fairness indicator of the service group, a diversity indicator of the intelligent system, and a development indicator of the intelligent system.

[0006] According to a service efficiency warning method for an intelligent system provided by the present invention, the different service efficiency indicators in the service efficiency data are combined in pairs to perform correlation analysis to obtain a time series of correlation coefficients between any two service efficiency indicators, as well as the mean and standard deviation of the time series. Specifically, it includes: performing correlation analysis on different service efficiency indicators in pairs, obtaining the Pearson correlation coefficients of the two service efficiency indicators in units of one hour in a day, obtaining a time series of Pearson correlation coefficients between any two indicators, and determining the mean and standard deviation of the time series.

[0007] According to a service efficiency early warning method of an intelligent system provided by the present invention, the time series of the correlation coefficient between any two service efficiency indicators satisfies the relationship: ; ; The mean and standard deviation of the time series satisfy the relationship: ; Among them, x(t) and y(t) are any two service performance indicator sequences of length, and are the sequences obtained by truncating x(t) and y(t) hour by hour according to the length of 24 hours, , i is the order of each moment in 24 hours, r(t) is the and The Pearson correlation coefficient between them, the length of r(t) is n, is the mean of the time series, is the standard deviation of the time series.

[0008] According to a service performance warning method of an intelligent system provided by the present invention, the warning rule is that at any time, the warning levels of any two different service performance indicators satisfy the relationship: ; in, For service efficiency I i and service performance I j The warning level, 0 means no warning. 1 means level 1 warning, 2 means level 2 warning. 3 indicates level 3 warning.

[0009] According to a service performance warning method for an intelligent body system provided by the present invention, the warning result of the intelligent body system is determined based on the service performance abnormality warning rule, including: determining the warning level of the two service performance indicators in units of one hour in a day based on the service performance abnormality warning rule; and taking the maximum value of the warning levels as the warning result of the intelligent body system at the current moment.

[0010] According to a service efficiency early warning method of an intelligent system provided by the present invention, the early warning result satisfies the relationship: ; in, W ( t ) is the warning result, For service efficiency I i and service performance I j warning level.

[0011] The present invention also provides an intelligent body system service efficiency anomaly warning device, comprising: an acquisition module, used to obtain the service efficiency data of the intelligent body system to be warned; a correlation analysis module, used to perform correlation analysis on different service efficiency indicators in the service efficiency data in pairs, to obtain a time series of correlation coefficients between any two service efficiency indicators, and a mean and standard deviation of the time series; a warning module, used to determine the warning result of the intelligent body system based on the service efficiency anomaly warning rules; wherein the warning rules are determined according to the mean and the standard deviation.

[0012] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein when the processor executes the computer program, it implements any of the above-mentioned intelligent system service performance abnormality warning methods.

[0013] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-mentioned intelligent system service performance abnormality warning methods.

[0014] The present invention provides a method and device for warning abnormal service performance of an intelligent body system, the method comprising: obtaining service performance data of an intelligent body system to be warned; performing correlation analysis on the combination of different service performance indicators in the service performance data, obtaining a time series of correlation coefficients between any two service performance indicators, and the mean and standard deviation of the time series; determining the warning result of the intelligent body system based on the service performance abnormality warning rule; wherein the warning rule is determined according to the mean and standard deviation. The present invention solves the problem of low accuracy of service performance warning caused by the crowd intelligence, ecology and complexity of the intelligent body system. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 It is a flow chart of an abnormal warning method for service performance of an intelligent system provided by the present invention.

[0017] Figure 2 It is a specific flow chart of an intelligent body system service performance abnormality warning method provided by the present invention.

[0018] Figure 3 It is a structural schematic diagram of an abnormal warning device for service efficiency of an intelligent system provided by the present invention.

[0019] Figure 4 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] Please refer to Figure 1 , Figure 1 A flowchart of an abnormal warning method for intelligent system service performance provided by the present invention.

[0022] Please refer to Figure 2 , Figure 2A schematic diagram of a specific process of an abnormal warning method for service efficiency of an intelligent system provided by the present invention.

[0023] The present invention provides a service efficiency early warning method of an intelligent system, comprising: S110: Obtain service performance data of the intelligent system to be warned.

[0024] As a preferred embodiment, the service performance data includes observation values ​​of one or more service performance indicators at each preset time interval; the service performance indicators include operational efficiency indicators of the intelligent agent system, fairness indicators of the intelligent agent system, objective performance indicators of the intelligent agent system, fairness indicators of the service group, diversity indicators of the intelligent agent system, and development indicators of the intelligent agent system.

[0025] In this embodiment, the intelligent agent system is, for example, a multi-agent traffic intelligent agent system, which divides the service subjects into service demanders (passengers) and service providers (drivers), and divides the service process into three parts: service input, service process, and service output.

[0026] From the driver's perspective, the economic value dimension is proposed in the service investment link ; From the perspective of passengers, propose the dimension of use value in the output link of services ; From the perspectives of both drivers and passengers, the social value dimension is proposed ; From the perspective of the integrated supply and demand of the intelligent system, the ecological value dimension is proposed and development value dimensions .

[0027] From the perspective of the driver, from the dimension of economic value, we propose the individual driver's profit efficiency index and the intelligent system's operational efficiency index; from the perspective of the driver, from the dimension of social value, we extract the stability index of the individual driver's profit and the fairness index of the intelligent system; from the perspective of the passenger, from the dimension of use value, we extract the passenger's subjective satisfaction index and the objective performance index of the service process; from the perspective of the passenger, from the dimension of social value, we extract the individual passenger's stability index and the fairness index of the passenger group; from the comprehensive perspective of supply and demand, from the dimension of ecological value, we extract the individual driver's ecological stability index and the intelligent system's diversity index; from the comprehensive perspective of supply and demand, from the dimension of development value, we extract the individual driver's development index and the intelligent system's development index.

[0028] In this embodiment, the economic value dimension measurement indicators from the driver's perspective include: proposing the driver's profit efficiency index , calculated by the ratio of individual driver income to individual driver cost, is used to characterize the profitability of individual drivers. ,in Order price , The commission ratio taken by the platform. For the tip, Fuel / electricity and vehicle depreciation costs; propose operational efficiency indicators for intelligent systems , calculated by the ratio of the total value of crowdsourcing orders to the total operating cost of the intelligent system, is used to characterize the profitability of the driver group at the system level. ,in is the equivalent monetary cost of greenhouse gas emissions.

[0029] The individual driver's income stability index is calculated through the time series difference of the individual driver's income, and is used to characterize the stability at the individual driver level.

[0030] The fairness index of the intelligent system is calculated by the Gini coefficient of the individual benefits of the drivers in the intelligent system, which is used to characterize the degree of difference in the individual benefits of the drivers in the intelligent system.

[0031] In this embodiment, the measurement indicators of the social value dimension from the perspective of drivers include: proposing an indicator of the stability of individual driver income , calculated through the time series difference of individual drivers’ income, is used to characterize the stability of individual drivers. ; Propose fairness indicators for intelligent agent systems , the Gini coefficient of individual driver benefits in the intelligent system is calculated to characterize the degree of difference in individual driver benefits in the intelligent system. The driver benefits in the intelligent system are ranked. ,in, is the sorted value, is the number of observations, is the average value, x i For the i numerical values, x j For the j A numerical value.

[0032] The passenger's subjective satisfaction index is calculated through the passenger's satisfaction score and is used to characterize the passenger's subjective perception.

[0033] The objective performance indicators of the service process are calculated based on the actual analysis of the scenario and are used to reflect the objective performance of the service process.

[0034] In this embodiment, regarding the measurement index of the use value dimension from the perspective of passengers, the passenger's subjective satisfaction index is proposed. , calculated through the passenger satisfaction score, used to characterize the passenger's subjective perception, ,in For passengers k Ratings of orders,m For order volume; propose objective performance indicators for the service process , such as passenger waiting time, vehicle detour coefficient, etc., which are used to reflect the objective performance of the service process. ,in, t wait For waiting time, t drive is the travel time, l walk It is within walking distance.

[0035] The stability index of individual passengers is calculated by the temporal difference of individual passenger use value satisfaction, which is used to characterize the stability at the individual passenger level.

[0036] The fairness index of the passenger group is calculated by the Gini coefficient of use value satisfaction among the passenger group, which is used to characterize the degree of difference in use value satisfaction among the passenger group.

[0037] In this embodiment, regarding the measurement index of the social value dimension from the perspective of passengers, the stability index of individual passengers is proposed. , through the calculation of the temporal difference of individual passenger use value satisfaction, it is used to characterize the stability of individual passenger level. ; Propose fairness indicators for passenger groups , calculated through the Gini coefficient of use value satisfaction among passenger groups, which is used to characterize the degree of difference in use value satisfaction among passenger groups. .

[0038] The ecological stability index of individual drivers is calculated through the niche width of individual driver types, which is used to characterize the amount of resources that individual drivers can utilize in the system.

[0039] The diversity index of the intelligent agent system is calculated through the diversity index of the intelligent agent system, which is used to characterize the diversity of service types provided by the system.

[0040] In this embodiment, regarding the measurement indicators of the ecological value dimension from the perspective of supply and demand, the ecological stability index of individual drivers is proposed. , calculated through the niche width of individual driver types, is used to characterize the amount of resources that individual drivers can use in the system. ,in , service level s The number of drivers in q , p s For service level s The proportion of drivers in r is the total number of service levels, and the total number of drivers is Q ; Propose diversity indicators for intelligent agent systems , calculated through the diversity index of the intelligent agent system, which is used to characterize the diversity of service types provided by the system. .

[0041] The development index of individual drivers is calculated through the changing trend of the input-output ratio of individual drivers, and is used to characterize the development potential of individual drivers.

[0042] The development index of the intelligent agent system is calculated by the changing trend of the system input-output ratio, which is used to characterize the potential development space of the system.

[0043] In this embodiment, the measurement indicators of the development value dimension from the perspective of supply and demand include: proposing the development indicators of individual drivers , calculated through the change trend of the driver's input-output ratio, is used to characterize the development potential of individual drivers, ,in, V E1 Providing drivers with a profit efficiency and developing intelligent system development indicators , through the calculation of the changing trend of the system input-output ratio, it is used to characterize the potential development space of the system, ,in, V E2 For the operational efficiency of the intelligent system.

[0044] Extract and obtain the six indicators of the intelligent system's operational efficiency index, the intelligent system's fairness index, the intelligent system's objective performance index, the service group's fairness index, the intelligent system's diversity index, and the intelligent system's development index, and record them as .

[0045] S120: performing correlation analysis on different service efficiency indicators in the service efficiency data in pairs, and obtaining a time series of correlation coefficients between any two service efficiency indicators, as well as a mean and a standard deviation of the time series.

[0046] As a preferred embodiment, correlation analysis is performed on different service performance indicators in the service performance data in pairs to obtain a time series of correlation coefficients between any two service performance indicators, as well as a mean and standard deviation of the time series. Specifically, the following steps are performed: correlation analysis is performed on different service performance indicators in pairs to obtain the Pearson correlation coefficients of the two service performance indicators in units of one hour in a day, to obtain a time series of Pearson correlation coefficients between any two indicators, and to determine the mean and standard deviation of the time series.

[0047] In this embodiment, correlation analysis is performed on the two combinations, and the Pearson correlation coefficient of the two indicators in the last 24 hours is calculated at each hour to obtain the time series of the correlation coefficient between any two indicators in the intelligent system's operational efficiency index, the intelligent system's fairness index, the intelligent system's objective performance index, the service group's fairness index, the intelligent system's diversity index, and the intelligent system's development index, as well as the mean and standard deviation of the time series.

[0048] As a preferred embodiment, the time series of the correlation coefficient between any two service performance indicators satisfies the following relationship: ; ; The mean and standard deviation of the time series satisfy the relationship: ; Among them, x(t) and y(t) are any two service performance indicator sequences of length, and are the sequences obtained by truncating x(t) and y(t) hour by hour according to the length of 24 hours, , i is the order of each moment in 24 hours, r(t) is the and The Pearson correlation coefficient between them, the length of r(t) is n, is the mean of the time series, is the standard deviation of the time series. The starting time is t1=1.

[0049] In this embodiment, the observation values ​​of the six service performance indicators in the last 24 hours are intercepted at all times after the start 24 hours, thereby obtaining three one-dimensional matrices of length 24 hour by hour. Assuming that the two service performance indicator sequences x(t) and y(t) of length n are intercepted hour by hour according to the length of 24 hours, we can obtain and .

[0050] In this embodiment, correlation analysis is performed on any two of the six service efficiency indicators to obtain 360 time series of correlation coefficients; the mean and standard deviation of the time series of correlation coefficients are calculated to obtain 360 sets of service efficiency abnormality warning rules based on the correlation between the two indicators; the warning results are combined to give the overall intelligent system efficiency abnormality warning level. Based on the correlation of service efficiency indicators, the present invention can realize automatic warning of intelligent system.

[0051] S130: Determine the warning result of the intelligent system based on the service performance abnormality warning rule; wherein the warning rule is determined according to the mean and the standard deviation.

[0052] As a preferred embodiment, the warning rule is that at any time, the warning levels of any two different service performance indicators satisfy the relationship: ; in, For service efficiency I i and service performance I j The warning level, 0 means no warning. 1 means level 1 warning, 2 means level 2 warning. 3 indicates level 3 warning.

[0053] As a preferred embodiment, the warning result of the intelligent system is determined based on the service performance abnormality warning rules, including: determining the warning level of two service performance indicators in units of one hour in a day based on the service performance abnormality warning rules; and taking the maximum value of the warning levels as the warning result of the intelligent system at the current moment.

[0054] As a preferred embodiment, the early warning result satisfies the relationship: ; in, W ( t ) is the warning result, For service efficiency I i and service performance I j The maximum value is used as the warning result of the intelligent system at the current hour.

[0055] The abnormal warning device for service performance of an intelligent body system provided by the present invention is described below. The abnormal warning device for service performance of an intelligent body system described below and the abnormal warning method for service performance of an intelligent body system described above can be referred to each other.

[0056] Please refer to Figure 3 , Figure 3 A schematic diagram of the structure of an abnormal warning device for service efficiency of an intelligent system provided by the present invention.

[0057] The present invention also provides an intelligent body system service efficiency anomaly warning device, including: an acquisition module 310, used to obtain the service efficiency data of the intelligent body system to be warned; a correlation analysis module 320, used to perform correlation analysis on different service efficiency indicators in the service efficiency data in pairs, and obtain a time series of correlation coefficients between any two service efficiency indicators, as well as a mean and standard deviation of the time series; a warning module 330, used to determine the warning result of the intelligent body system based on the service efficiency anomaly warning rules; wherein the warning rules are determined according to the mean and standard deviation.

[0058] Figure 4 An example of a structural diagram of an electronic device is shown in FIG. Figure 4 As shown, the electronic device may include: a processor 401, a communications interface 402, a memory 403 and a communication bus 404, wherein the processor 401, the communications interface 402 and the memory 403 communicate with each other through the communication bus 404. The processor 401 may call the logic instructions in the memory 403 to execute the service efficiency warning method of the intelligent system, which includes: obtaining the service efficiency data of the intelligent system to be warned; performing correlation analysis on the combination of different service efficiency indicators in the service efficiency data, and obtaining the time series of the correlation coefficient between any two service efficiency indicators, as well as the mean and standard deviation of the time series; determining the warning result of the intelligent system based on the abnormal warning rule of service efficiency; wherein the warning rule is determined according to the mean and standard deviation.

[0059] In addition, the logic instructions in the above-mentioned memory 403 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0060] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the service efficiency warning method of the intelligent body system provided by the above methods, and the method includes: obtaining service efficiency data of the intelligent body system to be warned; performing correlation analysis on different service efficiency indicators in the service efficiency data in pairs to obtain a time series of correlation coefficients between any two service efficiency indicators, as well as the mean and standard deviation of the time series; determining the warning result of the intelligent body system based on the service efficiency abnormality warning rules; wherein the warning rules are determined according to the mean and standard deviation.

[0061] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the service efficiency warning method of the intelligent body system provided by the above-mentioned methods, the method comprising: obtaining service efficiency data of the intelligent body system to be warned; performing correlation analysis on pairwise combinations of different service efficiency indicators in the service efficiency data to obtain a time series of correlation coefficients between any two service efficiency indicators, as well as a mean and standard deviation of the time series; determining the warning result of the intelligent body system based on service efficiency abnormality warning rules; wherein the warning rules are determined according to the mean and standard deviation.

[0062] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0063] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0064] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for warning abnormal service performance of an intelligent agent system, characterized in that: include: Obtain service performance data of the intelligent system to be warned; Perform correlation analysis on the different service performance indicators in the service performance data in pairs, and obtain a time series of correlation coefficients between any two service performance indicators, as well as a mean and a standard deviation of the time series; The warning result of the intelligent system is determined based on the service performance abnormality warning rule; wherein the warning rule is determined according to the mean and the standard deviation.

2. The method for warning abnormal service performance of an intelligent agent system according to claim 1, characterized in that: The service performance data includes observation values ​​of one or more service performance indicators at each preset time interval; The service performance indicators include the operational efficiency indicators of the intelligent agent system, the fairness indicators of the intelligent agent system, the objective performance indicators of the intelligent agent system, the fairness indicators of the service group, the diversity indicators of the intelligent agent system, and the development indicators of the intelligent agent system.

3. The method for warning abnormal service performance of an intelligent agent system according to claim 1, characterized in that: The correlation analysis is performed on the different service performance indicators in the service performance data in pairs to obtain a time series of correlation coefficients between any two service performance indicators, as well as the mean and standard deviation of the time series, specifically including: The different service performance indicators are combined in pairs for correlation analysis, and the Pearson correlation coefficients of the two service performance indicators in units of one hour in a day are obtained to obtain a time series of the Pearson correlation coefficients between any two indicators, and the mean and standard deviation of the time series are determined.

4. The method for warning abnormal service performance of an intelligent agent system according to claim 1, characterized in that: The time series of the correlation coefficient between any two service performance indicators satisfies the relationship: ； ； The mean and standard deviation of the time series satisfy the relationship: ； Among them, x(t) and y(t) are any two service performance indicator sequences of length, and are the sequences obtained by truncating x(t) and y(t) hour by hour according to the length of 24 hours, , i is the order of each moment in 24 hours, r(t) is the and The Pearson correlation coefficient between them, the length of r(t) is n, is the mean of the time series, is the standard deviation of the time series.

5. The method for warning abnormal service performance of an intelligent agent system according to claim 1, characterized in that: The warning rule is that at any time, the warning levels of any two different service performance indicators satisfy the relationship: ； in, For service efficiency I i and service performance I j The warning level, 0 means no warning. 1 means level 1 warning, 2 means level 2 warning. 3 indicates level 3 warning.

6. The method for warning abnormal service performance of an intelligent agent system according to claim 1, characterized in that: The determining of the warning result of the intelligent agent system based on the abnormal service performance warning rule includes: Determine the warning level of the two service performance indicators in units of one hour in a day based on the service performance abnormality warning rule; The maximum value among the warning levels is used as the warning result of the intelligent agent system at the current moment.

7. The method for warning abnormal service performance of an intelligent agent system according to any one of claims 1 to 6, characterized in that: The early warning result satisfies the relationship: ； in, W ( t ) is the warning result, For service efficiency I i and service performance I j warning level.

8. An abnormal warning device for intelligent system service performance, characterized in that: include: An acquisition module, used to acquire service efficiency data of the intelligent system to be warned; A correlation analysis module, used to perform correlation analysis on different service performance indicators in the service performance data in pairs, to obtain a time series of correlation coefficients between any two service performance indicators, and a mean and a standard deviation of the time series; An early warning module is used to determine the early warning result of the intelligent system based on the service performance abnormality early warning rule; wherein the early warning rule is determined according to the mean and the standard deviation.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the method for abnormal warning of service performance of the intelligent body system as described in any one of claims 1 to 7 is implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, the method for abnormal warning of service performance of the intelligent agent system as described in any one of claims 1 to 7 is implemented.

Images