CN116187741A

CN116187741A - Service system monitoring method and device and electronic equipment

Info

Publication number: CN116187741A
Application number: CN202211531683.4A
Authority: CN
Inventors: 汪自立; 马超; 夏粉; 蒋宁; 吴海英; 肖冰
Original assignee: Mashang Xiaofei Finance Co Ltd
Current assignee: Mashang Xiaofei Finance Co Ltd
Priority date: 2022-12-01
Filing date: 2022-12-01
Publication date: 2023-05-30

Abstract

The application discloses a service system monitoring method, a device and electronic equipment, which are used for solving the problem that the service system monitoring method in the related technology cannot realize accurate monitoring under the condition of external data change. The method comprises the following steps: acquiring a first service record set of a service system of a target service in a current monitoring period, wherein the first service record set comprises service records related to service performance indexes in the current monitoring period; acquiring a second service record set of the service system in a history period matched with the current monitoring period, wherein the second service record set comprises service records related to service performance indexes in the history period; determining abnormal probability of the service performance index in the current monitoring period based on the value type of the service record related to the service performance index and the value of the service record in each of the first service record set and the second service record set; based on the anomaly probability, service monitoring information of the service system is generated.

Description

Service system monitoring method and device and electronic equipment

Technical Field

The present disclosure relates to the field of computer technologies, and in particular, to a method and an apparatus for monitoring a service system, and an electronic device.

Background

The monitoring is the most important part of the product or service in the operation and even the whole life cycle, and the main function is to pre-warn risks in time in advance, capture and record problem events in advance and provide detailed data for tracing and positioning problems in the post. In the monitoring process of a service system, the most important is monitoring indexes (such as success rate, access amount and the like of the service), and the monitoring indexes are related to the service and are key points in the service application. Meanwhile, the important value of the monitoring index is to monitor the health state of the service and respond to the abnormal service caused by external or internal reasons of the system.

In the related art, whether the monitoring index is abnormal is mainly judged based on a preset threshold corresponding to the monitoring index, or whether the monitoring index is abnormal is judged by using an artificial intelligent model. However, both the two methods are affected by subjective factors such as human business knowledge and experience, so that the monitoring result is inaccurate, and especially in the case of external data change, the accuracy of the monitoring result cannot be ensured.

Disclosure of Invention

An object of the embodiment of the present application is to provide a method, an apparatus and an electronic device for monitoring a service system, which are used for solving a problem that the method for monitoring a service system in related technologies cannot realize accurate monitoring of the service system under the condition of external data change.

In order to achieve the above purpose, the embodiment of the present application adopts the following technical scheme:

in a first aspect, an embodiment of the present application provides a service system monitoring method, including:

acquiring a first service record set of a service system of a target service in a current monitoring period, wherein the first service record set comprises service records related to service performance indexes of the service system in the current monitoring period, and the service performance indexes comprise performance indexes of the service system related to the target service;

acquiring a second service record set of the service system in a history period matched with the current monitoring period, wherein the second service record set comprises service records related to the service performance index in the history period;

determining the abnormal probability of the service performance index in the current monitoring period based on the value type of the service record related to the service performance index, the value of each service record in the first service record set and the value of each service record in the second service record set;

and generating service monitoring information of the service system based on the abnormal probability of the service performance index.

In a second aspect, an embodiment of the present application provides a service system monitoring device, including:

a first obtaining unit, configured to obtain a first service record set of a service system of a target service in a current monitoring period, where the first service record set includes a service record related to a service performance index of the service system in the current monitoring period, and the service performance index includes a performance index of the service system related to the target service;

a second obtaining unit, configured to obtain a second service record set of the service system in a history period matched with the current monitoring period, where the second service record set includes service records related to the service performance index in the history period;

the determining unit is used for determining the abnormal probability of the service performance index in the current monitoring period based on the value type of the service record related to the service performance index, the value of each service record in the first service record set and the value of each service record in the second service record set;

and the monitoring unit is used for generating service monitoring information of the service system based on the abnormal probability of the service performance index.

In a third aspect, an embodiment of the present application provides an electronic device, including: a processor; a memory for storing the processor-executable instructions; wherein the processor is configured to execute the instructions to implement the method according to the first aspect.

In a fourth aspect, embodiments of the present application provide a computer-readable storage medium, which when executed by a processor of an electronic device, enables the electronic device to perform the method of the first aspect.

The above-mentioned at least one technical scheme that this application embodiment adopted can reach following beneficial effect:

because the service performance index is closely related to the service of the service system, is the key point of monitoring the service system, and the service record related to the service performance index is a factor directly influencing the service performance index, the service record related to the service performance index of the service system in the current monitoring period can reflect the performance of the service performance index in the current monitoring period, and the service record related to the service performance index of the service system in the history period matched with the current monitoring period can reflect the performance of the service performance index in the history period; in addition, the change rule of the business records of different value types along with time is different. Based on the analysis, the value of the service record in the current monitoring period and the value of the service record in the history period are analyzed by utilizing the value type of the service record related to the service performance index, so that the rule that the service record related to the service performance index changes along with time can be fully utilized to predict the abnormal probability of the service performance index in the current monitoring period, and the abnormal probability can reflect the abnormal probability of the service performance index in the current monitoring period; further, based on the abnormal probability of the service performance index, the service monitoring system of the service system is generated according to the rule of the service record related to the service performance index along with the time change, and the rule is a natural objective rule suitable for the change of external data and is not influenced by subjective factors such as artificial service knowledge and experience, so that the monitoring accuracy of the service system can be improved no matter whether the external data is changed or not.

Drawings

The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute an undue limitation to the application. In the drawings:

fig. 1 is a schematic flow chart of a method for monitoring a service system according to an embodiment of the present application;

fig. 2 is a schematic flow chart of a monitoring method of a service system according to another embodiment of the present application;

fig. 3 is a schematic structural diagram of a service system monitoring device according to an embodiment of the present application;

fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

For the purposes, technical solutions and advantages of the present application, the technical solutions of the present application will be clearly and completely described below with reference to specific embodiments of the present application and corresponding drawings. It will be apparent that the described embodiments are only some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.

The terms first, second and the like in the description and in the claims, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that embodiments of the present application may be implemented in sequences other than those illustrated or described herein. Furthermore, in the description and claims, "and/or" means at least one of the connected objects, and the character "/" generally means that the related objects are in an "or" relationship.

As described above, in the related art, two ways are mainly used to identify whether the monitoring index is abnormal. The first is a threshold mode, namely, a corresponding threshold is set for the monitoring index in advance, if the index value of the monitoring index at the current moment is larger or smaller than the threshold, the monitoring index is judged to be abnormal, and then an alarm is given. However, the threshold value of the mode is a static threshold value preset by a service person, is limited by the relevant knowledge and experience of the service person, has a certain subjective factor, particularly, under the condition of external data change, such as that a certain service is indirectly influenced by a certain rule or law, the difficulty of threshold value evaluation of the service person is increased, the influence of the subjective factor is increased, the problem that monitoring response to an abnormal event becomes insensitive due to unsuitable set threshold value is further easily caused, important abnormal information in a service system is lost, and the accuracy of a monitoring result is influenced.

The second is a supervised model mode, namely training a model for abnormality identification through the labeling of system features and experts, and analyzing monitoring indexes of the service system by using the model to realize the monitoring of the service system. However, in the case of external data changes, the marked abnormal historical data is no longer applicable, so that the model cannot accurately identify abnormal information in the service system, and the accuracy of the monitoring result is also affected.

In order to solve the problem that the service system monitoring method in the related art cannot accurately monitor the service system under the condition of external data change, the embodiment of the application aims to provide a service system monitoring method, because the service performance index is closely related to the service of the service system, which is the key point of monitoring the service system, and the service record related to the service performance index is a factor directly influencing the service performance index, the service record related to the service performance index of the service system in the current monitoring period can reflect the performance of the service performance index in the current monitoring period, and the service record related to the service performance index of the service system in the history period matched with the current monitoring period can reflect the performance of the service performance index in the history period; in addition, the change rule of the business records of different value types along with time is different. Based on the analysis, the value of the service record in the current monitoring period and the value of the service record in the history period are analyzed by utilizing the value type of the service record related to the service performance index, so that the rule that the service record related to the service performance index changes along with time can be fully utilized to predict the abnormal probability of the service performance index in the current monitoring period, and the abnormal probability can reflect the abnormal probability of the service performance index in the current monitoring period; further, based on the abnormal probability of the service performance index, the service monitoring system of the service system is generated according to the rule of the service record related to the service performance index along with the time change, and the rule is a natural objective rule suitable for the change of external data and is not influenced by subjective factors such as artificial service knowledge and experience, so that the monitoring accuracy of the service system can be improved no matter whether the external data is changed or not.

It should be understood that the service system monitoring method provided in the embodiments of the present application may be performed by an electronic device or software installed in the electronic device. The electronic devices referred to herein may include terminal devices such as smartphones, tablet computers, notebook computers, desktop computers, intelligent voice interaction devices, intelligent home appliances, smart watches, vehicle terminals, aircraft, etc.; alternatively, the electronic device may further include a server, such as an independent physical server, or may be a server cluster or a distributed system formed by a plurality of physical servers, or may be a cloud server that provides a cloud computing service.

The following describes in detail the technical solutions provided by the embodiments of the present application with reference to the accompanying drawings.

Referring to fig. 1, a flow chart of a method for monitoring a service system according to an embodiment of the present application is provided, and the method may include the following steps:

s102, acquiring a first service record set of a service system of a target service in a current monitoring period.

The first service record set comprises service records related to service performance indexes of the service system in the current monitoring period.

The current monitoring period refers to a first preset period before the current point in time. The first preset period may be set according to actual needs, which is not limited in the embodiment of the present application. For example, the first preset period is one day, and if the current time point is 8 am today, the current monitoring period is the period between 8 am yesterday and 8 am day.

Of course, in practical application, the service system may be monitored periodically. In this case, the current monitoring period is then the current period. For example, the monitoring period of the service system is 9 am every day, and if the current time point is 11 months and 1 day, the current monitoring period is a period from 9 am 10 months and 30 days to 9 am 11 months and 1 day.

The service performance index includes a performance index related to a target service of the service system, which may be specifically selected according to actual needs, which is not limited in the embodiment of the present application. The service record related to the service performance index in the current monitoring period is a factor affecting the index value of the service performance index in the current monitoring period, and is also called source data of the service performance index in the current period, which can reflect the performance of the service performance index in the current monitoring period. In practical applications, the service record may be selected according to a service performance index, which is not limited in the embodiment of the present application.

For example, if the target business is a complaint handling business and the business system is a complaint handling system for handling customer complaints, then the business performance metrics of the business system may include, for example, but not limited to, resolution, overall resolution, disambiguation population distribution, disambiguation age distribution, disambiguation gender distribution, etc. for each of the complaints. Wherein the business records related to the business performance indexes comprise complaint dialogue texts between clients and customer service, and for each complaint, the resolution of the complaint refers to the quantity ratio of the complaint dialogue texts which are resolved in the complaint dialogue texts related to the complaint, and the total resolution refers to the quantity ratio of the complaint dialogue texts which are resolved in all the complaint dialogue texts; the disambiguation population distribution comprises the number of complaint dialogue texts corresponding to each type of clients (such as students, social people and the like); the un-resolved age distribution comprises the number of complaint dialogue texts corresponding to the clients of each age group; the disambiguation profile includes the number of complaint dialog texts corresponding to customers of each gender (e.g., male, female), and so forth.

As another example, if the target service is a service recommendation service and the service system is a service recommendation system for making service recommendations, then the service performance indicators of the service system may include, for example, but not limited to: conversion per service, overall conversion, channel conversion, average age of conversion users, sex distribution of conversion users, etc. Wherein the business records related to the business performance indexes comprise service recommendation dialogue texts between users and the service recommendation system, and the conversion rate of the service refers to the ratio between the number of the service recommendation dialogue texts for completing conversion actions of the service and the number of the service recommendation dialogue texts related to the service; the total conversion rate is the ratio between the number of service recommendation dialogue texts for completing the conversion behavior and the number of service recommendation dialogue texts of the business system; for each channel, the conversion rate of the channel refers to the ratio between the number of service recommendation dialogue texts that complete the conversion action through the channel and the number of service recommendation dialogue texts associated with the channel; the average age of the conversion users comprises the number of users which are corresponding to each age group and complete the conversion behavior; the conversion user gender distribution includes the number of users completing the conversion behavior corresponding to each gender, and so on.

In practical application, the first service record set can be obtained by analyzing the historical operation record generated by the service system in the current monitoring period. The specific analysis means may be various analysis means commonly used in the art, and may be specifically selected according to actual needs, which is not limited in the embodiment of the present application. For example, if the service system is a complaint processing system, the historical operation record generated by the service system in the current monitoring period may include voice dialogue data of the service system in the current monitoring period, further, the voice dialogue data in the current monitoring period may be segmented by using a voice segmentation technology to obtain multiple segments of dialogue voices, and then each segment of dialogue voices is converted into a corresponding text by using an automatic voice recognition (Automatic Speech Recognition, ASR) technology, so that a complaint dialogue text in the current monitoring period, that is, a second service record set, may be obtained.

S104, acquiring a second business record set of the business system in a history period matched with the current monitoring period.

Wherein the second set of business records comprises business records associated with business performance indicators over a historical period of time.

The historical period that matches the current monitoring period may be a second preset period that precedes the current monitoring period. The second preset period may be set according to actual needs, which is not limited in the embodiment of the present application. For example, the second preset period may be 90 days, and if the current monitoring period is a period between 8 am yesterday and 8 am, then the historical period matching the current monitoring period is a period within 90 days before 8 am yesterday.

The service record related to the service performance index in the history period is a factor affecting the index value of the service performance index in the history period, also referred to as source data of the service performance index in the history period, which can reflect the performance of the service performance index in the history period.

For example, taking the above-described business system as a complaint handling system and its business performance index as an example, the second set of business records may include complaint dialogue text over a historical period of time. As another example, taking the service system as the service recommendation system and the service performance index thereof as an example, the second service record set may include service recommendation dialogue text in a history period.

In practical applications, the second service record set may be obtained by analyzing a history running record generated by the service system in a history period. The specific analysis means may be various analysis means commonly used in the art, and may be specifically selected according to actual needs, which is not limited in the embodiment of the present application. For example, if the service system is a complaint processing system, the history running record generated by the service system in the history period may include voice dialogue data of the service system in the history period, further, the voice dialogue data in the history period may be segmented by using a voice segmentation technology to obtain multiple segments of dialogue voices, and then each segment of dialogue voices is converted into a corresponding text by using an ASR technology, so that a complaint dialogue text in the history period, that is, the second service record set, may be obtained.

S106, determining the abnormal probability of the service performance index in the current monitoring period based on the value type of the service record related to the service performance index, the value of each service record in the first service record set and the value of each service record in the second service record set.

The value type of the service record refers to the value type of the service record, and specifically can comprise binary type, numerical type and multi-type. The binary type is that the value of the service record can only take one of the first value and the second value, for example, for the service performance index of a certain appeal and resolution, the related service record is complaint dialogue text, and the value can only take the resolution (which can be expressed by 1) or not take the resolution (which can be expressed by 0); the numerical value refers to that the value of the service record can be any numerical value, for example, for the service performance index of complaint processing duration, the service record related to the service record is a complaint dialogue text, and the value of the service record is the corresponding complaint processing duration; the multi-category type refers to that the service record takes the value of one candidate category of a plurality of candidate categories, for example, the service record related to the service record is complaint dialogue text for the service performance index of un-age distribution, and the value of the service record can be any one of the candidate categories of 0-18 years old, 19-30 years old, 31-40 years old, 40-60 years old and over 60 years old.

The change rule of the business records of different value types along with time is different. In S106, the service record in the current monitoring period and the service record in the history period are analyzed by using the value type of the service record related to the service performance index, so that the rule that the service record related to the service performance index changes along with time can be fully utilized to predict the abnormal probability of the service performance index in the current monitoring period, wherein the abnormal probability can reflect the possibility of the abnormal occurrence of the service performance index in the current monitoring period. For example, if the anomaly probability is larger, the probability that the traffic performance index is abnormal in the current monitoring period is higher; and if the abnormality probability is smaller, the possibility of abnormality of the service performance index in the current monitoring period is smaller.

Specifically, in order to fully utilize the law of time variation of each type of service record, so as to more accurately predict the abnormal probability of the service performance index in the current monitoring period, the following describes the calculation mode of the abnormal probability corresponding to each type of service record.

Case one: the value type of the service record related to the service performance is binary.

In this case, S108 may be specifically implemented as:

and step A1, determining the number of the first type of service records and the number of the second type of service records based on the value of each service record in the first service record set.

The first type of service records comprise service records with values of a first value in a first service record set, and the second type of service records comprise service records with values of a second value in the first service record set.

Illustratively, taking a service performance index as an example of a resolution corresponding to a certain claim, the method refers to the number ratio of the resolved complaint dialogue texts in the complaint dialogue texts related to the claim, namely, the following formula (1) shows:

where x represents the resolution of the claim, c represents the number of complaint dialogue texts associated with the claim, and a represents the number of complaint dialogue texts that have been resolved associated with the claim.

In this case, the business record associated with the resolution of the claim includes complaint dialogue text associated with the claim. For each complaint dialogue text related to the complaint, if the processing result of the complaint dialogue text is a harmony, the value of the complaint dialogue text is a first value 1; if the processing result of the complaint dialogue text is not decoded, the value of the complaint dialogue text is a second value of 0. In this case, the first set of business records includes complaint dialogue text associated with the complaint during the current monitoring period, the first type of business records being complaint dialogue text that has been and has been resolved in association with the complaint during the current monitoring period, and the second type of business records being complaint dialogue text that has not been and has been resolved in association with the complaint during the current monitoring period.

And step A2, determining the quantity ratio of the third type of business records in the second business record set based on the value of each business record in the second business record set, and taking the quantity ratio as a history index value of the business performance index in the history period.

The third type of service record is a service record with a value of a first value in the second service record set.

Still taking a service performance index as an example of a resolution corresponding to a certain requirement, the second service record set includes complaint dialogue text related to the requirement in a history period, and the third service record set includes complaint dialogue text related to the requirement in a history monitoring period. Accordingly, the ratio of the number of complaint dialogue texts which are already and are related to the complaints in the history monitoring period to the number of complaint dialogue texts which are related to the complaints in the history monitoring period is the history and resolution corresponding to a certain complaint in the history period.

And step A3, determining the abnormal probability of the service performance index in the current monitoring period based on the number of the first type service records, the number of the second type service records and the historical index value of the service performance index.

Specifically, the anomaly probability of the traffic performance index in the current monitoring period can be determined by the following formula (2):

Wherein, p represents the abnormal probability of the service performance index in the current monitoring period; a represents the number of the first type of service records in the first service record set; b represents the number of second-class business records in the first business record set; x represents a history index value of the traffic performance index in the history period; t represents time; Δ represents a preset granularity control parameter, the smaller the value thereof, the smaller the control granularity, and the larger the control granularity otherwise. In practical applications, the preset granularity control parameter Δ may be set according to actual needs, for example, according to expert experience, which is not limited in this embodiment of the present application.

It can be understood that, since the rule of the change of binary data along with time generally accords with the beta distribution (Beta Distribution), the abnormal probability of the service performance index in the current monitoring period is calculated by the formula, the rule of the change of binary service records along with time can be fully utilized, and the calculated abnormal probability is more accurate.

And a second case: the value type of the service record related to the service performance is numerical.

In this case, S108 may be specifically implemented as:

and B1, determining a first value mean value and a first value standard deviation corresponding to the first service record set based on the value of each service record in the first service record set.

Wherein the first value average refers to the value average of the service records in the first service record set, and can be determined by the ratio between the sum of the values of each service record in the first service record set and the number of service records contained in the first service record set, namely

Wherein (1)>

Represents the first value mean value, x _i Representing the value of the ith business record in the first business record set, NRepresenting the number of business records contained in the first set of business records.

The first standard deviation refers to the standard deviation of the values of the service records in the first service record set, which can be obtained by calculating based on the value of each service record in the first service record set and the first value average value by using a statistical analysis algorithm commonly used in the art, for example

Wherein sigma _curr Representing the first value standard deviation +.>

Represents the first value mean value, x _i The value of the ith service record in the first service record set is represented, and N represents the number of service records contained in the first service record set.

And B2, determining a second value mean value and a second value standard deviation corresponding to the second service record set based on the value of each service record in the second service record set.

The second value average refers to the value average of the service records in the second service record set. The second standard deviation of the values refers to the standard deviation of the values of the service records in the second service record set.

The specific implementation of step B2 is similar to that of step B1, and will not be described here again.

And B3, determining the abnormal probability of the service performance index in the current monitoring period based on the first value average value, the first value standard deviation, the second value average value and the second value standard deviation.

Specifically, the anomaly probability of the traffic performance index in the current monitoring period can be determined by the following formula (3):

wherein, p represents the abnormal probability of the service performance index in the current monitoring period;

representing a first value average, sigma _curr Representing the first value standard deviation +.>

Representing a second value of the mean value, sigma _hist And the second value standard deviation is represented, delta represents a preset granularity control parameter, and the smaller the value is, the smaller the control granularity is, and otherwise, the larger the control granularity is. In practical applications, the preset granularity control parameter Δ may be set according to actual needs, for example, according to expert experience, which is not limited in this embodiment of the present application.

And a third case: the value type of the service record related to the service performance is multi-category type.

In this case, S108 may be specifically implemented as:

and step C1, converting the value of each service record in the first service record set into a binary value under the target category.

For example, assuming that the range of values for each business record includes three candidate categories, category a, category B, and category C, then the value for each business record in the first set of business records may be converted to a binary type value under that category.

Specifically, for each service record, if the value of the service record is the class a, determining that the binary value of the service record under the class a is the first value; if the value of the service record is the category B, it may be determined that the binary value of the service record in the category a is the second value. Similar conversion processing can be performed for both category B and category C, thereby obtaining a binary type value for the business record under category B and a binary type value for the business record under category C.

And C2, converting the value of each service record in the second service record set into a binary value under the target category.

The target category is any candidate category in a plurality of candidate categories contained in the value range of the business record.

The specific implementation manner of the step C2 is similar to that of the step C1, and the description of the step C1 is specifically referred to above, and will not be repeated.

And C3, determining the number of the fourth type of service records and the number of the fifth type of service records corresponding to the target category based on the binary value of each service record in the first service record set under the target category.

The fourth type of service records comprise service records with binary values of a first numerical value in the first service record set, and the fifth type of service records comprise service records with binary values of a second numerical value in the first service record set.

The specific implementation manner of the step C3 is similar to that of the step A1 in the above case one, and the description of the step A1 may be specifically referred to and will not be repeated.

And C4, determining the quantity ratio of the sixth service records in the second service record set based on the binary value of each service record in the second service record set, and taking the quantity ratio as a history index value of the service performance index corresponding to the target class in the history period.

The sixth type of service record comprises a binary type service record with a first value in the second service record set.

The specific implementation manner of the step C4 is similar to that of the step A2 in the above case one, and the description of the step A2 may be specifically referred to hereinabove, which is not repeated.

And step C5, determining the abnormal probability of the service performance index in the current monitoring period based on the number of the fourth type service records corresponding to each candidate category in the value range, the number of the fifth type service categories corresponding to each candidate category and the historical index value of the service performance index corresponding to each candidate category.

More specifically, the number of fourth class business records corresponding to each candidate class, the number of fifth class business classes corresponding to each candidate class and the business performance index are based on the value rangeThe determining of the abnormal probability of the traffic performance index in the current monitoring period according to the historical index value may include: determining abnormal probability of the business performance index corresponding to the target class in the current monitoring period based on the number of the fourth type business records corresponding to the target class, the number of the fifth type business records and the historical index value of the business performance index corresponding to the target class; selecting the maximum abnormal probability from the abnormal probabilities corresponding to each candidate category in the value range of the service performance index as the abnormal probability of the service performance index in the current monitoring period, namely

Wherein p represents the abnormal probability of the service performance index in the current monitoring period, and max represents the maximum abnormal probability selected,/I>

And the abnormal probability corresponding to the ith candidate category in the value range of the business performance index is represented.

For example, assuming that the value range of each service record includes three candidate categories, namely category a, category B and category C, after calculating the abnormal probabilities of the service performance indexes corresponding to category a, category B and category C through the steps C1 to C4, the maximum abnormal probability can be selected from the abnormal probabilities as the abnormal probability of the service performance indexes in the current monitoring period, that is

Wherein, the maximum anomaly probability is selected>

Representing the abnormal probability of the business performance index corresponding to the class A,/for the business performance index>

Representing the abnormal probability of the business performance index corresponding to the category B, < ->

And the abnormal probability corresponding to the business performance index in the category C is represented.

It can be understood that by converting the multi-type data into binary data and then utilizing the characteristic that the law of the change of the binary data along with time generally accords with beta distribution (Beta Distribution), the abnormal probability of the service performance index in the current monitoring period is determined, the law of the change of the service record with time, which takes the value of the multi-type data, can be fully utilized, and the calculated abnormal probability is more accurate.

S108, generating service monitoring information of the service system based on the abnormal probability of the service performance index.

Specifically, based on the abnormal probability of the service performance index, whether the service performance index is abnormal or not can be determined, and in the case that the service performance index is abnormal, early warning information is output to indicate that the service performance index is abnormal, so that service personnel can take corresponding measures in time, and normal operation of the service system is ensured.

For example, if the abnormal probability of the service performance index is greater than or equal to the preset probability threshold, determining that the service performance index is abnormal, and further outputting early warning information indicating that the service performance index is abnormal; if the abnormal probability of the service performance index is smaller than the preset probability threshold, the service performance index is determined to be normal, and at the moment, the early warning information can not be output.

In order to further ensure the normal operation of the service system, as shown in fig. 2, in another embodiment of the present application, after S108, the service system monitoring method provided in one or more embodiments of the present application may further include:

s110, if the abnormal probability of the service performance index is greater than or equal to a preset probability threshold, determining the service performance index as an abnormal service performance index.

S112, obtaining the service record related to the abnormal service performance index in the current monitoring period from the first service record set as a target service record.

S114, optimizing the service processing strategy of the service system based on the target service record.

The service processing policy refers to a policy adopted by a service system for service processing. In practical application, the service processing strategies adopted by different service systems are different. For example, if the business system is a complaint handling system, the business handling policy may be a complaint response policy for handling customer complaints, such as how to respond for a particular complaint, etc.; if the business system is a service recommendation system, the business processing policy may be a service recommendation policy for making service recommendation, such as a recommendation channel, a recommendation period, etc. adopted for a certain product.

The service system monitoring method provided by the embodiment of the application can be applied to service system monitoring in various scenes. The following description is made in connection with two scenarios of customer complaint handling and service recommendation.

For a customer complaint processing scenario, that is, the target service is a complaint processing service, a service system in the scenario is a complaint processing system for processing customer complaints, and the service performance index of the service system may include, for example, but not limited to, resolution, total resolution, no-resolution population distribution, no-resolution age distribution, no-resolution sex distribution, and the like of each claim, and the service processing policy of the service system is a complaint response policy. Accordingly, the first set of business records includes complaint dialogue text associated with the business performance indicators during the current monitoring period, and the second set of business records includes complaint dialogue text associated with the business performance indicators during the historical period.

In this scenario, after the complaint dialogue text related to each service performance index in the current monitoring period and the complaint dialogue text related to each service performance index in the history period are analyzed and identified through the steps S102 and S110, in S112, the complaint dialogue text related to the abnormal service performance index in the current monitoring period may be obtained from the first service record set and used as the target complaint dialogue text; further, in S114, the target complaint dialogue text may be parsed based on the keywords in the target complaint dialogue text to obtain a complaint problem in the current monitoring period, and the complaint response policy of the complaint processing system may be updated based on the complaint problem.

For example, assuming that a law and regulation is issued by a relevant department on a certain day, a previous complaint response strategy is considered illegal or not compliant, which may cause a customer to question a corresponding complaint response strategy, thereby causing the complaint response strategy to fail and further affecting the resolution of the complaint processing system to be reduced. In contrast, through the steps S102 and S110, the complaint dialogue text related to each service performance index in the current monitoring period and the complaint dialogue text related to each service performance index in the history period are analyzed, so that three service performance index anomalies including the total resolution, the resolution under the a-complaint and the no-resolution population distribution can be identified; next, in S112, a complaint dialogue text related to the total resolution, a complaint dialogue text related to the resolution under the a complaint, and a complaint dialogue text related to the distribution of non-resolution groups in the current monitoring period may be obtained from the first service record set as target complaint dialogue texts; further, in S114, by analyzing the target dialogue texts and extracting the keywords therein, it may be determined that the complaint problem is that the type B customer is not satisfied with the complaint response policy related to the a complaint, and such complaint response policy may be optimized according to the related legal regulations.

For a service recommendation scenario, i.e. the target service is a service recommendation service, a service system in the scenario is a service recommendation system for making service recommendation, and service performance indexes of the service system may include, for example, but not limited to: conversion rate, overall conversion rate, conversion rate of each channel, average age of conversion users, sex distribution of conversion users, etc. of each service, and the business processing policy of the business system is a service recommendation policy. Accordingly, the first set of business records includes service recommendation dialogue text associated with the business performance indicators during the current monitoring period, and the second set of business records includes service recommendation dialogue text associated with the business performance indicators during the historical period.

In this scenario, after the service recommendation dialogue text related to each service performance index in the current monitoring period and the service recommendation dialogue text related to each service performance index in the history period are analyzed and identified through the steps S102 and S110, in S112, the service recommendation dialogue text related to the abnormal service performance index in the current monitoring period may be obtained from the first service record set and used as the target service recommendation dialogue text; further, in S114, the target service recommendation dialogue text may be parsed based on the keywords in the target service recommendation dialogue text, to obtain the association factor related to the service recommendation result in the current monitoring period, and to update the service recommendation policy of the service recommendation system based on the obtained association factor.

For example, suppose that a competitor of company a issues a product C and announces it through channel D, and that the product C has a significant preference, affecting the conversion rate of the same product C' of company a. In this regard, by analyzing the service recommendation dialogue text related to each service performance index in the current monitoring period and the service recommendation dialogue text related to each service performance index in the history period in the steps S102 and S110, it is possible to identify three service performance index anomalies, namely, the conversion rate of the product C ', the conversion rate of the D channel, and the average age of the converted user under the product C'; then, in S112, a complaint dialogue text related to the conversion rate of the product C ', a complaint dialogue text related to the conversion rate of the D channel, and a service recommendation dialogue text related to the average age of the converted user under the product C' in the current monitoring period may be obtained from the first service record set as target service recommendation dialogue texts; further, in S114, by analyzing the target service recommendation dialogue texts and extracting the keywords therein, it may be determined that the association factor affecting the service recommendation effect of the product C ' is loss of young female users of the product C ' in the D channel, and further, the service recommendation policy for the product C ' may be optimized for this association factor, for example, adding preferential activity information in the recommendation session for the product C ', or emphasizing the qualification and the resource of the company a in the recommendation session for the product C '.

According to the business system monitoring method provided by one or more embodiments of the present application, since the business performance index is related to the business of the business system, which is the key point of monitoring the business system, and the business record related to the business performance index is the factor directly influencing the business performance index, the business record related to the business performance index of the business system in the current monitoring period can reflect the performance of the business performance index in the current monitoring period, and the business record related to the business performance index of the business system in the history period matched with the current monitoring period can reflect the performance of the business performance index in the history period; in addition, the change rule of the business records of different value types along with time is different. Based on the analysis, the value of the service record in the current monitoring period and the value of the service record in the history period are analyzed by utilizing the value type of the service record related to the service performance index, so that the rule that the service record related to the service performance index changes along with time can be fully utilized to predict the abnormal probability of the service performance index in the current monitoring period, and the abnormal probability can reflect the abnormal probability of the service performance index in the current monitoring period; further, based on the abnormal probability of the service performance index, the service monitoring system of the service system is generated according to the rule of the service record related to the service performance index along with the time change, and the rule is a natural objective rule suitable for the change of external data and is not influenced by subjective factors such as artificial service knowledge and experience, so that the monitoring accuracy of the service system can be improved no matter whether the external data is changed or not.

The foregoing describes specific embodiments of the present disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

In addition, corresponding to the service system monitoring method shown in fig. 1, the embodiment of the application also provides a service system monitoring device. Referring to fig. 3, a schematic structural diagram of a service system monitoring device 300 according to an embodiment of the present application is provided, where the device 300 may include:

a first obtaining unit 310, configured to obtain a first service record set of a service system of a target service in a current monitoring period, where the first service record set includes a service record related to a service performance index of the service system in the current monitoring period, and the service performance index includes a performance index of the service system related to the target service;

A second obtaining unit 320, configured to obtain a second service record set of the service system in a history period matched with the current monitoring period, where the second service record set includes service records related to the service performance index in the history period;

a determining unit 330, configured to determine an abnormal probability of the service performance index in the current monitoring period based on a value type of the service record related to the service performance index, a value of each service record in the first service record set, and a value of each service record in the second service record set;

and the monitoring unit 340 is configured to generate service monitoring information of the service system based on the abnormal probability of the service performance index.

Optionally, the determining unit is specifically configured to:

if the value type of the service records is binary, determining the number of the first type of service records and the number of the second type of service records based on the value of each service record in the first service record set, wherein the first type of service records comprises the service records with the value of a first value in the first service record set, and the second type of service records comprises the service records with the value of a second value in the first service record set;

Determining the quantity ratio of third-class business records in the second business record set based on the value of each business record in the second business record set to be used as a historical index value of the business performance index in the historical period, wherein the third-class business records comprise business records with the value of the first value in the second business record set;

and determining the abnormal probability of the service performance index in the current monitoring period based on the number of the first-type service records, the number of the second-type service records and the historical index value of the service performance index.

Optionally, the determining unit is specifically configured to: if the value type of the service record is numerical, determining a first value mean value and a first value standard deviation corresponding to the first service record set based on the value of each service record in the first service record set; determining a second value mean value and a second value standard deviation corresponding to the second service record set based on the value of each service record in the second service record set; and determining the abnormal probability of the service performance index in the current monitoring period based on the first value average value, the first value standard deviation, the second value average value and the second value standard deviation.

Optionally, the determining unit is specifically configured to:

if the value type of the service record is multi-category type, converting the value of each service record in the first service record set into binary type value under a target category, and converting the value of each service record in the second service record set into binary type value under the target category, wherein the target category is any one of a plurality of candidate categories contained in the value range of the service record;

determining the number of fourth-type service records and the number of fifth-type service records corresponding to the target category based on the binary value of each service record in the first service record set under the target category, wherein the fourth-type service records comprise service records with binary values of first values in the first service record set, and the fifth-type service records comprise service records with binary values of second values in the first service record set;

determining the quantity ratio of a sixth type of service record in the second service record set based on the binary value of each service record in the second service record set to be used as a history index value corresponding to the service performance index in the target category in the history period, wherein the sixth type of service record comprises the service record with the binary value of the first value in the second service record set;

And determining the abnormal probability of the service performance index in the current monitoring period based on the number of the fourth-class service records corresponding to each candidate class in the value range, the number of the fifth-class service class corresponding to each candidate class and the historical index value corresponding to each candidate class of the service performance index.

Optionally, the determining unit determines, based on the number of fourth-class service records corresponding to each candidate class in the value range, the number of fifth-class service classes corresponding to each candidate class, and the historical index value of the service performance index corresponding to each candidate class, an abnormal probability of the service performance index in the current monitoring period, where the determining unit includes:

determining the abnormal probability of the service performance index corresponding to the target class in the current monitoring period based on the number of the fourth class service records and the number of the fifth class service records corresponding to the target class and the historical index value of the service performance index corresponding to the target class;

and selecting the maximum abnormal probability from the abnormal probabilities corresponding to each candidate category in the value range of the service performance index as the abnormal probability of the service performance index in the current monitoring period.

Optionally, the apparatus further comprises an optimization unit;

the optimizing unit is used for: after the monitoring unit generates the service monitoring information of the service system based on the abnormal probability of the service performance index, if the abnormal probability is greater than or equal to a preset probability threshold value, determining the service performance index as an abnormal service performance index; acquiring service records related to the abnormal service performance indexes in the current monitoring period from the first service record set as target service records; and optimizing the service processing strategy of the service system based on the target service record.

Optionally, the target service is a complaint processing service, the service system is a complaint processing system for processing customer complaints, the first service record set includes a complaint dialogue text related to the service performance index in the current monitoring period, the target service record is a target complaint dialogue text, and the service processing policy includes a complaint response policy;

the optimizing unit obtains, from the first service record set, a service record related to the abnormal service performance index in the current monitoring period as a target service record, including: acquiring complaint dialogue texts related to the abnormal business performance indexes in the current monitoring period from the first business record set as target complaint dialogue texts;

The optimizing unit optimizes the service processing policy of the service system based on the target service record, including: analyzing the target complaint dialogue text based on the keywords in the target complaint dialogue text to obtain complaint problems in the current monitoring period; updating the complaint response strategy of the complaint processing system based on the complaint problem.

Optionally, the target service is a service recommendation service, the service system is a service recommendation system for performing service recommendation, the first service record set includes a service recommendation dialogue text related to the service performance index in a current monitoring period, the target service record is a target service recommendation dialogue text, and the service processing policy includes a service recommendation policy;

the optimizing unit obtains, from the first service record set, a service record related to the abnormal service performance index in the current monitoring period as a target service record, including: acquiring service recommendation dialogue texts related to the abnormal service performance indexes in the current monitoring period from the first service record set as target service recommendation dialogue texts;

The optimizing unit optimizes the service processing policy of the service system based on the target service record, including: analyzing the target service recommendation dialogue text based on the keywords in the target service recommendation dialogue text to obtain association factors related to service recommendation results in the current monitoring period; and updating the service recommendation strategy of the service recommendation system based on the association factors.

It is obvious that the service system monitoring device provided in the embodiment of the present application can be used as an execution subject of the service system monitoring method shown in fig. 1, for example, step S102 in the service system monitoring method shown in fig. 1 may be executed by the first acquiring unit in the service system monitoring device shown in fig. 3, step S104 may be executed by the second acquiring unit in the service system monitoring device, step S106 may be executed by the determining unit in the service system monitoring device, and step S108 may be executed by the monitoring unit in the service system monitoring device.

According to another embodiment of the present application, each unit in the service system monitoring device shown in fig. 3 may be separately or completely combined into one or several other units to form a structure, or some (some) unit(s) of the units may be further split into a plurality of units with smaller functions to form a structure, which may achieve the same operation without affecting the implementation of the technical effects of the embodiments of the present application. The above units are divided based on logic functions, and in practical applications, the functions of one unit may be implemented by a plurality of units, or the functions of a plurality of units may be implemented by one unit. In other embodiments of the present application, the service system monitoring device may also include other units, and in practical applications, these functions may also be implemented with assistance of other units, and may be implemented by cooperation of multiple units.

According to another embodiment of the present application, the traffic system monitoring apparatus as shown in fig. 3 may be constructed by running a computer program (including program code) capable of executing the steps involved in the respective methods as shown in fig. 1 on a general-purpose computing device such as a computer including a processing element such as a central processing unit (Central Processing Unit, CPU), a random access storage medium (Random Access Memory, RAM), a Read-Only Memory (ROM), and a storage element, and the traffic system monitoring method of the present application is implemented. The computer program may be recorded on, for example, a computer readable storage medium, transferred to, and run in, an electronic device via the computer readable storage medium.

Fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present application. Referring to fig. 4, at the hardware level, the electronic device includes a processor, and optionally an internal bus, a network interface, and a memory. The Memory may include a Memory, such as a Random-Access Memory (RAM), and may further include a non-volatile Memory (non-volatile Memory), such as at least 1 disk Memory. Of course, the electronic device may also include hardware required for other services.

The processor, network interface, and memory may be interconnected by an internal bus, which may be an ISA (Industry Standard Architecture ) bus, a PCI (Peripheral Component Interconnect, peripheral component interconnect standard) bus, or EISA (Extended Industry Standard Architecture ) bus, among others. The buses may be classified as address buses, data buses, control buses, etc. For ease of illustration, only one bi-directional arrow is shown in FIG. 4, but not only one bus or type of bus.

And the memory is used for storing programs. In particular, the program may include program code including computer-operating instructions. The memory may include memory and non-volatile storage and provide instructions and data to the processor.

The processor reads the corresponding computer program from the nonvolatile memory to the memory and then runs, and a service system monitoring device is formed on a logic level. The processor is used for executing the programs stored in the memory and is specifically used for executing the following operations: acquiring a first service record set of a service system of a target service in a current monitoring period, wherein the first service record set comprises service records related to service performance indexes of the service system in the current monitoring period, and the service performance indexes comprise performance indexes of the service system related to the target service; acquiring a second service record set of the service system in a history period matched with the current monitoring period, wherein the second service record set comprises service records related to the service performance index in the history period; determining the abnormal probability of the service performance index in the current monitoring period based on the value type of the service record related to the service performance index, the value of each service record in the first service record set and the value of each service record in the second service record set; and generating service monitoring information of the service system based on the abnormal probability of the service performance index.

The method executed by the service system monitoring device disclosed in the embodiment shown in fig. 1 of the present application may be applied to a processor or implemented by the processor. The processor may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in a processor or by instructions in the form of software. The processor may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; but also digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The disclosed methods, steps, and logic blocks in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the embodiments of the present application may be embodied directly in hardware, in a decoded processor, or in a combination of hardware and software modules in a decoded processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in a memory, and the processor reads the information in the memory and, in combination with its hardware, performs the steps of the above method.

The electronic device may further execute the method of fig. 1 and implement the functions of the service system monitoring device in the embodiments shown in fig. 1 and fig. 2, which are not described herein again.

Of course, other implementations, such as a logic device or a combination of hardware and software, are not excluded from the electronic device of the present application, that is, the execution subject of the following processing flow is not limited to each logic unit, but may be hardware or a logic device.

The present embodiments also provide a computer readable storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by a portable electronic device comprising a plurality of application programs, enable the portable electronic device to perform the method of the embodiment of fig. 1, and in particular to: acquiring a first service record set of a service system of a target service in a current monitoring period, wherein the first service record set comprises service records related to service performance indexes of the service system in the current monitoring period, and the service performance indexes comprise performance indexes of the service system related to the target service; acquiring a second service record set of the service system in a history period matched with the current monitoring period, wherein the second service record set comprises service records related to the service performance index in the history period; determining the abnormal probability of the service performance index in the current monitoring period based on the value type of the service record related to the service performance index, the value of each service record in the first service record set and the value of each service record in the second service record set; and generating service monitoring information of the service system based on the abnormal probability of the service performance index.

In summary, the foregoing description is only a preferred embodiment of the present application, and is not intended to limit the scope of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

The system, apparatus, module or unit set forth in the above embodiments may be implemented in particular by a computer chip or entity, or by a product having a certain function. One typical implementation is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.

In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for system embodiments, since they are substantially similar to method embodiments, the description is relatively simple, as relevant to see a section of the description of method embodiments.

Claims

1. A method for monitoring a service system, comprising:

2. The method of claim 1, wherein the determining the probability of abnormality of the traffic performance indicator during the current monitoring period based on the type of value of the traffic record associated with the traffic performance indicator, the value of each traffic record in the first set of traffic records, and the value of each traffic record in the second set of traffic records comprises:

3. The method of claim 1, wherein the determining the probability of abnormality of the traffic performance indicator during the current monitoring period based on the type of value of the traffic record associated with the traffic performance indicator, the value of each traffic record in the first set of traffic records, and the value of each traffic record in the second set of traffic records comprises:

if the value type of the service record is numerical, determining a first value mean value and a first value standard deviation corresponding to the first service record set based on the value of each service record in the first service record set;

Determining a second value mean value and a second value standard deviation corresponding to the second service record set based on the value of each service record in the second service record set;

and determining the abnormal probability of the service performance index in the current monitoring period based on the first value average value, the first value standard deviation, the second value average value and the second value standard deviation.

4. The method of claim 1, wherein the determining the probability of abnormality of the traffic performance indicator during the current monitoring period based on the type of value of the traffic record associated with the traffic performance indicator, the value of each traffic record in the first set of traffic records, and the value of each traffic record in the second set of traffic records comprises:

5. The method of claim 4, wherein determining the anomaly probability of the traffic performance indicator in the current monitoring period based on the number of fourth class traffic records corresponding to each candidate class, the number of fifth class traffic classes corresponding to each candidate class, and the historical indicator value of the traffic performance indicator corresponding to each candidate class in the value range comprises:

6. The method of claim 1, wherein after generating traffic monitoring information for the traffic system based on the anomaly probability for the traffic performance indicator, the method further comprises:

If the abnormal probability is greater than or equal to a preset probability threshold, determining the service performance index as an abnormal service performance index;

acquiring service records related to the abnormal service performance indexes in the current monitoring period from the first service record set as target service records;

and optimizing the service processing strategy of the service system based on the target service record.

7. The method of claim 6, wherein the target business is a complaint handling business, the business system is a complaint handling system for handling customer complaints, the first set of business records includes complaint dialogue text associated with the business performance index for a current monitoring period, the target business records are target complaint dialogue text, and the business handling policy includes a complaint response policy;

the obtaining, from the first service record set, a service record related to the abnormal service performance index in the current monitoring period as a target service record includes:

acquiring complaint dialogue texts related to the abnormal business performance indexes in the current monitoring period from the first business record set as target complaint dialogue texts;

The optimizing the service processing policy of the service system based on the target service record includes:

analyzing the target complaint dialogue text based on the keywords in the target complaint dialogue text to obtain complaint problems in the current monitoring period;

updating the complaint response strategy of the complaint processing system based on the complaint problem.

8. The method of claim 6, wherein the target service is a service recommendation service, the service system is a service recommendation system for making service recommendations, the first set of service records includes service recommendation dialogue text associated with the service performance indicator during a current monitoring period, the target service records are target service recommendation dialogue text, and the service processing policy includes a service recommendation policy;

acquiring service recommendation dialogue texts related to the abnormal service performance indexes in the current monitoring period from the first service record set as target service recommendation dialogue texts;

analyzing the target service recommendation dialogue text based on the keywords in the target service recommendation dialogue text to obtain association factors related to service recommendation results in the current monitoring period;

and updating the service recommendation strategy of the service recommendation system based on the association factors.

9. A business system monitoring device, characterized by comprising:

10. An electronic device, comprising:

a processor;

a memory for storing the processor-executable instructions;

wherein the processor is configured to execute the instructions to implement the method of any one of claims 1 to 8.

11. A computer readable storage medium, characterized in that instructions in the storage medium, when executed by a processor of an electronic device, enable the electronic device to perform the method of any one of claims 1 to 8.