CN112835805A - Customer service system testing method and device and electronic equipment - Google Patents
Customer service system testing method and device and electronic equipment Download PDFInfo
- Publication number
- CN112835805A CN112835805A CN202110217708.2A CN202110217708A CN112835805A CN 112835805 A CN112835805 A CN 112835805A CN 202110217708 A CN202110217708 A CN 202110217708A CN 112835805 A CN112835805 A CN 112835805A
- Authority
- CN
- China
- Prior art keywords
- test
- node
- target
- customer service
- service system
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012360 testing method Methods 0.000 title claims abstract description 683
- 238000000034 method Methods 0.000 claims abstract description 59
- 238000012544 monitoring process Methods 0.000 claims description 46
- 230000002159 abnormal effect Effects 0.000 claims description 34
- 238000013101 initial test Methods 0.000 claims description 30
- 238000003062 neural network model Methods 0.000 claims description 27
- 230000005856 abnormality Effects 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 7
- 238000010998 test method Methods 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 7
- 230000003993 interaction Effects 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 230000010485 coping Effects 0.000 description 4
- 230000009191 jumping Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/36—Preventing errors by testing or debugging software
- G06F11/3668—Software testing
- G06F11/3672—Test management
- G06F11/3684—Test management for test design, e.g. generating new test cases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/36—Preventing errors by testing or debugging software
- G06F11/3668—Software testing
- G06F11/3672—Test management
- G06F11/3688—Test management for test execution, e.g. scheduling of test suites
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/36—Preventing errors by testing or debugging software
- G06F11/3668—Software testing
- G06F11/3672—Test management
- G06F11/3692—Test management for test results analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Hardware Design (AREA)
- Quality & Reliability (AREA)
- Biomedical Technology (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Debugging And Monitoring (AREA)
Abstract
The application discloses a method and a device for testing a customer service system and electronic equipment, wherein the method comprises the following steps: obtaining test configuration data; the test configuration data comprises target test data of at least one target test node, and node sequences are arranged among the target test nodes; inputting the test configuration data into a customer service system to be tested, so that the customer service system tests the target test node according to the target test data of the target test node according to the node sequence, and the output content of the customer service system on the target test node is obtained; and comparing the output content of the customer service system on the target test node with the corresponding preset standard content on the target test node to obtain the test result of the customer service system on the target test node.
Description
Technical Field
The application relates to the technical field of intelligent customer service, in particular to a method and a device for testing a customer service system and electronic equipment.
Background
In each service enterprise, in order to reduce labor cost, the consultation questions of the user are answered through the intelligent customer service system.
In order to ensure the normal operation of the intelligent customer service system, the built intelligent customer service system is usually tested before the intelligent customer service system is on-line.
In the conventional test method, a tester is required to monitor each test node of the intelligent customer service system, and if the tester is required to perform operations such as test data input or input option selection on each test node, the test efficiency of the intelligent customer service system is low.
Disclosure of Invention
In view of this, the present application provides a method and an apparatus for testing a customer service system, and an electronic device, so as to solve the technical problem of low testing efficiency of the customer service system.
The application provides a method for testing a customer service system, which comprises the following steps:
obtaining test configuration data; the test configuration data comprises target test data of at least one target test node, and node sequences are arranged among the target test nodes;
inputting the test configuration data into a customer service system to be tested, so that the customer service system tests the target test node according to the target test data of the target test node according to the node sequence, and the output content of the customer service system on the target test node is obtained;
and comparing the output content of the customer service system on the target test node with the corresponding preset standard content on the target test node to obtain the test result of the customer service system on the target test node.
The method, preferably, obtaining the test configuration data includes:
outputting a configuration interface, wherein the configuration interface comprises a plurality of test nodes to be selected, each test node to be selected corresponds to test data to be selected, and the test data to be selected is obtained according to historical test data;
receiving input operation aiming at a test node to be selected and test data to be selected in the configuration interface;
and obtaining at least one target test node and target test data of the target test node according to the input operation, wherein node sequences are arranged among the target test nodes.
The method, preferably, obtaining the test configuration data includes:
obtaining a current test case, wherein the current test case at least comprises a plurality of test nodes to be selected;
inputting the current test case into a neural network model to obtain at least one target test node output by the neural network model and test data of the target test node;
the neural network model is obtained by training a plurality of historical test cases, the historical test cases comprise a plurality of initial test nodes and at least one historical test node, the historical test nodes comprise historical test data, and the neural network model is trained by taking at least the initial test nodes as input samples and the historical test nodes and the historical test data as output samples.
In the above method, preferably, the neural network model takes the initial test node, the adjacent test nodes of the initial test node, and the historical test results of the initial test node as input samples;
the current test case also comprises the adjacent test nodes of the test nodes to be selected and the historical test results of the test nodes to be selected.
The above method, preferably, further comprises:
and outputting the output content of the customer service system on the target test node.
In the method, preferably, the node order between the target test nodes is generated based on a hop parameter between the target test nodes, and the hop parameter is used to characterize a hop adjacency relationship between the target test nodes.
The above method, preferably, further comprises:
acquiring monitoring data of the customer service system in the process of testing the target test node;
judging whether the customer service system has test abnormity on the target test node according to the monitoring data;
and under the condition that the customer service system has test exception on the target test node, acquiring a target exception type of the customer service system on the target test node, and executing operation corresponding to the target exception type.
The method above, preferably, the monitoring data comprises data in a plurality of monitoring dimensions;
wherein, according to the monitoring data, judging whether the customer service system has test abnormality on the target test node includes:
respectively obtaining an initial probability value of the customer service system on at least one abnormal type in the process of testing the target test node according to the data on each monitoring dimension in the monitoring data;
respectively counting the initial probability value corresponding to each monitoring dimension aiming at each abnormal type to obtain the abnormal probability value aiming at each abnormal type;
and judging whether the abnormal probability value is greater than or equal to an abnormal threshold value corresponding to the abnormal type so as to judge whether the customer service system has test abnormality on the target test node.
The application also provides a testing arrangement of customer service system, the device includes:
a configuration obtaining unit for obtaining test configuration data; the test configuration data comprises target test data of at least one target test node, and node sequences are arranged among the target test nodes;
the node testing unit is used for inputting the testing configuration data into a customer service system to be tested so that the customer service system tests the target testing node according to the target testing data of the target testing node according to the node sequence to obtain the output content of the customer service system on the target testing node;
and the result comparison unit is used for comparing the output content of the customer service system on the target test node with the corresponding preset standard content on the target test node so as to obtain the test result of the customer service system on the target test node.
The present application further provides an electronic device, including:
a memory for storing an application program and data generated by the application program running;
a processor for executing the application to implement: obtaining test configuration data; the test configuration data comprises target test data of at least one target test node, and node sequences are arranged among the target test nodes; inputting the test configuration data into a customer service system to be tested, so that the customer service system tests the target test node according to the target test data of the target test node according to the node sequence, and the output content of the customer service system on the target test node is obtained; and comparing the output content of the customer service system on the target test node with the corresponding preset standard content on the target test node to obtain the test result of the customer service system on the target test node.
According to the scheme, in the customer service system testing method, the customer service system testing device and the electronic equipment, after the target test data comprising at least one target test node and the test configuration data with the node sequence between the target test nodes are obtained, the test configuration data are input into the customer service system to be tested, so that the customer service system can test the target test nodes according to the node sequence and the target test data of the target test nodes, the output content of the customer service system on the target test nodes is further obtained, and based on the output content of the customer service system on the target test nodes and the corresponding preset standard content on the target test nodes, the test result of the customer service system on the target test nodes is obtained. Therefore, in the test process of the customer service system, the test on the plurality of test nodes can be realized without monitoring each test node of the intelligent customer service system by a tester, so that the test progress is accelerated, and the test efficiency of the customer service system is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
Fig. 1 is a flowchart of a method for testing a customer service system according to an embodiment of the present disclosure;
FIG. 2 is an exemplary diagram of a configuration interface in an embodiment of the present application;
FIG. 3 is a diagram illustrating an example of a customer service system testing in an embodiment of the present application;
fig. 4 is another flowchart of a method for testing a customer service system according to an embodiment of the present application;
fig. 5 is a partial flowchart of a testing method for a customer service system according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of a testing apparatus of a customer service system according to a second embodiment of the present application;
fig. 7 is another schematic structural diagram of a testing apparatus of a customer service system according to a second embodiment of the present application;
fig. 8 is a schematic structural diagram of an electronic device according to a third embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Referring to fig. 1, a flowchart of an implementation of a method for testing a customer service system according to an embodiment of the present application is provided, where the method may be applied to a computer or a server capable of establishing a data connection with the customer service system and performing data processing. The technical scheme in the embodiment is mainly used for improving the testing efficiency of testing the customer service system.
Specifically, the method in this embodiment may include the following steps:
step 101: test configuration data is obtained.
The test configuration data comprises target test data of at least one target test node, node sequences are arranged among the target test nodes, and the node sequences among the target test nodes represent the test sequences of the target test nodes to be tested.
It should be noted that the target test node may be a part of all test nodes included in a complete test case of the customer service system, and the node sequence between the target test nodes may be configured according to the requirement. For example, the node order between the target test nodes is generated based on hop parameters between the target test nodes that characterize the hop neighborhood between the target test nodes. The jump parameters can be configured in a corresponding configuration interface by a user, or can be obtained according to the initial node positions of the target test nodes in the complete test case. For example, a user connects each target test node on a configuration interface by using a connecting line to generate a jump parameter between each target test node, so as to represent a jump adjacency relationship between the target test nodes at two ends of the connecting line, and further generate a node sequence between the target test nodes based on the jump adjacency relationship, which can also be understood as a tested sequence between the target test nodes. For another example, after the target test nodes are obtained, the initial node position of each target test node is obtained in the complete test case, the target test nodes adjacent to the initial node position are automatically connected by the connecting line according to the sequence between the initial node positions to generate jump parameters between the target test nodes, so that the jump adjacency relation between the target test nodes at two ends of the connecting line is represented, and further the node sequence between the target test nodes is generated based on the jump adjacency relation.
It should be noted that the initial node positions of the target test nodes in the complete test case may be adjacent or not adjacent.
In one implementation manner, when obtaining the test configuration data in step 101, the configuration interface may be output for a user, and then the implementation may be performed based on an input operation of the user on the configuration interface, which is specifically as follows:
firstly, outputting a configuration interface, as shown in fig. 2, where the configuration interface may include a plurality of test nodes to be selected, the test nodes to be selected may include all test nodes in a complete test case, or may include only a part of test nodes, each test node to be selected corresponds to one or more test data to be selected, each test data to be selected is obtained according to historical test data, and based on this, a user may select or determine the test nodes to be selected in the configuration interface, connect the selected or determined test nodes to be selected by using a connection line, select or determine the test data to be selected of the test nodes to be selected, and finally perform a determination operation; then, receiving input operation aiming at the test node to be selected and the test data to be selected in the configuration interface, such as selection or determination operation of the test node to be selected and the test data to be selected by a user and connection operation among the test nodes, and further such as determination operation of the user, and the like; and finally, obtaining at least one target test node and target test data of the target test node according to the input operation, wherein node sequences are arranged among the target test nodes. For example, a test node to be selected or determined by a user in an input operation is taken as a target test node, a node sequence between the target test nodes is obtained according to a connecting line between the user and the target test node, and in addition, test data to be selected or determined by the user is taken as target test data of the corresponding target test node.
It should be noted that the test node to be selected in the configuration interface may be obtained according to the historical test case, and the test data to be selected of the test node to be selected may be obtained according to the historical test data.
Specifically, in this embodiment, a plurality of historical test cases may be used to train the constructed neural network model in advance, specifically, an initial test node in the historical test case is used as an input sample, the historical test nodes and the historical test data of the historical test nodes are used as output samples, training the neural network model, so that the trained neural network model can process the initial test nodes in the current test case, further outputting one or more current test nodes corresponding to the current test case and test data of the current test nodes, at this time, using the current test nodes as test nodes to be selected in the configuration interface, and the test data of the current test nodes are used as the test data to be selected of the test nodes to be selected in the configuration interface for the user to select or confirm.
Further, in the implementation scheme for obtaining the test node to be selected and the test data to be selected for the configuration interface, the neural network model may further use an initial test node in the historical test case, a test node adjacent to the initial test node, and a historical test result of the initial test node as input samples, and use a historical test node and historical test data in the historical test case as output samples for training, and after multiple training, the trained neural network model may process historical test results of the initial test node, the test node adjacent to the initial test node, and the initial test node in the current test case, and further output one or more current test nodes corresponding to the current test case and test data of the current test node.
It should be noted that the current test case mentioned in this embodiment refers to a test case used for testing the customer service system at this time. Specifically, the current test case may be a preset complete test case including all the test nodes, or the current test case may be a test case edited by the test nodes and including a part of the test nodes.
In another implementation manner, when obtaining the test configuration data in step 101, the obtaining of the test configuration data may be automatically implemented without the participation of a user, which is specifically as follows:
firstly, obtaining a current test case, wherein the current test case at least comprises a plurality of test nodes to be selected, and the test nodes to be selected can be all test nodes in the complete test case or part of test nodes; and then, inputting the current test case into the neural network model to obtain at least one target test node output by the neural network model and target test data of the target test node.
The neural network model is obtained by training a plurality of historical test cases, the historical test cases comprise a plurality of initial test nodes and at least one historical test node, the initial test nodes refer to all test nodes which are initially contained in the historical test cases and are not selected or confirmed by target test nodes, the historical test nodes refer to test nodes which are selected as the target test nodes in the historical test cases, the historical test nodes comprise historical test data, and the neural network model is trained by taking at least the initial test nodes as input samples and the historical test nodes and the historical test data as output samples.
Further, the neural network model may further take an initial test node in the historical test case, a test node adjacent to the initial test node, such as a test node before and after the initial test node, a historical test result of the initial test node, such as a result of test success or test failure, and the like as input samples, based on which, the current test case further includes the test node adjacent to the test node to be selected and the historical test result of the test node to be selected, and after the current test case is input to the neural network model, the neural network model may output at least one target test node and target test data of the target test node.
Step 102: and inputting the test configuration data into the customer service system to be tested so that the customer service system tests the target test node according to the target test data of the target test node according to the node sequence to obtain the output content of the customer service system on the target test node.
As shown in fig. 3, in this embodiment, the target test nodes in the test configuration data and the target test data of the target test nodes are input into the customer service system, and the customer service system sequentially processes the target test data of each target test node according to the sequence of the front and back neighbors between the target test nodes in the node sequence, so that the customer service system can obtain output content for the target test data of each target test node. For example, the customer service system performs voice recognition on the input voice data at each target test node, and then outputs a text reply or a voice reply for the voice data, thereby completing the test at the target test node.
It should be noted that the test case referred to in this application may be understood as a test item for a corresponding function of the customer service system, where the test node may be understood as a test link of the customer service system on the function, and the test data of the test node may be understood as test input data of the customer service system, such as voice input data or character input data.
Step 103: and comparing the output content of the customer service system on the target test node with the corresponding preset standard content on the target test node to obtain the test result of the customer service system on the target test node.
In this embodiment, the output content of the customer service system on the target test node is compared with the corresponding preset standard content, so that a test result representing whether the customer service system accurately replies on the target test node can be obtained.
According to the above scheme, in the testing method of the customer service system provided in the embodiment of the present application, after the target test data including at least one target test node is obtained and the test configuration data of the node sequence is provided between the target test nodes, the test configuration data is input into the customer service system to be tested, so that the customer service system can test the target test node according to the target test data of the target test node according to the node sequence, and further obtain the output content of the customer service system on the target test node, based on this, the output content of the customer service system on the target test node can be compared with the corresponding preset standard content on the target test node, so as to obtain the test result of the customer service system on the target test node. Therefore, in the embodiment, in the process of testing the customer service system, the test on the plurality of test nodes can be realized without monitoring each test node of the intelligent customer service system by a tester, so that the test progress is accelerated, and the test efficiency of the customer service system is improved.
In one implementation, after the output content of the customer service system on the target test node is obtained in step 102, the following steps may also be performed, as shown in fig. 4:
step 104: and outputting the output content of the customer service system on the target test node.
Specifically, in this embodiment, the output content of the customer service system on the target test node can be output to the terminal of the tester through the data connection with the terminal of the tester, and the tester is prompted to perform manual inspection and other processing in time.
In an implementation manner, in the process of testing the target test node by the customer service system in this embodiment, the following steps may be further included, as shown in fig. 5:
step 501: and acquiring monitoring data of the customer service system in the process of testing the target test node.
The monitoring data may include data in a plurality of monitoring dimensions, and the monitoring dimensions may be set according to requirements. For example, the monitoring data may include: the interaction times of the customer service system on the target test node, the interaction duration of the customer service system on the target test node, the reply content of the customer service system on the target test node, and the like.
Step 502: and judging whether the customer service system has test abnormity on the target test node according to the monitoring data, and executing step 503 if the customer service system has test abnormity on the target test node.
The data of the monitoring data in each monitoring dimension can be analyzed in the embodiment, such as numerical judgment and other processing, and whether the customer service system has test abnormality on the target test node or not is judged according to the analysis result, such as the numerical judgment result and the like.
In one implementation, step 502 may be implemented by:
respectively obtaining an initial probability value of the customer service system on at least one abnormal type in the process of testing the target test node according to data on each monitoring dimension in the monitoring data, for example, judging the data on each monitoring dimension in the monitoring data and a corresponding dimension threshold value on each abnormal type on the corresponding monitoring dimension, and taking a dimension probability value corresponding to the dimension threshold value as the initial probability value corresponding to the abnormal type on the corresponding monitoring dimension under the condition that the data on the monitoring dimension is greater than or equal to the corresponding dimension threshold value on the corresponding monitoring dimension on each abnormal type;
then, respectively counting the corresponding initial probability value on each monitoring dimension aiming at each abnormal type to obtain the abnormal probability value aiming at each abnormal type; for example, for each anomaly type, adding the corresponding initial probabilities in each monitoring dimension to obtain an anomaly probability value for each anomaly type;
and finally, judging whether the abnormal probability value is larger than or equal to an abnormal threshold value corresponding to the abnormal type so as to judge whether the customer service system has test abnormality on the target test node. For example, if the anomaly probability value is greater than or equal to the anomaly threshold corresponding to the anomaly type, it may be determined that the customer service system has a test anomaly on the target test node, and further, it may be determined that the customer service system has a target anomaly type corresponding to the anomaly threshold on the target test node.
For example, on the same target test node, if the number of interactions between the test systems implemented by the customer service system in the present application exceeds 5 times, the probability of the type of the dead cycle anomaly exceeds 30 percent, and if the interaction time between the test systems implemented by the customer service system in the present application exceeds 5 minutes, the probability of the type of the dead cycle anomaly reaches 20 percent, and so on, when the total probability of the total probabilities accumulated exceeds 82 percent, the occurrence of the dead cycle anomaly is determined.
Step 503: and acquiring a target exception type of the customer service system on the target test node, and executing an operation corresponding to the target exception type.
For example, in the case that the target exception type is a dead loop exception type, an operation of jumping out of a dead loop is performed, such as controlling the customer service system to stop testing, or controlling the customer service system to test the next target test node that is not tested in the node order.
Based on the above implementation, the present embodiment may also control the test flow of the customer service system by determining whether the output content of the customer service system on the target test node is the reply content for the target test data, for example, analyzing whether the output content of the customer service system on the target test node is the reply content aiming at the target test data or not through functional modules such as an inference engine and the like in the customer service system, and in case the output content of the customer service system on the target test node is not the reply content to the test data, in this embodiment, the customer service system may be controlled to test the target test node again according to the target test data of the target test node, interacting with the customer service system again until the end condition is met, so that the customer service system tests the next target test node which is not tested according to the node sequence;
wherein the end condition includes: the test times aiming at the target test node are larger than or equal to the time threshold value, or the output content of the customer service system on the target test node is the reply content aiming at the target test data.
Referring to fig. 6, a schematic structural diagram of a testing apparatus for a customer service system according to a second embodiment of the present application is provided, where the testing apparatus may be configured in a computer or a server capable of establishing a data connection with the customer service system and performing data processing. The technical scheme in the embodiment is mainly used for improving the testing efficiency of testing the customer service system.
Specifically, the apparatus in this embodiment may include the following units:
a configuration obtaining unit 601 configured to obtain test configuration data; the test configuration data comprises target test data of at least one target test node, and node sequences are arranged among the target test nodes;
a node testing unit 602, configured to input the test configuration data into a customer service system to be tested, so that the customer service system tests the target test node according to the target test data of the target test node in the node order, so as to obtain output content of the customer service system on the target test node;
a result comparing unit 603, configured to compare the output content of the customer service system on the target test node with a preset standard content corresponding to the target test node, so as to obtain a test result of the customer service system on the target test node.
According to the above scheme, in the testing device of the customer service system provided in the second embodiment of the present application, after the target test data including at least one target test node is obtained and the test configuration data of the node sequence is provided between the target test nodes, the test configuration data is input into the customer service system to be tested, so that the customer service system can test the target test node according to the target test data of the target test node according to the node sequence, and further obtain the output content of the customer service system on the target test node, based on this, the output content of the customer service system on the target test node can be compared with the corresponding preset standard content on the target test node, so as to obtain the test result of the customer service system on the target test node. Therefore, in the embodiment, in the process of testing the customer service system, the test on the plurality of test nodes can be realized without monitoring each test node of the intelligent customer service system by a tester, so that the test progress is accelerated, and the test efficiency of the customer service system is improved.
In one implementation, the configuration obtaining unit 601 is specifically configured to: outputting a configuration interface, wherein the configuration interface comprises a plurality of test nodes to be selected, each test node to be selected corresponds to test data to be selected, and the test data to be selected is obtained according to historical test data; receiving input operation aiming at a test node to be selected and test data to be selected in the configuration interface; and obtaining at least one target test node and target test data of the target test node according to the input operation, wherein node sequences are arranged among the target test nodes.
In one implementation, the configuration obtaining unit 601 is specifically configured to: obtaining a current test case, wherein the current test case at least comprises a plurality of test nodes to be selected; inputting the current test case into a neural network model to obtain at least one target test node output by the neural network model and test data of the target test node; the neural network model is obtained by training a plurality of historical test cases, the historical test cases comprise a plurality of initial test nodes and at least one historical test node, the historical test nodes comprise historical test data, and the neural network model is trained by taking at least the initial test nodes as input samples and the historical test nodes and the historical test data as output samples.
Optionally, the neural network model takes the initial test node, the test nodes adjacent to the initial test node, and the historical test result of the initial test node as input samples;
the current test case also comprises the adjacent test nodes of the test nodes to be selected and the historical test results of the test nodes to be selected.
In one implementation, the node test unit 602 is further configured to:
and outputting the output content of the customer service system on the target test node.
In one implementation, the node order between the target test nodes is generated based on a hop parameter between the target test nodes, the hop parameter being used to characterize a hop adjacency relationship between the target test nodes.
In one implementation, the apparatus in this embodiment may further include the following structure, as shown in fig. 7:
a test control unit 604, configured to obtain monitoring data of the customer service system in a process of testing the target test node; judging whether the customer service system has test abnormity on the target test node according to the monitoring data; and under the condition that the customer service system has test exception on the target test node, acquiring a target exception type of the customer service system on the target test node, and executing operation corresponding to the target exception type.
Optionally, the monitoring data includes data in a plurality of monitoring dimensions;
when determining whether the customer service system has test abnormality on the target test node according to the monitoring data, the test control unit 604 is specifically configured to: respectively obtaining an initial probability value of the customer service system on at least one abnormal type in the process of testing the target test node according to the data on each monitoring dimension in the monitoring data; respectively counting the initial probability value corresponding to each monitoring dimension aiming at each abnormal type to obtain the abnormal probability value aiming at each abnormal type; and judging whether the abnormal probability value is greater than or equal to an abnormal threshold value corresponding to the abnormal type so as to judge whether the customer service system has test abnormality on the target test node.
Referring to fig. 8, a schematic structural diagram of an electronic device according to a third embodiment of the present disclosure is provided, where the electronic device may be a computer or a server capable of establishing a data connection with a customer service system and performing data processing. The technical scheme in the embodiment is mainly used for improving the testing efficiency of testing the customer service system.
Specifically, the electronic device in this embodiment may include the following structure:
a memory 801 for storing an application program and data generated by the operation of the application program;
a processor 802 for executing the application to implement: obtaining test configuration data; the test configuration data comprises target test data of at least one target test node, and node sequences are arranged among the target test nodes; inputting the test configuration data into a customer service system to be tested, so that the customer service system tests the target test node according to the target test data of the target test node according to the node sequence, and the output content of the customer service system on the target test node is obtained; and comparing the output content of the customer service system on the target test node with the corresponding preset standard content on the target test node to obtain the test result of the customer service system on the target test node.
According to the above scheme, in the electronic device provided in the third embodiment of the present application, after the target test data including at least one target test node is obtained and the test configuration data has a node sequence between the target test nodes, the test configuration data is input into the customer service system to be tested, so that the customer service system can test the target test node according to the node sequence and the target test data of the target test node, and further obtain the output content of the customer service system on the target test node, and based on this, the output content of the customer service system on the target test node can be compared with the corresponding preset standard content on the target test node, so as to obtain the test result of the customer service system on the target test node. Therefore, in the embodiment, in the process of testing the customer service system, the test on the plurality of test nodes can be realized without monitoring each test node of the intelligent customer service system by a tester, so that the test progress is accelerated, and the test efficiency of the customer service system is improved.
Taking a customer service system of a certain bank in the financial industry as an example, aiming at the technical problem of low testing efficiency, the inventor of the application provides a bank customer service intelligent testing system established for the bank customer service system, and the bank customer service intelligent testing system based on flow jumping. For example, when a customer service intelligent test module is developed in a mobile phone bank, when a tester needs to test a customer service system, a flow template can be input into the test system, jump parameters can be set, and the corresponding nodes are directly jumped, so that the test time is saved, and meanwhile, the test system can intelligently respond according to the feedback of the customer service system. Based on the method, a tester inputs own test options and test voice or jump parameters into the mobile phone bank test module, and the test system can jump to the corresponding module directly according to the setting of the tester, so that the test time is saved; moreover, the test system collects all possible reply conditions of the customer service system and carries out intelligent handling according to the reply conditions, so that the intelligent level of the test system is improved.
Specifically, the test system implemented in the present application may include the following modules:
a test system jump module: the tester inputs own test options and test voice or jump parameters in the mobile phone bank test module, and the test system can directly jump to the corresponding module according to the setting of the tester, so that the test time is saved.
The intelligent coping module: the test system collects all possible reply conditions of the customer service system and carries out intelligent handling according to the reply conditions, and the intelligent level of the system is improved.
The intelligent testing system for the bank customer service based on the process jump can solve the problem of low testing efficiency at present, firstly, a customer service testing module is developed in a mobile phone bank, the module can directly guide a using flow chart of the customer service system into the module, the flow chart is displayed to a tester in a vivid and vivid mode, and the tester only needs to input digital selection or voice at each node of the flow chart;
the tester can also set a flow chart by himself, the tester can select a corresponding component in the mobile phone bank test module to complete connection by himself, the tester clicks to submit, and the test system can test by himself;
the method comprises the specific steps that a background system automatically fills information before a node in a flow link for testing, a task flow is transferred to a current node set by the tester and then reminds a client, namely, the client directly arrives at the node, and the client only needs to enter the test data required by the client at the node.
The specific method is that the historical test data is analyzed to obtain the branch number covered by case data in the historical data, the specific information of the branch and the historical error information, the information is used as model input, the selected test data is used as model output, the neural network structure is determined according to the number of the input and the output, and the number of parameters needing to be optimized in the genetic algorithm is further determined. In addition, the test sample can be used for verifying the prediction accuracy of the model to obtain an effective model, and the model is used for predicting and selecting test data, so that the effectiveness of the test data can be improved, the test system automatically fills historical test data into corresponding process nodes and walks to nodes set by testers to wait for the testers, and therefore the customer service system can achieve the aim of process jumping without being modified, and the test efficiency is improved.
Meanwhile, the test system is connected with a background expert system, the dialogue information of the test system and the customer service system is collected and input into the expert system, and whether the current test process has abnormal information or not and a corresponding method of the abnormality are judged through the system. The expert system consists of a knowledge base and an inference machine, wherein the knowledge base is a knowledge rule obtained by data analysis such as induction, summarization and the like, and comprises a method for judging whether the test system enters endless loop, a corresponding coping method and the like.
For example, rule 1: if the number of times of interaction between the test system and the customer service system of the same node exceeds 5 times, the probability of endless loop exceeds 30 percent, if the interaction time exceeds 5 minutes, the probability of endless loop reaches 20 percent, and the like, if the total probability exceeds 82 percent, the test system is the endless loop, and the corresponding method of the endless loop is to firstly inform the test personnel to end the case at the same time, and test the case with problems after giving priority to other cases.
In addition, the inference machine is established by adopting a machine learning method, an available machine learning model is obtained by analyzing historical data, then which rules in the knowledge base are met is judged according to the characteristics of the test case at this time, the rules are integrated together to judge integral probability information, whether the rules are abnormal or not is judged, if the rules are abnormal, a corresponding coping method is inquired, corresponding coping processing is automatically carried out, and delay of a test process due to faults is prevented. Meanwhile, a correct answer method of the customer service system is integrated in the knowledge base, and the test system can repeat voice information or return to the previous stage according to requirements through a matching answer method of the inference engine, such as the customer service system feeding back no repeated hearing request or returning to the previous stage, so that the intelligence level and the usefulness of the test system are improved, and the labor cost is reduced.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A method of testing a customer service system, the method comprising:
obtaining test configuration data; the test configuration data comprises target test data of at least one target test node, and node sequences are arranged among the target test nodes;
inputting the test configuration data into a customer service system to be tested, so that the customer service system tests the target test node according to the target test data of the target test node according to the node sequence, and the output content of the customer service system on the target test node is obtained;
and comparing the output content of the customer service system on the target test node with the corresponding preset standard content on the target test node to obtain the test result of the customer service system on the target test node.
2. The method of claim 1, wherein obtaining test configuration data comprises:
outputting a configuration interface, wherein the configuration interface comprises a plurality of test nodes to be selected, each test node to be selected corresponds to test data to be selected, and the test data to be selected is obtained according to historical test data;
receiving input operation aiming at a test node to be selected and test data to be selected in the configuration interface;
and obtaining at least one target test node and target test data of the target test node according to the input operation, wherein node sequences are arranged among the target test nodes.
3. The method of claim 1, wherein obtaining test configuration data comprises:
obtaining a current test case, wherein the current test case at least comprises a plurality of test nodes to be selected;
inputting the current test case into a neural network model to obtain at least one target test node output by the neural network model and test data of the target test node;
the neural network model is obtained by training a plurality of historical test cases, the historical test cases comprise a plurality of initial test nodes and at least one historical test node, the historical test nodes comprise historical test data, and the neural network model is trained by taking at least the initial test nodes as input samples and the historical test nodes and the historical test data as output samples.
4. The method of claim 3, wherein the neural network model takes the initial test node, neighboring test nodes of the initial test node, historical test results of the initial test node as input samples;
the current test case also comprises the adjacent test nodes of the test nodes to be selected and the historical test results of the test nodes to be selected.
5. The method of claim 1, further comprising:
and outputting the output content of the customer service system on the target test node.
6. The method of claim 1, wherein the node order between the target test nodes is generated based on a hop parameter between the target test nodes, the hop parameter characterizing a hop neighborhood relationship between the target test nodes.
7. The method of claim 1, further comprising:
acquiring monitoring data of the customer service system in the process of testing the target test node;
judging whether the customer service system has test abnormity on the target test node according to the monitoring data;
and under the condition that the customer service system has test exception on the target test node, acquiring a target exception type of the customer service system on the target test node, and executing operation corresponding to the target exception type.
8. The method of claim 7, wherein the monitoring data comprises data in a plurality of monitoring dimensions;
wherein, according to the monitoring data, judging whether the customer service system has test abnormality on the target test node includes:
respectively obtaining an initial probability value of the customer service system on at least one abnormal type in the process of testing the target test node according to the data on each monitoring dimension in the monitoring data;
respectively counting the initial probability value corresponding to each monitoring dimension aiming at each abnormal type to obtain the abnormal probability value aiming at each abnormal type;
and judging whether the abnormal probability value is greater than or equal to an abnormal threshold value corresponding to the abnormal type so as to judge whether the customer service system has test abnormality on the target test node.
9. A test apparatus for a customer service system, the apparatus comprising:
a configuration obtaining unit for obtaining test configuration data; the test configuration data comprises target test data of at least one target test node, and node sequences are arranged among the target test nodes;
the node testing unit is used for inputting the testing configuration data into a customer service system to be tested so that the customer service system tests the target testing node according to the target testing data of the target testing node according to the node sequence to obtain the output content of the customer service system on the target testing node;
and the result comparison unit is used for comparing the output content of the customer service system on the target test node with the corresponding preset standard content on the target test node so as to obtain the test result of the customer service system on the target test node.
10. An electronic device, comprising:
a memory for storing an application program and data generated by the application program running;
a processor for executing the application to implement: obtaining test configuration data; the test configuration data comprises target test data of at least one target test node, and node sequences are arranged among the target test nodes; inputting the test configuration data into a customer service system to be tested, so that the customer service system tests the target test node according to the target test data of the target test node according to the node sequence, and the output content of the customer service system on the target test node is obtained; and comparing the output content of the customer service system on the target test node with the corresponding preset standard content on the target test node to obtain the test result of the customer service system on the target test node.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110217708.2A CN112835805A (en) | 2021-02-26 | 2021-02-26 | Customer service system testing method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110217708.2A CN112835805A (en) | 2021-02-26 | 2021-02-26 | Customer service system testing method and device and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112835805A true CN112835805A (en) | 2021-05-25 |
Family
ID=75933783
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110217708.2A Pending CN112835805A (en) | 2021-02-26 | 2021-02-26 | Customer service system testing method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112835805A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111369081A (en) * | 2018-12-06 | 2020-07-03 | 北京嘀嘀无限科技发展有限公司 | Flow configuration method and device, electronic equipment and storage medium |
| CN111899883A (en) * | 2020-09-29 | 2020-11-06 | 平安科技（深圳）有限公司 | Disease prediction device, method, apparatus and storage medium for small sample or zero sample |
| CN111916111A (en) * | 2020-07-20 | 2020-11-10 | 中国建设银行股份有限公司 | Intelligent voice outbound method and device with emotion, server and storage medium |
-
2021
- 2021-02-26 CN CN202110217708.2A patent/CN112835805A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111369081A (en) * | 2018-12-06 | 2020-07-03 | 北京嘀嘀无限科技发展有限公司 | Flow configuration method and device, electronic equipment and storage medium |
| CN111916111A (en) * | 2020-07-20 | 2020-11-10 | 中国建设银行股份有限公司 | Intelligent voice outbound method and device with emotion, server and storage medium |
| CN111899883A (en) * | 2020-09-29 | 2020-11-06 | 平安科技（深圳）有限公司 | Disease prediction device, method, apparatus and storage medium for small sample or zero sample |
Non-Patent Citations (1)
| Title |
|---|
| 顾丽燕;望俊成;高腾;胡舣缘;: "智能客服系统测评分析", 中国科技资源导刊, no. 02, 28 March 2019 (2019-03-28), pages 79 - 84 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111177655B (en) | Data processing method and device and electronic equipment | |
| CN113010389A (en) | Training method, fault prediction method, related device and equipment | |
| US8010468B2 (en) | Method for wafer analysis with artificial neural network and system thereof | |
| CN112306816A (en) | Method and system for evaluating entity robot response based on deep learning | |
| CN112835805A (en) | Customer service system testing method and device and electronic equipment | |
| CN116431522A (en) | Automatic test method and system for low-code object storage gateway | |
| CN114519437B (en) | Cloud-based micro-service method and system for fault diagnosis analysis and repair reporting | |
| CN116435995A (en) | Time series processing method, computer readable storage medium and electronic device | |
| CN116383048A (en) | Software quality information processing method and device | |
| CN114840422A (en) | Test method, test device, electronic equipment and storage medium | |
| CN112015648A (en) | Test method, device, computer equipment and medium based on automation script | |
| CN116910274B (en) | Test question generation method and system based on knowledge graph and prediction model | |
| CN117828499B (en) | PCBA abnormal part determination method, system, storage medium and electronic equipment | |
| CN111160454B (en) | Quick change signal detection method and device | |
| CN116453437B (en) | Display screen module testing method, device, equipment and storage medium | |
| CN114154167A (en) | Safety detection model testing method and device, electronic equipment and storage medium | |
| CN118101532B (en) | Multi-protocol compatible network equipment self-adaptive test system and method | |
| KR102658875B1 (en) | Eddy current test data labeling system | |
| CN114817077B (en) | Method, system and network equipment for judging test quality and specification | |
| CN116737572A (en) | Internet-based application software testing method, system and storage medium | |
| CN118097899A (en) | Laboratory gas leakage alarm linkage control method | |
| KR20000051749A (en) | Automatic analyzer of trouble shooting in base station manager system method for solving the trouble | |
| CN114282728A (en) | Policy optimization processing method and device, storage medium and electronic device | |
| CN117171001A (en) | Automated testing based on intelligent exploration | |
| CN115878485A (en) | POS equipment automatic testing method, equipment and medium based on user behaviors |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |