CN113326203B

CN113326203B - Information recommendation method, equipment and storage medium

Info

Publication number: CN113326203B
Application number: CN202110694029.4A
Authority: CN
Inventors: 杨喜红; 卢道和; 周杰; 翁玉萍; 黄涛; 陈文龙; 袁文静
Original assignee: WeBank Co Ltd
Current assignee: WeBank Co Ltd
Priority date: 2021-06-22
Filing date: 2021-06-22
Publication date: 2022-08-12
Anticipated expiration: 2041-06-22
Also published as: CN113326203A; WO2022267364A1

Abstract

The information recommendation method disclosed by the application comprises the following steps: if a request message for requesting a test case including a target label is detected, acquiring m test cases to be recommended including the target label; determining a label included in each test case to be recommended to obtain n reference labels included in m test cases to be recommended; determining a first predicted value of each test case to be recommended for the target label and a second predicted value of each test case to be recommended for the target label based on the target label, the n reference labels and the m test cases to be recommended; determining the dynamic weight corresponding to each test case to be recommended; determining m third predicted values based on each dynamic weight, the corresponding first predicted value and the second predicted value; determining a first preset number of target recommended test cases from m test cases to be recommended based on the m third predicted values; and displaying a first preset number of target recommended test cases. The application also discloses an information recommendation device and a storage medium.

Description

Information recommendation method, equipment and storage medium

Technical Field

The present application relates to the field of testing technologies, and in particular, to an information recommendation method, device, and storage medium.

Background

With the rapid development of computer technology, more and more technologies are applied in the financial field, and the traditional financial industry is gradually changing to financial technology (Fintech), but higher requirements are also put forward on the technologies due to the requirements of the financial industry on safety and real-time performance. With the rapid development of internet technology, the internet has a great influence on the life, study, entertainment and other aspects of people. Before issuing various application programs, various tests need to be performed on the issued application programs by using various test cases to ensure that the performance of the issued application programs is most stable. At present, when a test case is determined to test an application program, the test case is determined by simply searching through a keyword, and the test is performed through the searched test case.

However, the determination method of the test case commonly used at present is simple, so that the determined test case has low matching degree, and the test effect is poor.

Content of application

In order to solve the technical problems, embodiments of the present application are expected to provide an information recommendation method, an information recommendation device, and a storage medium, so as to solve the problem that the current test case recommendation method is single, implement a test case recommendation method, accurately recommend a matched test case, and improve the test effect of the test case on an application program.

The technical scheme of the application is realized as follows:

in a first aspect, an information recommendation method includes:

if a request message for requesting a test case including a target label is detected, acquiring m test cases to be recommended including the target label; wherein m is an integer greater than or equal to 1;

determining the label included by each test case to be recommended to obtain n reference labels included by m test cases to be recommended; wherein n reference tags include the target tag, n being an integer greater than or equal to 1;

determining a first prediction value of each test case to be recommended for the target label and a second prediction value of each test case to be recommended for the target label based on the target label, the n reference labels and the m test cases to be recommended;

determining a dynamic weight corresponding to each test case to be recommended;

determining m third predicted values based on each dynamic weight, the corresponding first predicted value and the corresponding second predicted value;

determining a first preset number of target recommended test cases from m test cases to be recommended based on m third predicted values;

and responding to the request message, and displaying the first preset number of the target recommended test cases.

In a second aspect, an information recommendation apparatus, the apparatus comprising: a memory, a processor, and a communication bus; wherein:

the memory to store executable instructions;

the communication bus is used for realizing communication connection between the processor and the memory;

the processor is configured to execute the information recommendation program stored in the memory to implement the steps of the information recommendation method according to any one of the above items.

In a third aspect, a storage medium has stored thereon an information recommendation program which, when executed by a processor, implements the steps of the information recommendation method according to any one of the above.

In the embodiment of the application, if the information recommendation device monitors a request message for requesting a test case including a target label, after m test cases to be recommended of the target label are obtained, the label included in each test case to be recommended is determined, n reference labels included in the m test cases to be recommended are obtained, a first predicted value of each test case to be recommended for the target label and a second predicted value of each test case to be recommended for the target label are determined based on the target label, the n reference labels and the m test cases to be recommended, a dynamic weight corresponding to each test case to be recommended is determined, then m third predicted values are determined based on each dynamic weight, the corresponding first predicted value and the corresponding second predicted value, and a first preset number of target recommended test cases are determined from the m test cases to be recommended based on the m third predicted values, the method comprises the steps of responding to a request message, displaying a first preset number of target recommended test cases, balancing a first predicted value representing the similarity between the test cases and a second predicted value representing the similarity between the labels through the dynamic weight of each test case, determining to obtain a third predicted value of each test case for the target labels, and selecting a finally recommendable target recommended test case according to the relation between the third predicted values of the test cases.

Drawings

Fig. 1 is a schematic flowchart of an information recommendation method according to an embodiment of the present application;

fig. 2 is a schematic flowchart of another information recommendation method according to an embodiment of the present application;

fig. 3 is a schematic flowchart of another information recommendation method according to an embodiment of the present application;

FIG. 4 is a schematic diagram of a target relationship graph according to an embodiment of the present disclosure;

fig. 5 is a schematic diagram of data transmission provided in an embodiment of the present application;

fig. 6 is a schematic structural diagram of an information recommendation device according to an 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.

An embodiment of the present application provides an information recommendation method, which is applied to an information recommendation device and is shown in fig. 1, and the method includes the following steps:

step 101, if a request message for requesting a test case including a target label is detected, acquiring m test cases to be recommended including the target label.

Wherein m is an integer greater than or equal to 1.

In the embodiment of the application, the request message for requesting the test case including the target tag may be generated by a user performing a target tag selection operation on the information recommendation device, that is, the user selects a tag selection parameter on a test interface displayed on the information recommendation device, and when the target tag is selected and then clicked for confirmation, the request message is generated. The label is used for identifying the test case, and may be, for example, identification information for classifying the category, the test function, and the like of the test case, and one test case may include a plurality of different labels. The target tag includes at least one tag, but in some application scenarios, the target tag may also be null, that is, no tag is selected when the user selects a test case. When the target label is not empty, the corresponding m is the total number of the test cases with the target label in the test case set; when the target tag is empty, m is a preset empirical value, which may be, for example, an empirical value set by a user, usually by a tester according to the actual needs of the user, or an empirical value obtained by a large number of experiments, and the specific situation may be determined by the actual situation, which is not specifically limited herein.

And 102, determining the label included by each test case to be recommended to obtain n reference labels included by m test cases to be recommended.

Wherein the n reference tags include a target tag, and n is an integer greater than or equal to 1.

In the embodiment of the application, the label statistics of the determined m test cases to be recommended, which include the target label, is performed to obtain all n reference labels included in the m test cases to be recommended.

Step 103, determining a first predicted value of each test case to be recommended for the target label and a second predicted value of each test case to be recommended for the target label based on the target label, the n reference labels and the m test cases to be recommended.

The first predicted value is determined by the similarity between each test case to be recommended and each test case to be recommended except the corresponding test case to be recommended in the m test cases to be recommended, and the second predicted value is determined by the similarity between the target label and the labels except the target label in the n reference labels.

In the embodiment of the application, similarity between each test case to be recommended and other test cases is analyzed and calculated for a target label, n reference labels included in m test cases to be recommended and m test cases to be recommended, and a first predicted value of each test case to be recommended for the target label is determined; and for the target label, the n reference labels and the m test cases to be recommended, which are included in the m test cases to be recommended, analyzing and calculating the similarity between the target label and other labels except the target label in the n reference labels to obtain a second predicted value of each test case to be recommended for the target label.

And 104, determining the dynamic weight corresponding to each test case to be recommended.

In the embodiment of the application, the dynamic weight corresponding to each test case to be recommended is dynamically changed in different scenes, and is not unique and unchangeable, and the individual differences between different labels and the test cases can be obtained according to the different scenes of each test case to be recommended.

And 105, determining m third predicted values based on each dynamic weight, the corresponding first predicted value and the corresponding second predicted value.

In the embodiment of the application, each dynamic weight is adopted to dynamically adjust the corresponding first predicted value and the corresponding second predicted value to obtain a third predicted value corresponding to each test case to be recommended, so that m third predicted values corresponding to m test cases to be recommended respectively are obtained.

And 106, determining a first preset number of target recommended test cases from the m test cases to be recommended based on the m third predicted values.

In the embodiment of the application, m third predicted values corresponding to m test cases to be recommended are analyzed, so that a first preset number of target recommended test cases are determined from the m test cases to be recommended. The target recommended test case is a test case to be recommended, which has high conformity with the target label and can meet the test requirements of testers. The first preset number may be an empirical value obtained through a large number of experiments, or an empirical value determined based on the relationship between m according to an empirical algorithm, which may be determined by actual conditions, and is not limited herein.

And step 107, responding to the request message, and displaying a first preset number of target recommended test cases.

In the embodiment of the application, the information recommendation device responds to the request message, and displays the first preset number of target recommended test cases so that a tester can determine whether to test one or more functions of an object to be tested, such as an application program to be tested, based on the target recommended test cases.

Based on the foregoing embodiments, an embodiment of the present application provides an information recommendation method, which is applied to an information recommendation device and is shown in fig. 2, and the method includes the following steps:

step 201, if a request message for requesting a test case including a target tag is detected, acquiring m test cases to be recommended including the target tag.

Wherein m is an integer greater than or equal to 1.

In this embodiment, an information recommendation test device is taken as an example to describe the test device, the test device may be a device with a computing function, for example, a computer device, and a tester performs corresponding operations on the test device, for example, performs an operation on a test application interface of a test application program currently displayed by the test device, inputs a target label from a plurality of displayed labels, or directly inputs a program code including a test case obtained by a user and including the target label to generate a corresponding request message, and after receiving the request message, the test device selects all test cases to be recommended including the target label from a test case library corresponding to the test device, that is, obtains m test cases to be recommended including the target label. It should be noted that all test cases corresponding to the test device may be stored in a local storage area of the test device, and may also be stored in a cloud storage space accessible by the test device. All test cases corresponding to the test equipment can be all test cases in the whole test case library, and can also be part of test cases in the whole test case library which can only be accessed by the test equipment.

Step 202, determining the label included in each test case to be recommended, and obtaining n reference labels included in m test cases to be recommended.

In the embodiment of the application, it is assumed that m obtained test cases to be recommended including a target tag are 6 test cases to be recommended, including test case 1, test case 2, test case 3, test case 4, test case 5 and test case 6, and correspondingly, statistics is performed on the tags included in each test case to be recommended, for example, the test case 1 includes tag a and tag C by statistics, the test case 2 includes tag a and tag B, the test case 3 includes tag a and tag C, the test case 4 includes tag a and tag D, the test case 5 includes tag a, and the test case 6 includes tag a and tag B. Wherein, the target label is assumed to be a.

Step 203, determining a reference score of each test case to be recommended for each reference label based on the n reference labels and the m test cases to be recommended.

In the embodiment of the application, for the relationship between n reference tags and tags included in m test cases to be recommended, the reference score of each test case to be recommended for each reference tag is determined. The relationship between the n reference tags and the tags included in the m test cases to be recommended may be a relationship whether each test case to be recommended in the m test cases to be recommended includes a tag in the n reference tags.

Illustratively, based on 4 tags including tag a, tag B, tag C, tag D and 6 test cases to be recommended, including test case 1, test case 2, test case 3, test case 4, test case 5 and test case 6, reference score S of test case 1 for tag a can be determined _1A Reference score S for test case 1 for tag B _1B Test case 1 reference score S for tag C _1C Test case 1 reference score S for tag D _1D (ii) a Similarly, reference scores S of the test case 2 for the label A, the label B, the label C and the label D can be obtained _2A 、S _2B 、S _2C And S _2D Test case 3 reference score S for tag A, tag B, tag C, and tag D _3A 、S _3B 、S _3C And S _3D Test case 4 reference scores for tag A, tag B, tag C, and tag DS _4A 、S _4B 、S _4C And S _4D Test case 5 reference score S for tag A, tag B, tag C, and tag D _5A 、S _5B 、S _5C And S _5D Test case 6 reference scores S for tag A, tag B, tag C, and tag D _6A 、S _6B 、S _6C And S _6D 。

And 204, determining similarity parameters between each test case to be recommended and other test cases based on the reference scores of the m test cases to be recommended for the n reference labels, and obtaining m-1 first similarity parameters corresponding to each test case to be recommended.

And the other test cases are each test case to be recommended except for each corresponding test exception to be recommended in the m test cases to be recommended.

In the embodiment of the application, the reference score of each to-be-recommended test case for the n reference labels is obtained according to the reference scores of the m to-be-recommended test cases for the n reference labels, the reference score of each to-be-recommended test case for the n reference labels and the reference scores of other test cases for the n reference labels are subjected to similarity calculation analysis by a preset similarity calculation method, a first similarity parameter between each to-be-recommended test case and other test cases is determined, and the first similarity parameter between each to-be-recommended test case and other m-1 to-be-recommended test cases can be obtained according to each to-be-recommended test case, so that m-1 first similarity parameters can be obtained according to each to-be-recommended test case.

Illustratively, the reference scores S of the test case 1 for 4 tags are calculated _1A 、S _1B 、S _1C And S _1D Reference scores S for 4 tags with test case 2 _2A 、S _2B 、S _2C And S _2D First similarity parameter X between ₁₂ Calculating reference scores S of the test case 1 for 4 tags _1A 、S _1B 、S _1C And S _1D Reference scores S for 4 tags with test case 3 _3A 、S _3B 、S _3C And S _3D First similarity parameter X between ₁₃ Calculating reference scores S of the test case 1 for 4 tags _1A 、S _1B 、S _1C And S _1D Reference scores S for 4 tags with test case 4 _4A 、S _4B 、S _4C And S _4D First similarity parameter X between ₁₄ Calculating reference scores S of the test case 1 for 4 tags _1A 、S _1B 、S _1C And S _1D Reference scores S for 4 tags with test case 5 _5A 、S _5B 、S _5C And S _5D First similarity parameter X between ₁₅ Calculating reference scores S of the test case 1 for 4 tags _1A 、S _1B 、S _1C And S _1D Reference scores S for 4 tags related to test case 6 _6A 、S _6B 、S _6C And S _6D First similarity parameter X between ₁₆ And obtaining 5 first similarity parameters between the test case 1 and other 5 test cases. Wherein, the reference score S of the test case 1 for 4 labels _1A 、S _1B 、S _1C And S _1D Reference scores S for 4 tags with test case 2 _2A 、S _2B 、S _2C And S _2D First similarity parameter X between ₁₂ Can be calculated by formula

Calculated to obtain, and by the same way, X can be obtained ₁₃ ，X ₁₄ 、X ₁₅ And X ₁₆ 。

Similarly, 5 first similarity parameters X between the test case 2 and other 5 test cases can be obtained ₂₁ 、X ₂₃ 、X ₂₄ 、X ₂₅ And X ₂₆ 5 first similarity parameters X between the test case 3 and other 5 test cases ₃₁ 、X ₃₂ 、X ₃₄ 、X ₃₅ And X ₃₆ 5 first similarity parameters X between the test case 4 and other 5 test cases ₄₁ 、X ₄₂ 、X ₄₃ 、X ₄₅ And X ₄₆ Test case 5First similarity parameter X with other 5 test cases ₅₁ 、X ₅₂ 、X ₅₃ 、X ₅₄ And X ₅₆ First similarity parameter X between test case 6 and other 5 test cases ₆₁ 、X ₆₂ 、X ₆₃ 、X ₆₄ And X ₆₅ 。

And step 205, determining a first predicted value of each test case to be recommended for the target label based on m-1 first similarity parameters corresponding to each test case to be recommended.

In the embodiment of the application, for each test case to be recommended, m-1 first similarity parameters corresponding to the test case to be recommended are analyzed and processed, and a first predicted value of the test case for a target label is determined.

Illustratively, for test case 1, 5 first similarity parameters X for test case 1 ₁₂ 、X ₁₃ 、X ₁₄ 、X ₁₅ And X ₁₆ And analyzing and processing to obtain a first predicted value of the test case 1 for the target label A. For the same treatment of other test cases, detailed description is omitted here.

And step 206, determining error similarity parameters between the target label and other labels based on the reference scores of the n reference labels of the m test cases to be recommended, and obtaining n-1 second similarity parameters.

Wherein the other tags are each of the n reference tags except the target tag.

In the embodiment of the application, the reference scores of the m test cases to be recommended for the target label and the reference scores of the m test cases to be recommended for the other labels are selected for the reference scores of the n reference labels, and the two groups of reference scores are subjected to error similarity calculation analysis processing to obtain the second similarity parameters of the target label for the other labels. Since n reference tags are totally available, the second similarity parameters between the target tag and other n-1 other tags can be determined, so that n-1 second similarity parameters are obtained.

Illustratively, 4 reference targets are aimed at from 6 test cases to be recommendedIn the reference scores of the labels, reference scores corresponding to 6 test cases to be recommended aiming at the target label A are obtained, and S is obtained _1A 、S _2A 、S _3A 、S _4A 、S _5A And S _6A And when other labels are assumed as B, acquiring reference scores corresponding to the 6 test cases to be recommended aiming at the other labels B to obtain S _1B 、S _2B 、S _3B 、S _4B 、S _5B And S _6B Thus, can be to S _1A 、S _2A 、S _3A 、S _4A 、S _5A And S _6A And S _1B 、S _2B 、S _3B 、S _4B 、S _5B And S _6B Analyzing to determine a second similarity parameter X between the target label A and other labels B _AB (ii) a Similarly, a second similarity parameter X between the target tag a and the other tags C can be obtained _AC Second similarity parameter X between target label A and other labels D _AD Thus, 3 second similarity parameters X corresponding to the target tag a are obtained _AB 、X _AC And X _AD 。

And step 207, determining a second predicted value of each test case to be recommended for the target label based on the n-1 second similarity parameters.

In the embodiment of the application, n-1 second similarity parameters are analyzed and processed for each test case to be recommended, and a second predicted value of each test case to be recommended for the target label is obtained.

Illustratively, 3 second similarity parameters X corresponding to the target tag a _AB 、X _AC And X _AD And analyzing the relation between the corresponding test case 1 and the target label, and determining a second predicted value of the obtained test case 1 for the target label A. Similarly, test cases can be obtained2. And the test cases 3, 4, 5 and 6 respectively aim at the second predicted values of the target label.

And 208, determining the dynamic weight corresponding to each test case to be recommended.

In the embodiment of the application, the number of the labels included in each test case to be recommended and the number of the labels included in m test cases to be recommended are analyzed, and the dynamic weight corresponding to each test case to be recommended is determined and obtained.

And 209, determining m third predicted values based on each dynamic weight, the corresponding first predicted value and the corresponding second predicted value.

In the embodiment of the application, the dynamic weight corresponding to the test case 1, the first predicted value of the test case 1 and the second predicted value of the test case 2 are analyzed, and the third predicted value corresponding to the test case 1 is determined, and similarly, the third predicted values corresponding to the test case 2, the test case 3, the test case 4, the test case 5 and the test case 6 can be obtained respectively.

And step 210, determining a first preset number of target recommended test cases from the m test cases to be recommended based on the m third predicted values.

In other embodiments of the application, the m third predicted values are analyzed, for example, the m third predicted values may be sorted according to a magnitude relationship to obtain a sorting result, then a first preset number of third predicted values with a maximum value are selected, and test cases to be recommended corresponding to the first preset number of third predicted values are determined from the m test cases to be recommended and serve as a first preset number of target recommended test cases.

And step 211, responding to the request message, and displaying a first preset number of target recommended test cases.

In the embodiment of the application, after the first preset number of target recommended test cases are determined to be obtained, the request message is responded, and the first preset number of target recommended test cases are displayed in the corresponding display area, so that a tester can use the first predicted number of target recommended test cases to perform test analysis.

Therefore, the similarity between the test cases and the similarity between the target labels and other labels are comprehensively analyzed for the m test cases to be recommended and the n reference labels corresponding to the m test cases to be recommended, and the accuracy of the recommended first preset number of target recommended test cases is effectively improved.

Based on the foregoing embodiments, in other embodiments of the present application, step 203 may be implemented by steps 203a to 203 d:

step 203a, determining a preset score of each test case to be recommended for each reference label, and obtaining n preset scores of each test case to be recommended.

In the embodiment of the application, different preset scores are adopted for identification according to whether the test case to be recommended includes the reference tag, for example, when the test case to be recommended includes the reference tag, the preset score of the test case to be recommended for the reference tag may be set to a non-zero value, and when the test case to be recommended does not include the reference tag, the preset score of the test case to be recommended for the reference tag may be set to zero.

For example, when the test case to be recommended includes a reference tag, the preset score of the test case to be recommended for the reference tag may be set to 1, and when the test case to be recommended does not include the reference tag, the preset score of the test case to be recommended for the reference tag may be set to zero.

And 203b, performing operation processing on the n preset scores of each test case to be recommended to obtain a first numerical value.

In the embodiment of the application, the n preset scores of each test case to be recommended can be simply accumulated to obtain the first numerical value. In some application scenarios, the average value operation processing may be performed on the n preset scores of each test case to be recommended, so as to obtain a first numerical value.

And 203c, performing operation processing on each preset score and m of each test case to be recommended to obtain a second numerical value of each reference label corresponding to each test case to be recommended.

In the embodiment of the application, for each preset score and m of each test case to be recommended, an operation method capable of performing simple product operation or other operation methods such as weighted product operation may be adopted to perform operation processing, so as to obtain the second numerical value of each reference tag corresponding to each test case to be recommended.

And 203d, performing operation processing on the second numerical value and the first numerical value of each reference label corresponding to each test case to be recommended to obtain a reference score of each test case to be recommended for each reference label.

In the test of the application, the second numerical value and the first numerical value of each reference label corresponding to each test case to be recommended can be subjected to operation processing by adopting operation modes such as ratio operation or quotient calculation, so that the reference score of each test case to be recommended for each reference label is obtained. Therefore, the reference score of each test case to be recommended for each reference label is determined by the same reference score operation method, the consistency of the determined reference scores is effectively guaranteed, and the reliability of the determined reference scores is improved.

Based on the foregoing embodiments, in other embodiments of the present application, step 205 may be implemented by steps 205a to 205 c:

step 205a, selecting a second preset number of first target similarity parameters corresponding to each test case to be recommended from m-1 first similarity parameters corresponding to each test case to be recommended.

In the embodiment of the present application, the second preset number may be an empirical value obtained through a large number of experiments, may also be an empirical value calculated according to an empirical formula obtained through a large number of experiments, or may also be an empirical value set by a tester according to actual needs of the tester. In some application scenarios, the second preset number may be determined by calculating a product between m-1 and a preset ratio, where the preset ratio may be an empirical value obtained through a large number of experiments, or may be set by a tester according to actual requirements.

When a second preset number of first target similarity parameters are selected from m-1 first similarity parameters corresponding to each test case to be recommended, the m-1 first similarity parameters corresponding to each test case to be recommended are sorted in sequence based on magnitude relation, and then the first similarity parameters with the largest front second preset number are selected from the sorted m-1 first similarity parameters, so that the first target similarity parameters with the second preset number are obtained.

Exemplarily, assuming that the second preset number is 3, corresponding to 5 first similarity parameters X for the test case 1 ₁₂ 、X ₁₃ 、X ₁₄ 、X ₁₅ And X ₁₆ The 3 first target similarity parameters selected from the three sets of target similarity parameters are X ₁₂ 、X ₁₃ And X ₁₄ 。

Step 205b, determining the reference scores of the other corresponding test cases in each first target similarity parameter for the target tags from the reference scores of the m test cases to be recommended for the n reference tags, and obtaining a second preset number of first target scores.

In the embodiment of the application, from the reference scores of the m test cases to be recommended for the n reference labels, for the test case 1, the reference score is X based on 3 first target similarity parameters ₁₂ 、X ₁₃ And X ₁₄ Determining reference scores of the test cases 2, 3 and 4 for the target label A to obtain 3 first target scores S _2A 、S _3A And S _4A 。

Step 205c, determining a first predicted value of each test case to be recommended based on the second preset number of first target scores and the second preset number of first target similarity parameters.

In the embodiment of the application, the 3 first target scores and the 3 first target similarity parameters are analyzed, and a first predicted value of each test case to be recommended is determined.

Illustratively, for test case 1, 3 first targets are scored S _2A 、S _3A And S _4A And 3 first target similarity parameters X ₁₂ 、X ₁₃ And X ₁₄ And analyzing to determine a first predicted value of the test case 1. The process for determining and implementing the first predicted value of the other test case may refer to the process for determining and implementing the first predicted value of the test case 1, and details are not described here.

Therefore, the method for determining the first predicted value of each test case to be recommended is specifically limited, the method for determining the first predicted value of each test case to be recommended is unified, the accuracy of determining the first predicted value of each test case to be recommended is effectively guaranteed, and the high reliability of final recommendation is improved.

Based on the foregoing embodiments, in other embodiments of the present application, step 205c may be implemented by steps a 11-a 14:

step a11, performing operation processing on each first target score and corresponding first target similarity parameter of each test case to be recommended to obtain a second preset number of first numerical values of each test case to be recommended.

In the embodiment of the application, each first target score and the corresponding first target similarity parameter of each test case to be recommended may be subjected to operation processing by, for example, multiplication or other operation methods, so as to obtain a first numerical value of each test case to be recommended, and since each test case to be recommended includes a second preset number of first target similarities, the second preset number of first numerical values may be determined for each test case to be recommended.

Step a12, performing operation processing on a second preset number of first values of each test case to be recommended to obtain a second value of each test case to be recommended.

In the embodiment of the application, the second preset number of first values of each test case to be recommended may be subjected to operation processing by using an accumulation operation method or a weighted accumulation operation method, so as to obtain the second value of each test case to be recommended.

Step a13, performing operation processing on the first target similarity parameters of the second preset number of each test case to be recommended to obtain a third numerical value of each test case to be recommended.

In the embodiment of the application, the second preset number of first target similarity parameters of each test case to be recommended may be subjected to operation processing by using an accumulation operation method or a weighted accumulation operation method, so as to obtain a third value of each test case to be recommended.

Step a14, performing operation processing on the second numerical value of each test case to be recommended and the third numerical value of each test case to be recommended to obtain a first predicted value of each test case to be recommended.

In the embodiment of the application, the second value of each test case to be recommended and the third value of each test case to be recommended can be subjected to operation processing by adopting operation methods such as ratio operation or quotient calculation, and the first predicted value of each test case to be recommended is obtained.

Illustratively, the first predicted value P for test case 1 _DBR The formula for the calculation of (1, A) can be written as

The first predicted value P of the test case 2 can be obtained in the same way _DBR (2, A), first prediction value P of test case 3 _DBR (3, A), first prediction value P of test case 4 _DBR (4, A), first prediction value P of test case 5 _DBR (5, A), first prediction value P of test case 6 _DBR (6，A)。

Therefore, a specific implementation method for determining the first predicted value of each test case to be recommended is limited, the determination method of the first predicted value of each test case to be recommended is unified, the accuracy of determining the first predicted value of each test case to be recommended is effectively guaranteed, and the high reliability of final recommendation is improved.

Based on the foregoing embodiments, in other embodiments of the present application, step 206 may be implemented by steps 206a to 206 b:

step 206a, obtaining the reference score of each test case to be recommended for the target label and the reference score of each corresponding test case to be recommended for n-1 other labels from the reference scores of the m test cases to be recommended for the n reference labels.

In the embodiment of the application, the reference score of each test case to be recommended for the target label is obtained from the reference scores of the m test cases to be recommended for the n reference labels, and S is obtained _1A 、S _2A 、S _3A 、S _4A 、S _5A And S _6A (ii) a To obtain S _1B 、S _1C And S _1D ，S _2B 、S _2C And S _2D ，S _3B 、S _3C And S _3D ，S _4B 、S _4C And S _4D ，S _5B 、S _5C And S _5D And S _6B 、S _6C And S _6D 。

And step 206b, performing similarity calculation on the reference scores of the n test cases to be recommended for the target label and the reference scores of the corresponding n test cases to be recommended for other labels by adopting a preset similarity calculation method to obtain n-1 second similarity parameters.

In the embodiment of the present application, the preset similarity algorithm may be a pearson similarity algorithm, a modified cosine similarity algorithm, a cosine similarity algorithm, or the like.

For example, the calculation formula for determining the second similarity parameter between the target tag a and the other tag B by using the pearson similarity algorithm may be expressed as:

similarly, X can be calculated _AC And X _AD 。

Based on the foregoing embodiments, in other embodiments of the present application, step 207 may be implemented by steps 207a to 207 d:

step 207a, selecting a third preset number of second target similarity parameters from the n-1 second similarity parameters.

Wherein the third predetermined number is less than or equal to n-1.

In the embodiment of the present application, the third preset number may be an empirical value obtained through a large number of experiments, or may be an empirical value obtained by calculating n-1 by using an empirical formula. And sequentially sorting the n-1 second similarity parameters according to the magnitude relation, and then selecting a third preset number of second target similarity parameters with the maximum value from the sorted n-1 second similarity parameters.

Exemplarily from X _AB 、X _AC And X _AD Selecting a second similarity parameter with the pre-set ratio, assuming that the third pre-set number is 2, and the corresponding 2 second target similarity parameters are X _AB And X _AC 。

And step 207b, acquiring m second target scores corresponding to the reference label corresponding to each second target similarity parameter from the reference scores of the n reference labels of the m test cases to be recommended.

And the second target score is a reference score corresponding to each reference label except the target label corresponding to each second target similarity parameter of each test case to be recommended.

In the embodiment of the application, 2 second target similarity parameters are obtained as X from the reference scores of the m test cases to be recommended for the n reference labels _AB And X _AC The m test cases to be recommended are m reference scores of the target label A, the m test cases to be recommended are m reference scores of other labels B, m second target scores of other labels B are obtained, and the m test cases to be recommended are m reference scores of other labels C, and m second target scores of other labels C are obtained.

And step 207c, performing operation processing on the m second target scores corresponding to the reference label corresponding to each second target similarity parameter by using a mean processing method to obtain a third preset number plus 1 fourth numerical value.

In the embodiment of the present application, the mean processing method may be a simple mean calculation method, or may be other weighted mean algorithms. Exemplarily, performing operation processing on m second target scores of the target label a by using a mean value processing method to obtain a fourth numerical value corresponding to the target label a; performing operation processing on the m second target scores of the other labels B by adopting a mean value processing method to obtain fourth numerical values corresponding to the other labels B; and performing operation processing on the m second target scores of the other labels C by adopting a mean value processing method to obtain fourth numerical values corresponding to the other labels C, so that 3 fourth numerical values can be obtained.

And step 207d, determining a second predicted value based on the third preset number of second target similarity parameters, the second target score of each test case to be recommended corresponding to the third preset number of second target similarity parameters, and the third preset number of fourth numerical values.

In the embodiment of the application, a third preset number of second target similarity parameters, a third preset number of second target scores of each to-be-recommended test case corresponding to the second target similarity parameters, and a third preset number plus 1 fourth numerical value are analyzed and calculated to obtain a second predicted value.

Therefore, the method for determining the second predicted value of each test case to be recommended is unified by limiting the method for determining the similarity calculation between the tags, the accuracy for determining the second predicted value of each test case to be recommended is effectively guaranteed, and the high reliability of final recommendation is improved.

Based on the foregoing embodiments, in other embodiments of the present application, the step 207d may be implemented by the steps b 11-b 15:

and b11, performing operation processing on the second target score of each test case to be recommended corresponding to each second target similarity parameter and the corresponding fourth numerical value to obtain a fifth numerical value of each test case to be recommended corresponding to each second target similarity parameter.

In the embodiment of the application, the second target score and the corresponding fourth value of each to-be-recommended test case corresponding to each second target similarity parameter may be subjected to operation processing by using a difference operation or weighted difference operation method, so as to obtain a fifth value of each to-be-recommended test case corresponding to each second target similarity parameter.

And b12, performing operation processing on each second target similarity parameter and the corresponding fifth numerical value to obtain a sixth numerical value corresponding to each second target similarity parameter.

In this embodiment of the application, the operation processing may be performed on each second target similarity parameter and the corresponding fifth numerical value by using a multiplication method or a weighted product operation method, so as to obtain a sixth numerical value corresponding to each second target similarity parameter.

And b13, performing operation processing on the sixth numerical values of the third preset number to obtain seventh numerical values.

In this embodiment of the application, the operation processing may be performed on the third preset number of sixth numerical values by using an accumulation sum operation method or a weighted accumulation sum operation method, so as to obtain a seventh numerical value.

And b14, performing operation processing on a third preset number of second target similarity parameters to obtain an eighth numerical value.

In this embodiment of the application, the third preset number of second target similarity parameters may be subjected to operation processing by using an accumulation and operation method or a weighted accumulation and operation method, so as to obtain an eighth value.

And b15, performing operation processing on the seventh numerical value and the eighth numerical value to obtain a first reference numerical value.

In this embodiment of the application, the seventh numerical value and the eighth numerical value are subjected to operation processing such as ratio operation or quotient calculation, so as to obtain the first reference numerical value.

And b16, accumulating and calculating the fourth numerical value corresponding to the first reference numerical value and the target label to obtain a second predicted value.

In the embodiment of the application, the second predicted value of the test case 1 for the target tag a

Similarly, a second predicted value P of the test case 2 for the target label A can be calculated _PCC (1, A), testing the second predicted value P of the case 3 aiming at the target label A _PCC (3, A), testing the second predicted value P of the case 4 aiming at the target label A _PCC (4, A), testing the second predicted value P of the case 5 aiming at the target label A _PCC (5, A), testing the second predicted value P of the case 6 aiming at the target label A _PCC (6, A). Wherein, the above mentioned

A fourth value corresponding to the target tag a,

to refer to the fourth value corresponding to label B,

is the fourth value corresponding to reference label C.

Based on the foregoing embodiments, in other embodiments of the present application, step 208 can be implemented by steps 208a to 208 d:

and 208a, determining the number of the labels included in each test case to be recommended.

In this embodiment of the application, the number of labels of the labels included in the test case 1 is 2, the number of labels of the labels included in the test case 2 is 2, the number of labels of the labels included in the test case 3 is 2, the number of labels of the labels included in the test case 4 is 2, the number of labels of the labels included in the test case 5 is 1, and the number of labels of the labels included in the test case 6 is 2.

And 208b, calculating the first preset weight value corresponding to each test case to be recommended and the number of the corresponding labels to obtain a ninth numerical value corresponding to each test case to be recommended.

In the embodiment of the application, the first preset weight value corresponding to each test case to be recommended may be an experience value set by a tester according to each test case, or may be an experience value obtained by training a large number of test samples of the first preset weight value corresponding to each test case to be recommended by using a model training method.

When the first preset weight value is determined by adopting a model training method according to a large number of test samples of the first preset weight value corresponding to each test case to be recommendedThe model used can be as follows:

wherein L is _ij Representing the historical prediction recommendation score when a certain test case to be recommended recommends the i label, R _ij The real recommendation score when a certain test case to be recommended recommends the i tag is shown, and n is the total sample number of the certain test case to be recommended recommending the i tag.

And 208c, determining the ratio of the ninth value corresponding to each test case to be recommended to n to obtain a tenth value corresponding to each test case to be recommended.

And 208d, determining the minimum value of the tenth value and the second preset weight value corresponding to each test case to be recommended to obtain the dynamic weight corresponding to each test case to be recommended.

In the embodiment of the present application, the second preset weight value is an empirical value obtained through a large number of experiments, and in general, the second preset weight value may be set to 1.

Therefore, different dynamic weights are determined for each test case to be recommended to balance the influence of the first predicted value and the corresponding second predicted value of each test case to be recommended on the final third predicted value of each test case to be recommended, the reliability of the third predicted values is effectively improved, and the reliability of the recommendation result of each test case to be recommended is improved.

Based on the foregoing embodiments, in other embodiments of the present application, step 209 may be implemented by steps 209a to 209 c:

step 209a, each dynamic weight and the corresponding second predicted value are calculated to obtain a second reference value.

In the embodiment of the application, a product operation method can be adopted for operation on each dynamic weight and the corresponding second predicted value to obtain a second reference value corresponding to each test case to be recommended.

Step 209b, the difference between 1 and each dynamic weight and the corresponding first predicted value are calculated to obtain a third reference value.

In this embodiment, the difference between 1 and each dynamic weight and the corresponding first predicted value may be calculated by a multiplication method to obtain a third reference value. In some application scenarios, the difference between 1 and each dynamic weight and the corresponding first predicted value may also be calculated by a division operation method or a quotient calculation method.

And 209c, calculating each second reference value and the corresponding third reference value to obtain m third predicted values.

In the embodiment of the application, the second reference value and the corresponding third reference value of each test case to be recommended may be subjected to summation operation or ratio operation, so as to obtain m third predicted values.

Illustratively, the third predicted value P (1, a) ═ D1 × P for test case 1 _PCC (1，A)+(1-D1)*P _DBR (1, A), wherein D1 is the dynamic weight corresponding to the test case 1.

Therefore, the method for determining the third predicted value is defined specifically, the method for determining the third predicted value for each test case to be recommended is uniform, the uniformity of the third predicted value for each test case to be recommended is effectively guaranteed, the comparability of the third predicted value of each test case to be recommended is guaranteed, and the high reliability of final recommendation is improved.

Based on the foregoing embodiments, in other embodiments of the present application, step 209c may be implemented by steps c 11-c 12:

and c11, if the number of the target labels is P, operating each second reference value and corresponding third reference value of each test case to be recommended for each target label to obtain P fourth predicted values of each test case to be recommended for P target labels.

Wherein p is an integer greater than or equal to 2.

In the embodiment of the application, when at least two target tags are input by a tester, after the second reference value and the corresponding third reference value of each test case to be recommended for each target tag are determined by the method, the fourth predicted value of each test case to be recommended for each target tag is calculated.

For example, assuming that test case 1 includes target label a and target label B, a fourth predicted value P (1, a) ═ D1 × P of test case 1 for target label a may be calculated _PCC (1，A)+(1-D1)*P _DBR (1, a), the fourth predicted value of the test case 1 for the target tag B is P (1, B) ═ D1 × P _PCC (1，B)+(1-D1)*P _DBR And (1, B), similarly, the fourth predicted values of the test case 2 for the target label a are P (2, a) and P (2, B), the fourth predicted values of the test case 3 for the target label a are P (3, a) and P (3, B), the fourth predicted values of the test case 4 for the target label a are P (4, a) and P (4, B), the fourth predicted values of the test case 5 for the target label a are P (5, a) and P (5, B), and the fourth predicted values of the test case 6 for the target label a are P (6, a) and P (6, B).

And c12, performing operation processing on the P fourth predicted values of each test case to be recommended aiming at the P target labels to obtain m third predicted values.

In the embodiment of the application, the P fourth predicted values of each to-be-recommended test case for the P target tags may be subjected to operation processing by using a summation or averaging operation method to obtain the third predicted value of each to-be-recommended test case, and further, the third predicted values of the m to-be-recommended test cases may be obtained. For example, for test case 1, the test case 1 sums up 2 fourth predicted values corresponding to the target tag a and the target tag B, and the third predicted value of the test case 1 is P (1, a) + P (1, B).

Therefore, the method for recommending the test cases when a plurality of target labels are provided is fully considered, the applicability of the information recommendation method is effectively increased, and a wider application scene is ensured.

Based on the foregoing embodiments, in other embodiments of the present application, step 211 may be implemented by steps 211a to 211 c:

step 211a, responding to the request message, and determining the objects to be tested corresponding to the first preset number of target recommended test cases.

In the embodiment of the application, the object to be tested is a software product which needs to be tested by a tester by using a first preset number of target recommended test cases, for example, an updated application program to be tested, and is released to a user for use after the test is passed.

And step 211b, generating a target relation graph based on the objects to be tested, the first preset number of target recommended test cases and the target labels.

In the embodiment of the application, a target relation graph is generated according to various functional modules included by an object to be tested, a first preset number of target recommended test cases and target labels. In some application scenarios, the target relationship diagram may be obtained by updating information parameters of a preset relationship diagram corresponding to the object to be tested by using a first preset number of target recommended test cases and target tags. Further, the third predicted value of each target recommended test case for each target label can also be displayed in the target relationship graph.

And step 211c, displaying the target relation graph.

In the embodiment of the application, the target relation graph is displayed in the target display area of the test, so that a tester can visually see the influence of the first preset number of target recommended test cases on the object to be tested according to the target relation graph, and quickly call the first preset number of target recommended test cases to test the object to be tested, thereby improving the test efficiency in the test process and reducing the complex operation flow that the tester needs to manually find the test cases.

Illustratively, an embodiment of the present application provides an information recommendation method, which is shown in fig. 3, and the specific implementation process refers to the following steps: step 31, determining a target label; step 32, determining a test case to be recommended with a target label and the dynamic weight of the test case to be recommended; step 33, calculating by adopting a mixed weight algorithm to obtain a third predicted value of each test case to be recommended for the target label; step 34, determining a target recommended test case based on the third predicted value of each test case to be recommended for the target label; step 35, updating the target recommended test case and the corresponding third predicted value to a preset relation graph; step 36, sending the target recommended test case to a test platform to realize a test process; step 37, if a new test case or a new label is detected, updating the preset relational graph; and step 38, updating the dynamic weight of the corresponding test case to be recommended based on the third predicted value of the target recommended test case for the target label. The specific implementation process of step 33 may refer to the specific implementation processes of the embodiments corresponding to steps 102 to 105 or steps 203 to 209, and will not be described in detail here.

One resulting target relationship graph may be shown in fig. 4, where fig. 4 includes: a product Y to be tested; each functional module realized by the to-be-tested product at least comprises a payment module Y11, a payment mode Y12, a risk assessment Y13, an account module Y14, a parameter adding tool Y15, a knowledge base Y16 and an application module Y17; the test case at least comprises: the mobile phone short message 1Y21, the mobile phone short message 2Y22, the mobile phone short message 3Y23, the mobile phone short message 3Y24, the current attention Y25, the use scene Y26, the management desk filling Y27, the pulling timing Y28, the question and answer pushing Y29 and the stock Y210; the label at least comprises: the program Y31, the webpage Y32, the inline Y33, the front end Y34 and the result page Y35, wherein the arrow direction of the arrow connecting line between each two circles in the target relationship graph indicates the association relationship between the objects represented by the two circles.

The relation among a product to be tested, modules for each function module realized by the product to be tested, test cases for each test case, and labels can be shown in fig. 5, that is, the product to be tested is composed of the function modules, each function module adopts a different test case for testing, and each test case is marked with a different label.

It should be noted that, for the descriptions of the same steps and the same contents in this embodiment as those in other embodiments, reference may be made to the descriptions in other embodiments, which are not described herein again.

Based on the foregoing embodiments, an embodiment of the present application provides an information recommendation device, and as shown in fig. 6, the information recommendation device 4 may include: a processor 41, a memory 42, and a communication bus 43, wherein:

a memory 42 for storing executable instructions;

a communication bus 43 for implementing a communication connection between the processor 41 and the memory 42;

a processor 41 for executing the information recommendation program stored in the memory 42 to implement the following steps:

determining a label included by each test case to be recommended to obtain n reference labels included by m test cases to be recommended; wherein the n reference tags comprise a target tag, and n is an integer greater than or equal to 1;

determining a first predicted value of each test case to be recommended for the target label and a second predicted value of each test case to be recommended for the target label based on the target label, the n reference labels and the m test cases to be recommended; the first predicted value is determined by the similarity between each test case to be recommended and each test case to be recommended except the corresponding test case to be recommended in the m test cases to be recommended, and the second predicted value is determined by the similarity between the target label and the labels except the target label in the n reference labels;

determining the dynamic weight corresponding to each test case to be recommended;

determining a first preset number of target recommended test cases from m test cases to be recommended based on the m third predicted values;

and responding to the request message, and displaying a first preset number of target recommended test cases.

Based on the foregoing embodiment, in other embodiments of the present application, when the processor 41 performs the steps of determining, based on the target tag, the n reference tags, and the m test cases to be recommended, a first predicted value of each test case to be recommended for the target tag and a second predicted value of each test case to be recommended for the target tag, the steps may be implemented by:

determining a reference score of each test case to be recommended aiming at each reference label based on the n reference labels and the m test cases to be recommended;

determining similarity parameters between each test case to be recommended and other test cases based on the reference scores of the m test cases to be recommended aiming at the n reference labels to obtain m-1 first similarity parameters corresponding to each test case to be recommended; the other test cases are each to-be-recommended test case except for each corresponding to-be-recommended test exception in the m to-be-recommended test cases;

determining a first predicted value of each test case to be recommended for a target label based on m-1 first similarity parameters corresponding to each test case to be recommended;

determining error similarity parameters between the target label and other labels based on the reference scores of the m test cases to be recommended aiming at the n reference labels to obtain n-1 second similarity parameters; wherein, the other labels are each reference label except the target label in the n reference labels;

and determining a second predicted value of each test case to be recommended for the target label based on the n-1 second similarity parameters.

Based on the foregoing embodiments, in other embodiments of the present application, the processor 41 performs the steps of determining a reference score of each to-be-recommended test case for each reference tag based on the n reference tags and the m to-be-recommended test cases, and may be implemented by the following steps:

determining a preset score of each test case to be recommended for each reference label to obtain n preset scores of each test case to be recommended;

performing operation processing on the n preset scores of each test case to be recommended to obtain a first numerical value;

performing operation processing on each preset score and m of each test case to be recommended to obtain a second numerical value of each reference label corresponding to each test case to be recommended;

and performing operation processing on the second numerical value and the first numerical value of each reference label corresponding to each test case to be recommended to obtain a reference score of each test case to be recommended for each reference label.

Based on the foregoing embodiment, in other embodiments of the present application, when the processor 41 executes the steps to determine the first predicted value of each test case to be recommended based on the m-1 first similarity parameters corresponding to each test case to be recommended, the steps may be implemented by:

selecting a second preset number of first target similarity parameters corresponding to each test case to be recommended from m-1 first similarity parameters corresponding to each test case to be recommended;

determining reference scores of other corresponding test cases in each first target similarity parameter for the target labels from the reference scores of the m test cases to be recommended for the n reference labels to obtain a second preset number of first target scores;

and determining a first predicted value of each test case to be recommended based on the second preset number of first target scores and the second preset number of first target similarity parameters.

Based on the foregoing embodiment, in other embodiments of the present application, when the processor 41 executes the steps to determine the first predicted value of each to-be-recommended test case based on the second preset number of first target scores and the second preset number of first target similarity parameters, the steps may be implemented by:

calculating each first target score and corresponding first target similarity parameter of each test case to be recommended to obtain a second preset number of first numerical values of each test case to be recommended;

performing operation processing on a second preset number of first values of each test case to be recommended to obtain a second value of each test case to be recommended;

performing operation processing on a second preset number of first target similarity parameters of each test case to be recommended to obtain a third numerical value of each test case to be recommended;

and carrying out operation processing on the second numerical value of each test case to be recommended and the third numerical value of each test case to be recommended to obtain a first predicted value of each test case to be recommended.

Based on the foregoing embodiment, in other embodiments of the present application, the processor 41 executes the steps to determine the error similarity parameter between the target tag and other tags based on the reference scores of the m test cases to be recommended for the n reference tags, and when obtaining the n-1 second similarity parameters, the steps may be implemented by:

obtaining a reference score of each test case to be recommended for a target label and a reference score of each corresponding test case to be recommended for n-1 other labels from the reference scores of the m test cases to be recommended for the n reference labels;

and performing similarity calculation on the reference scores of the n test cases to be recommended aiming at the target label and the reference scores of the corresponding n test cases to be recommended aiming at other labels by adopting a preset similarity calculation method to obtain n-1 second similarity parameters.

Based on the foregoing embodiment, in other embodiments of the present application, when the processor 41 executes the steps to determine the second predicted value of each test case to be recommended for the target tag based on the n-1 second similarity parameters, the steps may be implemented by:

selecting a third preset number of second target similarity parameters from the n-1 second similarity parameters; wherein the third preset number is less than or equal to n-1;

acquiring m second target scores corresponding to the reference labels except the target label corresponding to each second target similarity parameter from the reference scores of the n reference labels of the m test cases to be recommended; the second target score is a reference score corresponding to each test case to be recommended aiming at a reference label except the target label corresponding to each second target similarity parameter;

performing operation processing on the m second target scores corresponding to the reference labels except the target label corresponding to each second target similarity parameter by adopting a mean processing method to obtain a third preset number of fourth numerical values;

and determining a second predicted value based on a third preset number of second target similarity parameters, a second target score of each test case to be recommended corresponding to the third preset number of second target similarity parameters and a third preset number of fourth values.

Based on the foregoing embodiment, in other embodiments of the present application, when the processor 41 executes the steps to determine the second predicted value based on the third preset number of second target similarity parameters, the second target score of each to-be-recommended test case corresponding to the third preset number of second target similarity parameters, and the third preset number of fourth numerical values, the steps may be implemented by:

performing operation processing on the second target score and the corresponding fourth numerical value of each test case to be recommended corresponding to each second target similarity parameter to obtain a fifth numerical value of each test case to be recommended corresponding to each second target similarity parameter;

performing operation processing on each second target similarity parameter and the corresponding fifth numerical value to obtain a sixth numerical value corresponding to each second target similarity parameter;

performing operation processing on a third preset number of sixth numerical values to obtain a seventh numerical value;

performing operation processing on a third preset number of second target similarity parameters to obtain an eighth numerical value;

and performing operation processing on the seventh numerical value and the eighth numerical value to obtain a second predicted value.

Based on the foregoing embodiment, in other embodiments of the present application, when the processor 41 executes the steps to determine the dynamic weight corresponding to each test case to be recommended, the following steps may be implemented:

determining the number of labels of each to-be-recommended test case;

calculating a first preset weight value corresponding to each test case to be recommended and the number of corresponding labels to obtain a ninth numerical value corresponding to each test case to be recommended;

determining the ratio of the ninth value corresponding to each test case to be recommended to n to obtain a tenth value corresponding to each test case to be recommended;

and determining the minimum value of the tenth numerical value and the second preset weight value corresponding to each test case to be recommended to obtain the dynamic weight corresponding to each test case to be recommended.

Based on the foregoing embodiment, in other embodiments of the present application, when the processor 41 executes the steps to determine m third predicted values based on each dynamic weight, the corresponding first predicted value, and the corresponding second predicted value, the steps may be implemented by:

calculating each dynamic weight and the corresponding second predicted value to obtain an eighth numerical value;

calculating the difference value between 1 and each dynamic weight and the corresponding first predicted value to obtain a ninth value;

and calculating each eighth numerical value and the corresponding ninth numerical value to obtain m third predicted values.

Based on the foregoing embodiment, in other embodiments of the present application, when the processor 41 executes the steps to operate each eighth numerical value and the corresponding ninth numerical value to obtain m third predicted values, the following steps may be implemented:

if the number of the target labels is P, calculating each eighth numerical value of each test case to be recommended aiming at each target label and the corresponding ninth numerical value to obtain P fourth predicted values of each test case to be recommended aiming at the P target labels; wherein p is an integer greater than or equal to 2;

and performing operation processing on the P fourth predicted values of each test case to be recommended aiming at the P target labels to obtain m third predicted values.

Based on the foregoing embodiment, in other embodiments of the present application, when the processor 41 executes the step response request message and displays the first preset number of target recommended test cases, the following steps may be performed:

responding to the request message, and determining to-be-tested objects corresponding to a first preset number of target recommended test cases;

generating a target relation graph based on the object to be tested, a first preset number of target recommended test cases and target labels;

and displaying the target relation graph.

It should be noted that, in the embodiment of the present application, the multiple or multiple programs may be explained by steps of the one or multiple processors, and refer to the method implementation processes provided in the embodiments corresponding to fig. 1 to 2, which are not described herein again.

Based on the foregoing embodiments, embodiments of the present application provide a computer-readable storage medium, which is referred to as a storage medium for short, where one or more programs are stored in the computer-readable storage medium, and the one or more programs can be executed by one or more processors to implement an implementation process of an information recommendation method provided in the embodiments corresponding to fig. 1 to 2, and details are not described here again.

As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

The above description is only a preferred embodiment of the present application, and is not intended to limit the scope of the present application.

Claims

1. An information recommendation method, characterized in that the method comprises:

determining a first predicted value of each test case to be recommended aiming at the target label and a second predicted value of each test case to be recommended aiming at the target label based on the target label, the n reference labels and the m test cases to be recommended;

determining a dynamic weight corresponding to each test case to be recommended;

and responding to the request message, and displaying the target recommended test cases with the first preset number.

2. The method of claim 1, wherein the determining a first predicted value of each of the to-be-recommended test cases for the target tag and a second predicted value of each of the to-be-recommended test cases for the target tag based on the target tag, the n reference tags, and the m to-be-recommended test cases comprises:

determining a reference score of each to-be-recommended test case for each reference label based on the n reference labels and the m to-be-recommended test cases;

determining similarity parameters between each test case to be recommended and other test cases based on the reference scores of the m test cases to be recommended for the n reference labels to obtain m-1 first similarity parameters corresponding to each test case to be recommended; the other test cases are each to-be-recommended test case except for each corresponding to-be-recommended test exception in the m to-be-recommended test cases;

determining the first predicted value of each test case to be recommended aiming at the target label based on m-1 first similarity parameters corresponding to each test case to be recommended;

determining error similarity parameters between a target label and other labels based on the reference scores of the m test cases to be recommended aiming at the n reference labels to obtain n-1 second similarity parameters; wherein the other tags are each of the n reference tags except the target tag;

and determining the second predicted value of each test case to be recommended aiming at the target label based on n-1 second similarity parameters.

3. The method of claim 2, wherein the determining a reference score for each of the recommended test cases for each of the reference tags based on the n reference tags and the m test cases to be recommended comprises:

4. The method according to claim 2, wherein the determining the first predicted value of each test case to be recommended based on the m-1 first similarity parameters corresponding to each test case to be recommended comprises:

determining reference scores of the other corresponding test cases in each first target similarity parameter for the target labels from the reference scores of the m test cases to be recommended for the n reference labels, and obtaining a second preset number of first target scores;

and determining the first predicted value of each test case to be recommended based on the second preset number of first target scores and the second preset number of first target similarity parameters.

5. The method according to claim 4, wherein the determining the first predicted value of each of the to-be-recommended test cases based on the second preset number of the first target scores and the second preset number of the first target similarity parameters comprises:

performing operation processing on each first target score and the corresponding first target similarity parameter of each test case to be recommended to obtain a first numerical value of the second preset number of each test case to be recommended;

performing operation processing on the second preset number of first numerical values of each test case to be recommended to obtain a second numerical value of each test case to be recommended;

performing operation processing on the first target similarity parameters of the second preset number of each test case to be recommended to obtain a third numerical value of each test case to be recommended;

and performing operation processing on the second numerical value of each test case to be recommended and the third numerical value of each test case to be recommended to obtain the first predicted value of each test case to be recommended.

6. The method according to claim 2, wherein the determining error similarity parameters between a target tag and other tags based on the reference scores of the m test cases to be recommended for the n reference tags to obtain n-1 second similarity parameters comprises:

obtaining the reference score of each to-be-recommended test case for the target label and the reference score of each corresponding to-be-recommended test case for n-1 other labels from the reference scores of the m to-be-recommended test cases for the n reference labels;

and performing similarity calculation on the reference scores of the n test cases to be recommended aiming at the target label and the reference scores of the corresponding n test cases to be recommended aiming at other labels by adopting a preset similarity algorithm to obtain n-1 second similarity parameters.

7. The method according to claim 2, wherein the determining the second predicted value of each test case to be recommended for the target tag based on the n-1 second similarity parameters comprises:

acquiring m second target scores corresponding to the reference label corresponding to each second target similarity parameter from the reference scores of the n reference labels of the m test cases to be recommended; the second target score is a reference score corresponding to a reference label except the target label corresponding to each second target similarity parameter of each test case to be recommended;

performing operation processing on the m second target scores corresponding to the reference label corresponding to each second target similarity parameter by using a mean processing method to obtain a third preset number plus 1 fourth numerical value;

and determining the second predicted value based on the third preset number of the second target similarity parameters, the second target score and the third preset number of the second target similarity parameters corresponding to the third preset number of the second target similarity parameters of each test case to be recommended plus 1 fourth numerical value.

8. The method according to claim 7, wherein the determining the second predicted value based on the second target scores and the third preset number plus 1 fourth numerical value of each to-be-recommended test case corresponding to the third preset number of the second target similarity parameters and the third preset number of the second target similarity parameters comprises:

performing operation processing on the sixth numerical values of the third preset number to obtain seventh numerical values;

performing operation processing on the third preset number of second target similarity parameters to obtain an eighth numerical value;

performing operation processing on the seventh numerical value and the eighth numerical value to obtain a first reference numerical value;

and performing accumulation calculation on the first reference value and the fourth value corresponding to the target label to obtain the second predicted value.

9. The method according to claim 2, wherein the determining the dynamic weight corresponding to each test case to be recommended comprises:

determining the number of labels of each label included in the test case to be recommended;

and determining the minimum value of the tenth numerical value and a second preset weight value corresponding to each test case to be recommended to obtain the dynamic weight corresponding to each test case to be recommended.

10. The method according to any one of claims 1 to 9, wherein the determining m third predicted values based on each of the dynamic weights, the corresponding first predicted value, and the corresponding second predicted value comprises:

calculating each dynamic weight and the corresponding second predicted value to obtain a second reference value;

calculating the difference value between 1 and each dynamic weight and the corresponding first predicted value to obtain a third reference value;

and calculating each second reference value and the corresponding third reference value to obtain m third predicted values.

11. The method of claim 10, wherein said operating each of the second reference values and the corresponding third reference value to obtain m third predicted values comprises:

if the number of the target labels is P, operating each second reference value and the corresponding third reference value of each to-be-recommended test case for each target label to obtain P fourth predicted values of each to-be-recommended test case for P target labels; wherein p is an integer greater than or equal to 2;

12. The method according to any one of claims 1 to 9 and 11, wherein the displaying the first preset number of the target recommended test cases in response to the request message comprises:

responding to the request message, and determining to-be-tested objects corresponding to the first preset number of the target recommended test cases;

generating a target relation graph based on the object to be tested, the first preset number of target recommended test cases and the target labels;

and displaying the target relation graph.

13. An information recommendation apparatus, characterized in that the apparatus comprises: a memory, a processor, and a communication bus; wherein:

the memory to store executable instructions;

the processor is configured to execute the information recommendation program stored in the memory, and implement the steps of the information recommendation method according to any one of claims 1 to 12.

14. A storage medium, characterized in that the storage medium has stored thereon an information recommendation program which, when executed by a processor, implements the steps of the information recommendation method according to any one of claims 1 to 12.