Test service recommendation method and device, computer equipment and medium

Abstract

The invention discloses a test service recommendation method and device, computer equipment and a medium, and relates to the technical field of test services, and the method comprises the steps: obtaining task progress information sent by a user side, and combining user historical behavior information and task basic information recorded by a platform side; task progress features are extracted from the task progress information, and multi-dimensional features are extracted from the user historical behavior information and the task basic information; inputting the task features and the multi-dimensional features into a pre-constructed demand prediction model; and according to the output of the demand prediction model, in combination with the dynamically adjusted exploration factor, carrying out personalized test service recommendation on the user. According to the method, the specific requirements of the user in the current task stage can be accurately understood, so that test service recommendation matched with the task state is provided, and the problem that a traditional recommendation system is difficult to deal with a complex test task environment is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of testing services, and in particular to a testing service recommendation method, device, computer equipment and medium. Background Art

[0002] In the current testing service field, as the software development and testing process becomes increasingly complex, the testing tasks faced by users are becoming more and more cumbersome and diverse. These tasks may involve multiple stages, each with its own specific requirements and challenges. Therefore, users' demand for testing services at different task stages also presents a dynamic change.

[0003] However, existing test service recommendation systems often make recommendations based on static user profiles or simple behavioral rules, ignoring the real-time and dynamic nature of task progress. These methods are unable to cope with the ever-changing needs of users, resulting in a mismatch between the recommended test services and the user's current task status, reducing the effectiveness of the recommendation and user satisfaction.

[0004] Specifically, traditional recommendation systems have the following shortcomings:

[0005] Missing task progress information: Existing recommendation systems usually do not track or consider the real-time progress of user tasks, and therefore cannot accurately recommend testing services based on the specific progress of the task.

[0006] Single user behavior data: Most recommendation systems only rely on basic behavior data such as user clicks and browsing, ignoring the user's specific behavior patterns and interaction details during task execution, making it difficult to fully reflect the user's real needs.

[0007] Insufficient personalization: Due to the above limitations, existing recommendation systems find it difficult to achieve truly personalized recommendations, that is, to customize recommendations based on the unique needs and preferences of each user. Summary of the invention

[0008] In view of the defects in the prior art, the present invention provides a

[0009] In a first aspect, the present invention provides a test service recommendation method, the method comprising:

[0010] Obtain the task progress information sent by the user, combined with the user's historical behavior information and task basic information recorded by the platform;

[0011] Extracting task progress features from the task progress information, and extracting multi-dimensional features from the user historical behavior information and task basic information; inputting the task features and multi-dimensional features into a pre-built demand forecasting model;

[0012] Based on the output of the demand forecasting model and combined with the dynamically adjusted exploration factors, personalized testing service recommendations are made to users.

[0013] Preferably, before obtaining the task progress information sent by the user terminal, the following steps are included:

[0014] Update the task progress based on the task progress model to obtain task progress information in real time; the task progress model is:

[0015]

[0016] Where p represents the task progress p∈[0,1], p=0 means the task starts, and p=1 means the task is completed; t is the amount of tasks completed in the time period t to t+1, W total is the total workload of the task;

[0017] The task progress information obtained in real time is sent to the recommendation platform.

[0018] Preferably, the process of constructing the demand forecasting model includes:

[0019] Build an initial demand forecast model;

[0020] Using a labeled training data set to train the initial demand prediction model, the training data set includes the user's historical task progress features and multi-dimensional features and corresponding test service demand labels;

[0021] During the training process, the cross-validation method is used to evaluate the generalization ability of the model, and the optimal model parameters are selected to obtain the demand forecasting model.

[0022] Preferably, the exploration factor is used to adjust the balance between exploration and utilization. The exploration factor is determined according to the number of user interactions. The greater the number of interactions, the smaller the exploration factor. The exploration means randomly recommending a test service to the user with a low probability. The exploration means recommending a test service with the highest predicted score to the user with a high probability.

[0023] In a second aspect, the present invention provides a test service recommendation system, including a service recommendation platform, wherein the service recommendation platform includes:

[0024] The data acquisition module is used to obtain the task progress information sent by the user end, combined with the user's historical behavior information and task basic information recorded by the platform end;

[0025] A model prediction module is used to extract task progress features from the task progress information, extract multi-dimensional features from the user historical behavior information and task basic information; and input the task features and multi-dimensional features into a pre-built demand prediction model;

[0026] The service recommendation module is used to recommend personalized testing services to users based on the output of the demand prediction model and the dynamically adjusted exploration factor.

[0027] Preferably, before obtaining the task progress information sent by the user terminal, the following steps are included:

[0028] The task progress tracking module is used to update the task progress based on the task progress model to obtain task progress information in real time; the task progress model is:

[0029]

[0030] Where p represents the task progress p∈[0,1], p=0 means the task starts, and p=1 means the task is completed; t is the amount of tasks completed in the time period t to t+1, W total is the total workload of the task;

[0031] The data transmission module is used to send the task progress information obtained in real time to the recommendation platform.

[0032] Preferably, the task progress tracking module includes:

[0033] Anomaly detection unit, used to detect and process abnormal task progress data;

[0034] The user feedback interface is used to show users the current task progress and reasons for recommending testing services in real time.

[0035] In a third aspect, the present invention provides a computer device, including a processor and a memory, wherein the memory stores a computer-readable storage medium, and when the computer-readable storage medium is executed by the processor, the method described above is implemented.

[0036] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, and the computer program, when executed, implements any of the methods described above.

[0037] The beneficial effects of the present invention are embodied in: the present invention provides a test service recommendation method, device, computer equipment and medium, the method comprising: obtaining task progress information sent by the user end, combining the user historical behavior information and task basic information recorded by the platform end; extracting task progress features from the task progress information, and extracting multi-dimensional features from the user historical behavior information and task basic information; inputting the task features and multi-dimensional features into a pre-built demand forecasting model; and making personalized test service recommendations to users based on the output of the demand forecasting model and in combination with a dynamically adjusted exploration factor. By obtaining task progress information in real time, the present invention can accurately understand the specific needs of users at the current task stage, thereby providing test service recommendations that match the task status. By introducing the exploration factor, the present invention achieves a balance between exploration and utilization in the recommendation process, and can both recommend test services that users may be interested in and discover new services that may be more popular with users. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following is a brief introduction to the drawings required for the specific embodiments or the description of the prior art. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn according to the actual scale.

[0039] Figure 1 A flow chart of a test service recommendation method is provided for the present invention;

[0040] Figure 2 A structural schematic diagram of a test service recommendation device is provided for the present invention;

[0041] Figure 3 The present invention provides a structural schematic diagram of a computer testing device. DETAILED DESCRIPTION

[0042] The following embodiments of the technical solution of the present invention are described in detail in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and are therefore only used as examples, and cannot be used to limit the protection scope of the present invention.

[0043] It should be noted that, unless otherwise specified, the technical terms or scientific terms used in this application should have the common meanings understood by those skilled in the art to which the present invention belongs.

[0044] Embodiment 1

[0045] like Figure 1 As shown, the present invention provides a test service recommendation method, the method comprising:

[0046] Step 1: Obtain the task progress information sent by the user, combined with the user's historical behavior information and task basic information recorded by the platform.

[0047] In the field of testing services, a user may be performing a complex testing task, and his or her requirements will change dynamically according to the current progress of the task. Existing recommendation systems often cannot accurately understand the specific requirements of users at the current task stage, resulting in the recommended testing services not matching the user's current task status. Therefore, the embodiment of the present invention adds real-time task progress information.

[0048] Specifically, the acquisition process is as follows: updating the task progress based on the task progress model to obtain the task progress information in real time; the task progress model is:

[0049]

[0050] Where p represents the task progress p∈[0,1], p=0 means the task starts, and p=1 means the task is completed; t is the amount of tasks completed in the time period t to t+1, W total is the total workload of the task;

[0051] The task progress information obtained in real time is sent to the recommendation platform.

[0052] The task progress model is used to calculate and update the task progress in real time based on the real-time operation data (such as the number of completed steps, the amount of data processed, etc.) and the basic information of the task (such as the total workload, task list, etc.) sent by the user. After completing a certain amount of workload each time, the user uploads the relevant data to the server, and the server updates the task progress based on this data.

[0053] The recommendation platform not only receives real-time task progress information, but also records and integrates the user's historical behavior information on the platform, including the user's past clicks, browsing behaviors, and basic task information such as the task type entered before the task starts.

[0054] Step 2: extracting task progress features from the task progress information, and extracting multi-dimensional features from the user historical behavior information and task basic information; inputting the task features and multi-dimensional features into a pre-built demand forecasting model.

[0055] Specifically, the multi-dimensional features include: user historical behavior characteristics: including the user's past choice of testing services, usage frequency, usage time, satisfaction evaluation, etc. These characteristics can reveal the user's preferences and habits; task type characteristics: different types of tasks may require different testing services, so the type of task, complexity, required skills, etc. are also important characteristics.

[0056] In order to predict the user's needs at a given task progress, a supervised learning model such as random forest or gradient boosted tree (GBDT) is used. The model input will include the task progress p and other relevant features x (such as user historical behavior, task type, etc.), and the output is the score of the test service that the user may need at the current progress.

[0057] It should be noted that before making a prediction, the task progress information, user historical behavior information and task basic information need to be clarified and formatted to meet data requirements.

[0058] Step 3: Based on the output of the demand prediction model and the dynamically adjusted exploration factor, personalized testing service recommendations are made to users.

[0059] Specifically, the construction process of the demand forecasting model includes: constructing an initial demand forecasting model; using a labeled training data set to train the initial demand forecasting model, wherein the training data set includes the user's historical task progress characteristics and multi-dimensional characteristics as well as corresponding test service demand labels; during the training process, a cross-validation method is used to evaluate the generalization ability of the model, and the optimal model parameters are selected to obtain a demand forecasting model.

[0060] In order to evaluate the generalization ability of the model and select the optimal model parameters, the cross-validation method is used. Cross-validation divides the data set into multiple parts, takes one part as the test set, and the rest as the training set for training and testing. Through multiple cross-validations, the performance of the model on different data subsets can be evaluated, and the model parameters with the best performance can be selected as the optimal parameters.

[0061] Furthermore, the exploration factor is used to adjust the balance between exploration and utilization. The exploration factor is determined according to the number of user interactions. The more interactions there are, the smaller the exploration factor is. The exploration means randomly recommending a test service to the user with a low probability. The exploration means recommending a test service with the highest predicted score to the user with a high probability.

[0062] At the beginning of the recommendation, an initial exploration factor value is set. This value is usually large, indicating that exploration is more inclined in the initial stage. As the number of interactions between the user and the recommendation system increases, the value of the exploration factor is gradually adjusted. A common strategy is to reduce the value of the exploration factor according to a certain decay function after each user interacts with the system. For example, linear decay, exponential decay, etc. can be used. At each recommendation, whether to explore or exploit is determined based on the current exploration factor value. If the generated random number is less than the exploration factor value, a test service is randomly selected for recommendation exploration; otherwise, the service with the highest predicted probability is selected for recommendation exploitation.

[0063] In summary, the present invention provides a new solution to the deficiencies of existing recommendation systems in dealing with dynamically changing user test service needs, such as missing task progress information, single user behavior data, and insufficient personalization. The method obtains the task progress information sent by the user end in real time, and extracts task progress features and multi-dimensional features in combination with the user's historical behavior information and task basic information recorded by the platform end. Then, these features are input into a pre-built demand forecasting model, and personalized test service recommendations are made to users based on the output of the model and the dynamically adjusted exploration factors. The present invention also provides a corresponding recommendation system, computer equipment, and medium to implement the above method. Through the application of the present invention, the accuracy of test service recommendations and user satisfaction can be significantly improved.

[0064] Embodiment 2

[0065] like Figure 2 As shown, the present invention provides a test service recommendation system, including a service recommendation platform, wherein the service recommendation platform includes:

[0066] The data acquisition module is used to obtain the task progress information sent by the user end, combined with the user's historical behavior information and task basic information recorded by the platform end;

[0067] A model prediction module is used to extract task progress features from the task progress information, extract multi-dimensional features from the user historical behavior information and task basic information; and input the task features and multi-dimensional features into a pre-built demand prediction model;

[0068] The service recommendation module is used to recommend personalized testing services to users based on the output of the demand prediction model and the dynamically adjusted exploration factor.

[0069] In the embodiment of the present invention, before obtaining the task progress information sent by the user terminal, the following steps are included:

[0070] The task progress tracking module is used to update the task progress based on the task progress model to obtain task progress information in real time; the task progress model is:

[0071]

[0072] Where p represents the task progress p∈[0,1], p=0 means the task starts, and p=1 means the task is completed; t is the amount of tasks completed in the time period t to t+1, W total is the total workload of the task;

[0073] The data transmission module is used to send the task progress information obtained in real time to the recommendation platform.

[0074] In an embodiment of the present invention, the task progress tracking module includes:

[0075] Anomaly detection unit, used to detect and process abnormal task progress data;

[0076] The user feedback interface is used to show users the current task progress and reasons for recommending testing services in real time.

[0077] It should be understood that a test service recommendation system provided in an embodiment of the present invention and a test service recommendation method provided in the above embodiment are based on the same inventive concept. For more specific working principles of each module in the embodiment of the present invention, please refer to the above embodiment and will not be repeated in this embodiment.

[0078] Embodiment 3

[0079] The above-mentioned test service recommendation system can be implemented in the form of a computer program. The computer program can be used in Figure 3 Runs on the computer device shown.

[0080] See also Figure 3 , Figure 3 It is a schematic block diagram of a computer device provided by an embodiment of the present invention. The computer device may be a terminal, wherein the terminal may be an electronic device with communication function such as a smart phone, a tablet computer, a laptop computer, a desktop computer, a personal digital assistant, and a wearable device. The computer device includes a processor, a memory, and an interface connected via a system bus, wherein the memory may include a non-volatile storage medium and an internal memory. The non-volatile storage medium may store an operating system and a computer program. When the computer program is executed, the processor may execute a test service recommendation method. The processor is used to provide computing and control capabilities to support the operation of the entire computer device. The internal memory provides an environment for the operation of the computer program in the non-volatile storage medium, and when the computer program is executed by the processor, the processor may execute a test service recommendation method.

[0081] It should be understood that in the embodiments of the present application, the processor may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0082] Embodiment 4

[0083] It is understood by those skilled in the art that all or part of the processes in the method for implementing the above embodiment can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a storage medium, which is a computer-readable storage medium. The computer program is executed by at least one processor in the computer system to implement the process steps of the embodiment of the above method.

[0084] Therefore, the present invention also provides a storage medium. The storage medium can be a computer-readable storage medium. The storage medium stores a computer program. The computer-readable storage medium can be the memory of the device provided in the aforementioned embodiment, such as the hard disk or memory of the device. The computer-readable storage medium can also be an external memory of the device, such as a plug-in hard disk equipped on the identification device, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. Further, the computer-readable storage medium can also include both the internal memory of the identification device and the external memory. The computer-readable storage medium is used to store the computer program and other programs and data. The computer-readable storage medium can also be used to temporarily store data that has been output or is to be output.

[0085] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention.

Claims

1. A test service recommendation method, characterized in that: include: Obtain the task progress information sent by the user, combined with the user's historical behavior information and task basic information recorded by the platform; Extracting task progress features from the task progress information, and extracting multi-dimensional features from the user historical behavior information and task basic information; Inputting the task characteristics and multi-dimensional characteristics into a pre-built demand forecasting model; Based on the output of the demand forecasting model and combined with the dynamically adjusted exploration factors, personalized testing service recommendations are made to users.

2. A test service recommendation method according to claim 1, characterized in that: Before obtaining the task progress information sent by the user, include: Update the task progress based on the task progress model to obtain task progress information in real time; the task progress model is: Where p represents the task progress p∈[0,1], p=0 means the task starts, and p=1 means the task is completed; t is the amount of tasks completed in the time period t to t+1, W total is the total workload of the task; The task progress information obtained in real time is sent to the recommendation platform.

3. A test service recommendation method according to claim 1, characterized in that: The construction process of the demand forecasting model includes: Build an initial demand forecast model; Using a labeled training data set to train the initial demand prediction model, the training data set includes the user's historical task progress features and multi-dimensional features and corresponding test service demand labels; During the training process, the cross-validation method is used to evaluate the generalization ability of the model, and the optimal model parameters are selected to obtain the demand forecasting model.

4. A test service recommendation method according to claim 1, characterized in that: The exploration factor is used to adjust the balance between exploration and utilization. The exploration factor is determined according to the number of user interactions. The greater the number of interactions, the smaller the exploration factor. The exploration means randomly recommending a test service to the user with a low probability. The exploration means recommending a test service with the highest predicted score to the user with a high probability.

5. A test service recommendation system, characterized in that: A service recommendation platform is included, and the service recommendation platform includes: The data acquisition module is used to obtain the task progress information sent by the user end, combined with the user's historical behavior information and task basic information recorded by the platform end; A model prediction module is used to extract task progress features from the task progress information, extract multi-dimensional features from the user historical behavior information and task basic information; and input the task features and multi-dimensional features into a pre-built demand prediction model; The service recommendation module is used to recommend personalized testing services to users based on the output of the demand prediction model and the dynamically adjusted exploration factor.

6. A test service recommendation system according to claim 5, characterized in that: Before obtaining the task progress information sent by the user, include: The task progress tracking module is used to update the task progress based on the task progress model to obtain task progress information in real time; the task progress model is: Where p represents the task progress p∈[0,1], p=0 means the task starts, and p=1 means the task is completed; t is the amount of tasks completed in the time period t to t+1, W total is the total workload of the task; The data transmission module is used to send the task progress information obtained in real time to the recommendation platform.

7. A test service recommendation system according to claim 6, characterized in that: The task progress tracking module includes: Anomaly detection unit, used to detect and process abnormal task progress data; The user feedback interface is used to show users the current task progress and reasons for recommending testing services in real time.

8. A computer device, characterized in that: The method comprises a processor and a memory, wherein a computer-readable storage medium is stored in the memory, and when the computer-readable storage medium is executed by the processor, the method according to any one of claims 1 to 4 is implemented.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which implements the method according to any one of claims 1 to 4 when executed.

Images