Collaborative knowledge obsolescence detection method, device and equipment for open source community

Abstract

The present application relates to a method, device and equipment for detecting outdated collaborative knowledge for open source communities. The method includes: obtaining historical collaborative data in open source software projects, and constructing training samples based on the historical collaborative data; the training samples include the observation value vector of the independent variable set within the observation window period at the current moment; the independent variable set includes the revision history information of the open source collaborative knowledge document and the community dynamic interaction information; the training samples are marked by labels; the training samples are input into the logistic regression model for fitting to obtain an outdated detection model; the observation value vector of the independent variable set within the observation window period of the time point to be detected is input into the outdated detection model to obtain the outdated detection result of the open source collaborative knowledge document. This method can automatically identify whether there is outdated collaborative knowledge in the open source collaborative knowledge document, so as to remind the open source project managers to maintain and update the documents in a timely manner and ensure the smooth participation of open source contributors.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a collaborative knowledge obsolescence detection method, apparatus and device for an open source community. Background Art

[0002] With the rapid development and widespread application of open source software, the open source community is growing stronger around the world, and the participation and contribution content of contributors are gradually increasing. The success of an open source project depends largely on the management of the project, the transparency of the development process, and the effective transfer of collaborative knowledge. As an important part of it, the open source software contribution document plays a role in providing guidance and norms for contributors, including the project's contribution rules, coding standards, development processes, etc. However, with the continuous development of technology and the iteration of projects, the collaborative knowledge originally described in the contribution document may change due to technological evolution, tool updates, or workflow adjustments, causing some of the content in the document to become outdated. Outdated collaborative knowledge may mislead open source contributors, bringing negative experience to their participation process, and also affecting the efficiency of open source collaboration.

[0003] In order to ensure that open source contributors can obtain accurate and timely collaboration guidance when participating in the project, the collaboration knowledge in the open source software contribution documents must be regularly reviewed and updated to ensure that it is consistent with the actual situation of the open source project. Currently, open source project management teams or community contributors usually rely on manual methods to discover these outdated collaboration knowledge contents, usually by reviewing documents one by one, obtaining community feedback, or identifying them through actual operations during project iterations. However, this method not only relies on manual experience and judgment, but also has certain lags and uncertainties, which may cause outdated knowledge contents to remain undiscovered for a long time, thereby misleading new contributors and affecting the smooth progress of the project.

[0004] The existing manual methods of discovering outdated content have problems such as low efficiency and long feedback cycles. In serious cases, it may cause contributors to develop under the guidance of incorrect knowledge, affecting the collaborative effect and development progress of the project. In addition, the manual method is prone to waste of resources, especially when the open source project is large and the document content is complex, the manual review and management workload is huge. Therefore, there is an urgent need for a more efficient and automated technical means to detect and update outdated collaborative knowledge in open source project documents, so as to improve the development efficiency and quality of open source software and reduce potential errors and waste of resources. Summary of the invention

[0005] Based on this, it is necessary to provide a collaborative knowledge obsolescence detection method, device and equipment for the open source community to address the above technical issues.

[0006] A collaborative knowledge obsolescence detection method for an open source community, the method comprising:

[0007] Obtain historical collaboration data in an open source software project, and construct training samples based on the historical collaboration data; the training samples include observation value vectors of an independent variable set within an observation window at the current moment; the independent variable set includes revision history information of an open source collaboration knowledge document and community dynamic interaction information; the training samples are labeled by a label; when the label is 1, it indicates that the open source collaboration knowledge document is revised at the current moment; when the label is 0, it indicates that the open source collaboration knowledge document is not revised at the current moment;

[0008] The training samples are input into the logistic regression model for fitting to obtain an outdated detection model; the outdated detection model is used to represent the relationship between the independent variable set and the dependent variable; when the dependent variable is 1, it indicates that the open source collaborative knowledge document needs to be revised and there is an outdated risk; when the dependent variable is 0, it indicates that the open source collaborative knowledge document does not need to be revised and there is no outdated risk;

[0009] The observation value vector of the independent variable set within the observation window period of the time point to be detected is input into the obsolescence detection model to obtain the obsolescence detection result of the open source collaborative knowledge document.

[0010] In one of the embodiments, it also includes: obtaining a revision list of open source collaborative knowledge documents from a code repository of open source software; each element in the revision list includes a revision time attribute; constructing a positive sample based on an observation value vector of an independent variable set within an observation window period of the revision time attribute; the label of the positive sample is 1; deleting the time period corresponding to the positive sample on the timeline of historical collaborative data, randomly selecting multiple observation windows within the remaining time period, and constructing a negative sample based on the observation value vector of the independent variable set within each observation window period; the label of the negative sample is 0.

[0011] In one of the embodiments, it also includes: calculating the observation value vector of the independent variable set within the observation window period of the time point to be detected, inputting the observation value vector into the obsolescence detection model, and obtaining the predicted value; if the predicted value is 0, it means that the open source collaborative knowledge document does not need to be revised and there is no obsolescence risk; if the predicted value is 1, it means that the open source collaborative knowledge document needs to be revised and there is an obsolescence risk.

[0012] In one of the embodiments, the method further includes: when the outdated detection result indicates that the open source collaborative knowledge document is at risk of being outdated, adding an outdated risk mark to the open source collaborative knowledge document to remind project management to update it.

[0013] In one embodiment, it also includes: the independent variable set is ( , , , , ),in, Indicates the number of times the open source software source code file has been revised in the most recent time window. Indicates the number of times the open source software technical documentation has been revised in the most recent time window. Indicates the number of times the open source software community document has been revised in the most recent time window. Indicates the proportion of code contributions submitted by core developers in the most recent time window. Indicates the change in the average number of revisions of code contributions in the most recent time window compared to the previous time window. Indicates the change in the average number of review comments for code contributions between the most recent time window and the previous time window.

[0014] In one of the embodiments, the change in the average number of revisions of code contributions includes 1, -1 or 0, where 1 indicates an increase, -1 indicates a decrease, and 0 indicates no change.

[0015] In one of the embodiments, the change in the average number of review comments for code contributions includes 1, -1 or 0, where 1 indicates an increase, -1 indicates a decrease, and 0 indicates no change.

[0016] A collaborative knowledge obsolescence detection device for an open source community, the device comprising:

[0017] A sample acquisition module is used to acquire historical collaboration data in an open source software project and construct training samples based on the historical collaboration data; the training samples include observation value vectors of an independent variable set within an observation window at the current moment; the independent variable set includes revision history information of an open source collaboration knowledge document and community dynamic interaction information; the training samples are marked by labels; when the label is 1, it indicates that the open source collaboration knowledge document is revised at the current moment; when the label is 0, it indicates that the open source collaboration knowledge document is not revised at the current moment;

[0018] A model fitting module is used to input the training samples into the logistic regression model for fitting, so as to obtain an outdated detection model; the outdated detection model is used to represent the relationship between the independent variable set and the dependent variable; when the dependent variable is 1, it indicates that the open source collaborative knowledge document needs to be revised and there is an outdated risk; when the dependent variable is 0, it indicates that the open source collaborative knowledge document does not need to be revised and there is no outdated risk;

[0019] The outdated detection module is used to input the observation value vector of the independent variable set within the observation window period of the time point to be detected into the outdated detection model to obtain the outdated detection result of the open source collaborative knowledge document.

[0020] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0021] Obtain historical collaboration data in an open source software project, and construct training samples based on the historical collaboration data; the training samples include observation value vectors of an independent variable set within an observation window at the current moment; the independent variable set includes revision history information of an open source collaboration knowledge document and community dynamic interaction information; the training samples are labeled by a label; when the label is 1, it indicates that the open source collaboration knowledge document is revised at the current moment; when the label is 0, it indicates that the open source collaboration knowledge document is not revised at the current moment;

[0022] The training samples are input into the logistic regression model for fitting to obtain an outdated detection model; the outdated detection model is used to represent the relationship between the independent variable set and the dependent variable; when the dependent variable is 1, it indicates that the open source collaborative knowledge document needs to be revised and there is an outdated risk; when the dependent variable is 0, it indicates that the open source collaborative knowledge document does not need to be revised and there is no outdated risk;

[0023] The observation value vector of the independent variable set within the observation window period of the time point to be detected is input into the obsolescence detection model to obtain the obsolescence detection result of the open source collaborative knowledge document.

[0024] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the following steps:

[0025] Obtain historical collaboration data in an open source software project, and construct training samples based on the historical collaboration data; the training samples include observation value vectors of an independent variable set within an observation window at the current moment; the independent variable set includes revision history information of an open source collaboration knowledge document and community dynamic interaction information; the training samples are labeled by a label; when the label is 1, it indicates that the open source collaboration knowledge document is revised at the current moment; when the label is 0, it indicates that the open source collaboration knowledge document is not revised at the current moment;

[0026] The training samples are input into the logistic regression model for fitting to obtain an outdated detection model; the outdated detection model is used to represent the relationship between the independent variable set and the dependent variable; when the dependent variable is 1, it indicates that the open source collaborative knowledge document needs to be revised and there is an outdated risk; when the dependent variable is 0, it indicates that the open source collaborative knowledge document does not need to be revised and there is no outdated risk;

[0027] The observation value vector of the independent variable set within the observation window period of the time point to be detected is input into the obsolescence detection model to obtain the obsolescence detection result of the open source collaborative knowledge document.

[0028] The above-mentioned collaborative knowledge obsolescence detection method, device and equipment for the open source community avoids the delay of manual detection by automatically acquiring historical collaborative data, and ensures real-time monitoring of document obsolescence risks. Secondly, by constructing a multi-dimensional independent variable set, the document revision history and community dynamic interaction information are integrated, which can improve the accuracy and comprehensiveness of detection. The clarity of training samples is ensured by labeling, and the model is supported to learn the rules of document revision. By training the logistic regression model, it can quickly and accurately predict whether the document is outdated, and realize automated obsolescence detection. Finally, the method of the present invention is real-time and can instantly feedback the revision needs of open source collaborative knowledge documents, reducing developers' dependence on outdated documents, helping to ensure the timeliness of collaborative knowledge, thereby improving the participation efficiency of open source contributors and the sustainable and healthy development of the project. The embodiments of the present invention can improve the intelligence level of document management in the open source community and ensure the timely updating and effective transmission of collaborative knowledge. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 A schematic diagram of a process of a collaborative knowledge obsolescence detection method for an open source community in one embodiment;

[0030] Figure 2 2 is a structural block diagram of a collaborative knowledge obsolescence detection device for an open source community in one embodiment, wherein 202 represents a sample acquisition module, 204 represents a model fitting module, and 206 represents an obsolescence detection module;

[0031] Figure 3 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0032] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0033] In one embodiment, Figure 1 As shown, a collaborative knowledge obsolescence detection method for an open source community is provided, including the following steps:

[0034] Step 102: Obtain historical collaboration data in the open source software project, and construct training samples based on the historical collaboration data.

[0035] It can be understood that by obtaining historical collaboration data in open source software projects (including code revision history and community interaction dynamics data), a data set can be automatically constructed as the basis for subsequent model training. In this way, the model can automatically identify whether there is outdated knowledge based on historical data without manual intervention. This makes it possible to track document revisions and community dynamics in open source projects in real time, and promptly discover whether documents are outdated, reducing the tediousness and lag of manual detection and improving work efficiency.

[0036] The training samples include the observation value vectors of the independent variable set within the observation window at the current moment; the independent variable set includes the revision history information of the open source collaborative knowledge document and the community dynamic interaction information; the training samples are marked with labels; when the label is 1, it means that the open source collaborative knowledge document has been revised at the current moment; when the label is 0, it means that the open source collaborative knowledge document has not been revised at the current moment.

[0037] It can be understood that by constructing a set of independent variables that include open source collaborative knowledge document revision history information and community dynamic interaction information, the method can comprehensively reflect the multi-dimensional information that affects whether a document is outdated. Open source collaborative knowledge document revision history information can reflect whether the document has been updated, while community dynamic interaction information (such as developer discussions, review comments, etc.) reflects whether there are new requirements or changes in the document during the development process. The independent variable set integrates multi-dimensional collaborative information, which can more accurately judge the timeliness of the document and avoid missing multiple factors that may cause the document to be outdated, thereby improving the accuracy and timeliness of detection.

[0038] Step 104: input the training samples into the logistic regression model for fitting to obtain an outdated detection model.

[0039] The obsolescence detection model is used to represent the relationship between the set of independent variables and the dependent variable. The model contains a binary dependent variable Y, which indicates whether the open source collaborative knowledge document has been revised. When the dependent variable is 1, it means that the open source collaborative knowledge document needs to be revised and there is a risk of obsolescence. When the dependent variable is 0, it means that the open source collaborative knowledge document does not need to be revised and there is no risk of obsolescence.

[0040] By learning the relationships in historical data, the model can automatically predict which documents are at risk of becoming obsolete. This not only reduces the burden of manual review, but also improves the efficiency and accuracy of detection. The model can quickly make judgments when new data enters, thereby ensuring the currency of the document.

[0041] Step 106, inputting the observation value vector of the independent variable set within the observation window period of the time point to be detected into the outdated detection model to obtain the outdated detection result of the open source collaborative knowledge document.

[0042] By inputting the observed value vector of the independent variable set within the observation window period of the time point to be detected into the trained model, the system can immediately feedback whether the document is outdated. This greatly improves the real-time performance of the detection, ensures that the collaborative knowledge in the open source community remains up to date, and developers can obtain document update requirements in the first place, thereby improving the efficiency and quality of open source contributions.

[0043] The method of the present invention can automatically identify whether there is outdated collaborative knowledge in the open source collaborative knowledge document, so as to remind the open source project manager to maintain and update the document in time and ensure the smooth participation of open source contributors.

[0044] In the above-mentioned collaborative knowledge obsolescence detection method for the open source community, the delay of manual detection is avoided by automatically acquiring historical collaborative data, ensuring real-time monitoring of document obsolescence risks. Secondly, by constructing a multi-dimensional independent variable set, the document revision history and community dynamic interaction information are integrated, which can improve the accuracy and comprehensiveness of detection. The clarity of the training samples is ensured by labeling, and the model is supported to learn the rules of document revision. By training the logistic regression model, it can quickly and accurately predict whether the document is outdated, and realize automated obsolescence detection. Finally, the method of the present invention is real-time and can instantly feedback the revision needs of open source collaborative knowledge documents, reducing developers' dependence on outdated documents, helping to ensure the timeliness of collaborative knowledge, thereby improving the participation efficiency of open source contributors and the sustainable and healthy development of the project. The embodiments of the present invention can improve the intelligence level of document management in the open source community and ensure the timely updating and effective transmission of collaborative knowledge.

[0045] In one embodiment, training samples are constructed based on historical collaboration data, including: obtaining a revision list of open source collaboration knowledge documents from a code repository of open source software; each element in the revision list includes a revision time attribute; constructing a positive sample based on an observation value vector of an independent variable set within an observation window period of the revision time attribute; the label of the positive sample is 1; deleting the time period corresponding to the positive sample on the timeline of the historical collaboration data, randomly selecting multiple observation windows within the remaining time period, and constructing a negative sample based on the observation value vector of the independent variable set within each observation window period; the label of the negative sample is 0.

[0046] Specifically, we first obtain complete historical collaboration data from open source software projects, including code revision data and community interaction data, and then construct a training dataset based on the collaboration data. The dataset construction includes positive sample data construction and negative sample data construction.

[0047] For the construction of positive sample data, we first retrieve the revision history of the open source collaborative knowledge document from the code repository of the open source software project and obtain the revision list R_list (the size of R_list is n). Each element in R_list (i≤1≤n) has 1 attribute represents the time when the revision occurred. Then, for each ,based on , get the past observation window period (i.e. [ ], is the size of the observation window) the observed value vector of all variables , and form 1 positive sample ( , 1).

[0048] For the construction of negative sample data, firstly, the time period covered by the positive sample data is deleted from the complete timeline involved in the project collaboration data, and then n time periods of observation window size are randomly selected in the remaining time segments. In each time window, the observation value vector of all variables is measured and obtained. , and form 1 negative sample ( , 0).

[0049] The datasets of positive and negative samples are fused and input into the logistic regression model for training. After the training, the outdated detection model M is obtained.

[0050] In one embodiment, an observation value vector of an independent variable set within an observation window period of a time point to be detected is input into an outdated detection model to obtain an outdated detection result of the open source collaborative knowledge document, including: calculating an observation value vector of an independent variable set within an observation window period of the time point to be detected, inputting the observation value vector into the outdated detection model, and obtaining a predicted value; if the predicted value is 0, it means that the open source collaborative knowledge document does not need to be revised and there is no risk of obsolescence; if the predicted value is 1, it means that the open source collaborative knowledge document needs to be revised and there is a risk of obsolescence.

[0051] Specifically, the outdated detection model M is used regularly to predict the revision requirements of open source collaborative knowledge documents. At a given time point t, the observation value vector of all indicators is first calculated: , input model M and get the predicted value .

[0052] when When it is 0, it means that the open source collaborative knowledge document does not need to be revised and there is no risk of obsolescence.

[0053] when When it is 1, it indicates that the open source collaboration knowledge document needs to be revised and therefore there is a risk of being outdated. Therefore, an outdated risk mark is added to the open source collaboration knowledge document to remind project management to update it.

[0054] In one embodiment, when the outdated detection result indicates that the open source collaborative knowledge document is at risk of being outdated, an outdated risk mark is added to the open source collaborative knowledge document to remind project management to update it.

[0055] In one embodiment, the set of independent variables is ( , , , , ),in, Indicates the number of times the open source software source code file has been revised in the most recent time window. Indicates the number of times the open source software technical documentation has been revised in the most recent time window. Indicates the number of times the open source software community document has been revised in the most recent time window. Indicates the proportion of code contributions submitted by core developers in the most recent time window. Indicates the change in the average number of revisions of code contributions in the most recent time window compared to the previous time window. Indicates the change in the average number of review comments for code contributions between the most recent time window and the previous time window.

[0056] In one embodiment, the change in the average revision count of code contributions includes 1, -1, or 0, where 1 indicates an increase, -1 indicates a decrease, and 0 indicates no change.

[0057] In one embodiment, the change in the average number of review comments for code contributions includes 1, -1, or 0, where 1 indicates an increase, -1 indicates a decrease, and 0 indicates no change.

[0058] It should be understood that although Figure 1 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 1 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0059] In one embodiment, Figure 2 As shown, a collaborative knowledge obsolescence detection device for an open source community is provided, comprising:

[0060] The sample acquisition module 202 is used to acquire historical collaboration data in the open source software project and construct training samples based on the historical collaboration data; the training samples include the observation value vector of the independent variable set within the observation window period at the current moment; the independent variable set includes the revision history information of the open source collaboration knowledge document and the community dynamic interaction information; the training samples are marked by labels; when the label is 1, it means that the open source collaboration knowledge document is revised at the current moment; when the label is 0, it means that the open source collaboration knowledge document is not revised at the current moment;

[0061] The model fitting module 204 is used to input the training samples into the logistic regression model for fitting, and obtain the obsolescence detection model; the obsolescence detection model is used to represent the relationship between the independent variable set and the dependent variable; when the dependent variable is 1, it means that the open source collaborative knowledge document needs to be revised and there is an obsolescence risk; when the dependent variable is 0, it means that the open source collaborative knowledge document does not need to be revised and there is no obsolescence risk;

[0062] The outdated detection module 206 is used to input the observation value vector of the independent variable set within the observation window period of the time point to be detected into the outdated detection model to obtain the outdated detection result of the open source collaborative knowledge document.

[0063] In one of the embodiments, it is also used to obtain a revision list of open source collaborative knowledge documents from a code repository of open source software; each element in the revision list includes a revision time attribute; a positive sample is constructed based on an observation value vector of an independent variable set within an observation window period of the revision time attribute; the label of the positive sample is 1; the time period corresponding to the positive sample is deleted on the timeline of historical collaborative data, and multiple observation windows are randomly selected in the remaining time period, and a negative sample is constructed based on the observation value vector of the independent variable set within each observation window period; the label of the negative sample is 0.

[0064] In one of the embodiments, it is also used to calculate the observation value vector of the independent variable set within the observation window period of the time point to be detected, and input the observation value vector into the obsolescence detection model to obtain a predicted value; if the predicted value is 0, it means that the open source collaborative knowledge document does not need to be revised and there is no risk of obsolescence; if the predicted value is 1, it means that the open source collaborative knowledge document needs to be revised and there is a risk of obsolescence.

[0065] In one of the embodiments, when the outdated detection result indicates that the open source collaborative knowledge document is at risk of being outdated, an outdated risk mark is added to the open source collaborative knowledge document to remind project management to update it.

[0066] In one embodiment, the set of independent variables is ( , , , , ),in, Indicates the number of times the open source software source code file has been revised in the most recent time window. Indicates the number of times the open source software technical documentation has been revised in the most recent time window. Indicates the number of times the open source software community document has been revised in the most recent time window. Indicates the proportion of code contributions submitted by core developers in the most recent time window. Indicates the change in the average number of revisions of code contributions in the most recent time window compared to the previous time window. Indicates the change in the average number of review comments for code contributions between the most recent time window and the previous time window.

[0067] In one of the embodiments, the change in the average revision number of code contributions includes 1, -1 or 0, where 1 represents an increase, -1 represents a decrease, and 0 represents no change.

[0068] In one of the embodiments, the change in the average number of review comments for code contributions includes 1, -1 or 0, where 1 represents an increase, -1 represents a decrease, and 0 represents no change.

[0069] For the specific limitations of the collaborative knowledge obsolescence detection device for the open source community, please refer to the limitations of the collaborative knowledge obsolescence detection method for the open source community above, which will not be repeated here. Each module in the above-mentioned collaborative knowledge obsolescence detection device for the open source community can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above-mentioned modules.

[0070] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 3As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a collaborative knowledge obsolescence detection method for an open source community is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0071] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0072] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method in the above embodiment when executing the computer program.

[0073] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method in the above embodiment are implemented.

[0074] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0075] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0076] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention. It should be pointed out that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A collaborative knowledge obsolescence detection method for open source communities, characterized in that: The method comprises: Obtain historical collaboration data in an open source software project, and construct training samples based on the historical collaboration data; the training samples include observation value vectors of an independent variable set within an observation window at the current moment; the independent variable set includes revision history information of an open source collaboration knowledge document and community dynamic interaction information; the training samples are labeled by a label; when the label is 1, it indicates that the open source collaboration knowledge document is revised at the current moment; when the label is 0, it indicates that the open source collaboration knowledge document is not revised at the current moment; The training samples are input into the logistic regression model for fitting to obtain an outdated detection model; the outdated detection model is used to represent the relationship between the independent variable set and the dependent variable; when the dependent variable is 1, it indicates that the open source collaborative knowledge document needs to be revised and there is an outdated risk; when the dependent variable is 0, it indicates that the open source collaborative knowledge document does not need to be revised and there is no outdated risk; The observation value vector of the independent variable set within the observation window period of the time point to be detected is input into the obsolescence detection model to obtain the obsolescence detection result of the open source collaborative knowledge document.

2. The method according to claim 1, characterized in that Construct training samples based on historical collaboration data, including: Obtaining a revision list of an open source collaborative knowledge document from a code repository of the open source software; each element in the revision list includes a revision time attribute; Constructing a positive sample according to the observed value vector of the independent variable set within the observation window period of the revision time attribute; the label of the positive sample is 1; The time period corresponding to the positive sample is deleted on the timeline of the historical collaboration data, and multiple observation windows are randomly selected in the remaining time period. Negative samples are constructed according to the observation value vectors of the independent variable set in each observation window period; the label of the negative sample is 0.

3. The method according to claim 1, characterized in that The observation value vector of the independent variable set within the observation window period of the time point to be detected is input into the outdated detection model to obtain the outdated detection result of the open source collaborative knowledge document, including: Calculate the observation value vector of the independent variable set within the observation window period of the time point to be detected, input the observation value vector into the outdated detection model, and obtain the predicted value; If the predicted value is 0, it means that the open source collaborative knowledge document does not need to be revised and there is no risk of obsolescence; If the predicted value is 1, it means that the open source collaborative knowledge document needs to be revised and there is a risk of obsolescence.

4. The method according to claim 3, characterized in that When the outdated detection result indicates that the open source collaborative knowledge document is at risk of being outdated, an outdated risk mark is added to the open source collaborative knowledge document to remind project management to update it.

5. The method according to claim 1, characterized in that The independent variable set is ( , , , , ),in, Indicates the number of times the open source software source code file has been revised in the most recent time window. Indicates the number of times the open source software technical documentation has been revised in the most recent time window. Indicates the number of times the open source software community document has been revised in the most recent time window. Indicates the proportion of code contributions submitted by core developers in the most recent time window. Indicates the change in the average number of revisions of code contributions in the most recent time window compared to the previous time window. Indicates the change in the average number of review comments for code contributions between the most recent time window and the previous time window.

6. The method according to claim 5, characterized in that The changes in the average number of revisions of code contributions include 1, -1, or 0, where 1 indicates an increase, -1 indicates a decrease, and 0 indicates no change.

7. The method according to claim 5, characterized in that The changes in the average number of review comments for code contributions include 1, -1, or 0, where 1 indicates an increase, -1 indicates a decrease, and 0 indicates no change.

8. A collaborative knowledge obsolescence detection device for an open source community, characterized in that: The device comprises: A sample acquisition module is used to acquire historical collaboration data in an open source software project and construct training samples based on the historical collaboration data; the training samples include observation value vectors of an independent variable set within an observation window at the current moment; the independent variable set includes revision history information of an open source collaboration knowledge document and community dynamic interaction information; the training samples are marked by labels; when the label is 1, it indicates that the open source collaboration knowledge document is revised at the current moment; when the label is 0, it indicates that the open source collaboration knowledge document is not revised at the current moment; A model fitting module is used to input the training samples into the logistic regression model for fitting, so as to obtain an outdated detection model; the outdated detection model is used to represent the relationship between the independent variable set and the dependent variable; when the dependent variable is 1, it indicates that the open source collaborative knowledge document needs to be revised and there is an outdated risk; when the dependent variable is 0, it indicates that the open source collaborative knowledge document does not need to be revised and there is no outdated risk; The outdated detection module is used to input the observation value vector of the independent variable set within the observation window period of the time point to be detected into the outdated detection model to obtain the outdated detection result of the open source collaborative knowledge document.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

Images