Information processing method and device, storage medium and electronic equipment

Abstract

The invention discloses an information processing method and device, a storage medium and electronic equipment. The method relates to the technical field of financial science and technology, and comprises the steps that a target portrait of a target object is acquired, and the target portrait is constructed at least based on historical code data output by the target object; performing knowledge point matching with a knowledge mapping model according to the target portrait and the code defect to obtain matched knowledge information; according to the matched knowledge information, a learning path card is generated, the learning path card is pushed to the target object, and the learning path card at least comprises a recommended knowledge resource link and predicted learning duration. Through the resource recommendation method and device, the problem that the accuracy of resource recommendation is low due to the fact that learning resources are recommended according to posts of developers in the prior art is solved.

Description

Technical Field

[0001] This application relates to the field of financial technology, and more specifically, to an information processing method and apparatus, a storage medium and an electronic device. Background Technology

[0002] In real-world applications, code quality during software development directly impacts system stability and security. Companies aim to reduce code defect rates and improve development efficiency through effective training. However, the software development field commonly employs a job-skill-based training resource recommendation approach. This strategy ignores the individual skill weaknesses and learning needs of developers, resulting in low accuracy in resource recommendations. For instance, even developers in the same role may exhibit significant differences in their abilities regarding exception handling and concurrent programming; traditional training programs often fail to accurately match these personalized needs.

[0003] There is currently no effective solution to the problem of low accuracy in recommending learning resources based on developers' job roles in related technologies. Summary of the Invention

[0004] The main objective of this application is to provide an information processing method and apparatus, storage medium and electronic device to solve the problem in related technologies where recommending learning resources based on the developer's job title results in low accuracy of resource recommendations.

[0005] To achieve the above objectives, according to one aspect of this application, an information processing method is provided. The method includes: obtaining a target profile of a target object, wherein the target profile is constructed at least based on historical code data output by the target object; performing knowledge point matching based on the target profile and a code defect and knowledge mapping model to obtain matching knowledge information; generating a learning path card based on the matching knowledge information, and pushing the learning path card to the target object, wherein the learning path card includes at least: recommended knowledge resource links and estimated learning time.

[0006] Furthermore, obtaining the target profile of the target object includes: obtaining a defect code dataset, aggregating the defect codes in the defect code dataset to obtain the defect patterns corresponding to the defect codes; obtaining the target defect code corresponding to the target object from the defect code dataset; and obtaining the target profile based on the target defect code and the defect pattern corresponding to the defect code.

[0007] Further, obtaining the target profile based on the target defect code and the corresponding defect pattern includes: obtaining a quantitative evaluation matrix of the target object in the knowledge domain where the defect exists, based on the target defect code and the corresponding defect pattern, wherein the quantitative evaluation matrix includes at least the target object in the knowledge domain where the defect exists, and the target score corresponding to that knowledge domain; generating a weakness heatmap based on the quantitative evaluation matrix and target defect code examples; and obtaining the target profile based on the weakness heatmap and the quantitative evaluation matrix.

[0008] Furthermore, after matching knowledge points based on the target profile and the code defect and knowledge mapping model to obtain matched knowledge information, the method further includes: constructing a mapping rule base between the defect pattern and the knowledge points in the target knowledge base based on the defect pattern and the target knowledge base; constructing a target knowledge graph based on the target knowledge base; and constructing the code defect and knowledge mapping model based on the mapping rule base and the target knowledge graph.

[0009] Furthermore, the matching of knowledge points based on the target profile and the code defect and knowledge mapping model to obtain the matching knowledge information includes: obtaining multiple target knowledge domains corresponding to the target object and defect patterns corresponding to each target knowledge domain from the target profile; determining initial knowledge information from the code defect and knowledge mapping model based on the multiple target knowledge domains and the defect patterns corresponding to each target knowledge domain; determining the associated coding environment based on the defect patterns corresponding to each target knowledge domain; and obtaining the matching knowledge information based on the initial knowledge information and the associated coding environment.

[0010] Furthermore, generating a learning path card based on the matching knowledge information includes: determining the dependencies between knowledge information based on the matching knowledge information and the code defect and knowledge mapping model; obtaining the experience level corresponding to the target object based on the attribute parameters of the target object; and obtaining the learning path card based on the dependencies and the experience level.

[0011] Furthermore, after pushing the learning path card to the target object, the method further includes: obtaining target code data output by the target object after learning through a probe; updating the target profile based on the target code data to obtain an updated target profile.

[0012] Furthermore, the method further includes: calculating the validity of knowledge in the target knowledge base based on the target code data to obtain a calculation result; adjusting the weights of knowledge in the target knowledge base based on the calculation result to obtain updated weight values ​​corresponding to knowledge in the target knowledge base; and processing the knowledge in the target knowledge base based on the updated weight values ​​to obtain a processed target knowledge base.

[0013] To achieve the above objectives, according to another aspect of this application, an information processing apparatus is provided. The apparatus includes: a first acquisition unit, configured to acquire a target profile of a target object, wherein the target profile is constructed at least based on historical code data output by the target object; a matching unit, configured to perform knowledge point matching based on the target profile and a code defect and knowledge mapping model to obtain matching knowledge information; and a generation unit, configured to generate a learning path card based on the matching knowledge information and push the learning path card to the target object, wherein the learning path card includes at least: recommended knowledge resource links and estimated learning time.

[0014] Further, the first acquisition unit includes: a first acquisition subunit, used to acquire a defect code dataset and aggregate the defect codes in the defect code dataset to obtain a defect pattern corresponding to the defect code; a second acquisition subunit, used to acquire the target defect code corresponding to the target object from the defect code dataset; and a first determination subunit, used to obtain the target profile based on the target defect code and the defect pattern corresponding to the defect code.

[0015] Further, the determining subunit includes: a first determining module, used to obtain a quantitative evaluation matrix of the target object in the knowledge domain where the defect exists, based on the target defect code and the defect pattern corresponding to the defect code, wherein the quantitative evaluation matrix includes at least the target object in the knowledge domain where the defect exists, and the target score corresponding to the knowledge domain; a generating module, used to generate a weakness heatmap based on the quantitative evaluation matrix and target defect code cases; and a second determining module, used to obtain the target profile based on the weakness heatmap and the quantitative evaluation matrix.

[0016] Furthermore, the device further includes: a first construction unit, configured to, after matching knowledge points based on the target profile and the code defect and knowledge mapping model to obtain matched knowledge information, construct a mapping rule base between the defect pattern and the knowledge points in the target knowledge base based on the defect pattern and the target knowledge base; a second construction unit, configured to construct a target knowledge graph based on the target knowledge base; and a third construction unit, configured to construct the code defect and knowledge mapping model based on the mapping rule base and the target knowledge graph.

[0017] Further, the matching unit includes: a third acquisition subunit, used to acquire multiple target knowledge domains corresponding to the target object and defect patterns corresponding to each target knowledge domain from the target profile; a second determination subunit, used to determine initial knowledge information from the code defect and knowledge mapping model based on the multiple target knowledge domains and the defect patterns corresponding to each target knowledge domain; a third determination subunit, used to determine the associated coding environment based on the defect patterns corresponding to each target knowledge domain; and a fourth determination subunit, used to obtain the matching knowledge information based on the initial knowledge information and the associated coding environment.

[0018] Furthermore, the generation unit includes: a fifth determining subunit, used to determine the dependency relationship between knowledge information based on the matching knowledge information and the code defect and knowledge mapping model; a first processing subunit, used to obtain the experience level corresponding to the target object based on the attribute parameters of the target object; and a second processing subunit, used to obtain the learning path card based on the dependency relationship and the experience level.

[0019] Furthermore, the device further includes: a second acquisition unit, configured to acquire target code data output by the target object after learning via a probe after the learning path card is pushed to the target object; and an update unit, configured to update the target profile based on the target code data to obtain an updated target profile.

[0020] Furthermore, the device further includes: a calculation unit, configured to calculate the validity of knowledge in the target knowledge base based on the target code data, and obtain a calculation result; an adjustment unit, configured to adjust the weights of knowledge in the target knowledge base based on the calculation result, and obtain updated weight values ​​corresponding to the knowledge in the target knowledge base; and to process the knowledge in the target knowledge base based on the updated weight values, and obtain a processed target knowledge base.

[0021] According to another aspect of the present invention, an electronic device is also provided, comprising: a memory storing an executable program; and a processor for running the program, wherein the program executes the information processing method described above during runtime.

[0022] According to another aspect of the present invention, a computer-readable storage medium is also provided, wherein the storage medium stores a program, wherein the program controls the device where the storage medium is located to execute any of the above-described information processing methods during runtime.

[0023] In this embodiment, the following steps are adopted: obtaining a target profile of the target object, wherein the target profile is constructed based at least on the historical code data output by the target object; matching knowledge points according to the target profile and the code defect and knowledge mapping model to obtain matching knowledge information; generating a learning path card based on the matching knowledge information and pushing the learning path card to the target object, wherein the learning path card includes at least: recommended knowledge resource links and estimated learning time, which solves the technical problem in related technologies that recommends learning resources according to the developer's job position, resulting in low accuracy of resource recommendation.

[0024] This solution collects historical code data from the target developer to construct a comprehensive profile reflecting their skill level, common defect types, and repair efficiency. Based on this profile, a deep matching model between code defects and knowledge mapping is used to pinpoint the most relevant knowledge points and learning resources. The matched knowledge information is then integrated to generate a learning path card, which is subsequently pushed to the target developer. This approach ensures that developers receive personalized recommendations promptly, eliminating the need for them to spend extra effort selecting suitable course resources. The construction of the target profile accurately identifies developers' skill gaps, avoids one-size-fits-all job training, reduces resource mismatch, and thus improves the accuracy of resource recommendations. Attached Figure Description

[0025] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0026] Figure 1 This is a hardware structure block diagram of a computer terminal for implementing an information processing method according to an embodiment of this application;

[0027] Figure 2 This is a flowchart of an information processing method provided according to an embodiment of this application;

[0028] Figure 3 This is a schematic diagram of an information processing method provided according to an embodiment of this application;

[0029] Figure 4 This is a schematic diagram of an information processing apparatus provided according to an embodiment of this application;

[0030] Figure 5 This is a structural block diagram of an electronic device according to an embodiment of this application. Detailed Implementation

[0031] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0032] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0033] It should be noted that the information collected in this application (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for display, data used for analysis, etc.) are information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of this data all comply with relevant laws, regulations, and standards, necessary confidentiality measures have been taken, and they do not violate public order and good morals. Corresponding access points are provided for users to choose to authorize or refuse. For example, interfaces are set up between this system and relevant users or organizations, providing users with corresponding access points to choose to agree to or refuse automated decision-making results; if the user chooses to refuse, the process proceeds to the expert decision-making stage.

[0034] Example 1

[0035] According to an embodiment of this application, an embodiment of an information processing method is also provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0036] The method embodiment provided in Embodiment 1 of this application can be executed on a mobile terminal, computer terminal, or similar computing device. Figure 1 A hardware structure block diagram of a computer terminal (or mobile device) for implementing an information processing method is shown. Figure 1 As shown, the computer terminal 10 (or mobile device) may include one or more processors 102 (shown as 102a, 102b, ..., 102n in the figure) 102 (processor 102 may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of a BUS bus), a network interface, a power supply, and / or a camera. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, computer terminal 10 may also include... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0037] It should be noted that the aforementioned one or more processors 102 and / or other data processing circuits are generally referred to herein as "data processing circuits". These data processing circuits may be embodied, in whole or in part, in software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuits may be a single, independent processing module, or may be integrated, in whole or in part, into any other element within the computer terminal 10 (or mobile device). As involved in the embodiments of this application, the data processing circuits serve as a processor control mechanism (e.g., selection of a variable resistor termination path connected to an interface).

[0038] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the information processing method in this embodiment. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, thereby realizing the above-mentioned information processing method. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the computer terminal 10 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0039] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of the computer terminal 10. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0040] The display may be a touchscreen liquid crystal display (LCD) that allows the user to interact with the user interface of the computer terminal 10 (or mobile device).

[0041] Under the aforementioned operating environment, this application provides the following: Figure 2 The information processing method shown. Figure 2 This is a flowchart of an information processing method according to Embodiment 1 of this application. The information processing method includes:

[0042] Step S201: Obtain the target profile of the target object, wherein the target profile is constructed based at least on the historical code data output by the target object.

[0043] Optionally, code commit records of the target object can be extracted from the source code repository via API or custom scripts, including information such as commit time, modified files, and lines of code. This data can reveal the developer's coding habits, coding style, and frequently modified code modules. After obtaining the raw code data, code modules and modification types are extracted from the code commit records; defect types and repair efficiency are extracted from defect reports, and these features are converted into quantitative indicators. For example, the frequency of occurrence of specific defect types can be used to assess the target object's skill level in the relevant field; and the average repair time and defect recurrence rate can be calculated to measure its defect management capabilities, thereby generating a target profile of the target object.

[0044] It should be noted that the profile can be updated according to a preset time window to reflect the target's latest skill status and growth trend. The profile can also be updated immediately when the target encounters a serious code defect or successfully fixes a critical issue, ensuring that the learning resource recommendation strategy can be adjusted in a timely manner.

[0045] Step S202: Based on the target profile and the code defect and knowledge mapping model, knowledge points are matched to obtain matching knowledge information.

[0046] Optionally, based on the skill weaknesses revealed in the target profile, and combined with a code defect-knowledge mapping model, the most relevant knowledge points and learning resources that can best improve the target's skills can be identified and matched. It should be noted that the defect-knowledge mapping model can be a multi-level relational database that tightly links code defect types, descriptions, and fixes with knowledge domains, knowledge points, and learning resources.

[0047] In an optional embodiment, the most relevant knowledge points can be matched using a preset rule engine based on the capability scores of each knowledge domain in the target profile. For example, if the target object has a low capability score in the database optimization domain, the rule engine will automatically match knowledge points related to "pagination query optimization" and "index design".

[0048] In an alternative embodiment, for more complex or specific skill problems, NLP techniques can be used to parse the defect description, extract key information (such as the exception type, the technical field involved, the specific code module, etc.), and match it with concepts in a knowledge graph to determine the most relevant learning resources. For example, for a defect described as "service becomes unstable when handling a large number of concurrent requests," NLP can identify "concurrent programming" and "service stability" as relevant areas, and then recommend knowledge points such as "thread-safe programming" and "load balancing strategies."

[0049] The algorithm described above can generate a list of matching knowledge information for each target object. The list can include: knowledge domain: such as exception handling, concurrent programming, etc.; knowledge point ID: refined to specific concepts, such as NPE-001 (null pointer exception handling); and learning resource recommendations: links and information of related courses, documents, practical laboratories, and other resources.

[0050] Step S203: Based on the matching knowledge information, generate a learning path card and push the learning path card to the target object. The learning path card includes at least: recommended knowledge resource links and estimated learning time.

[0051] Optionally, based on the matching knowledge information obtained in step S202, the most relevant learning materials are selected from the knowledge resource base, and the expected learning time is estimated according to their content depth and difficulty, thereby obtaining the learning path card.

[0052] For example, the logic for generating learning path cards is shown in Table 1.

[0053] Table 1

[0054]

[0055] Once you have the learning path card, you can send it to the target audience through various channels, such as sending an email with details of the learning path card, so that the target audience can view and schedule their learning plan outside of work hours.

[0056] In summary, by collecting historical code data from the target developer, a comprehensive profile reflecting their skill level, common defect types, and repair efficiency is constructed. Based on this profile, a deep matching process using a code defect and knowledge mapping model is employed to pinpoint the most relevant knowledge points and learning resources. This matched knowledge information is then integrated to generate a learning path card, which is subsequently pushed to the target developer. This approach ensures that developers receive personalized recommendations promptly, eliminating the need for them to expend extra effort in selecting suitable course resources. The construction of this target profile accurately identifies developer skill gaps, avoids one-size-fits-all job training, reduces resource mismatch, and ultimately improves the accuracy of resource recommendations.

[0057] Optionally, in the information processing method provided in this application embodiment, obtaining the target profile of the target object includes: obtaining a defect code dataset, and aggregating the defect codes in the defect code dataset to obtain the defect patterns corresponding to the defect codes; obtaining the target defect code corresponding to the target object from the defect code dataset; and obtaining the target profile based on the target defect code and the defect pattern corresponding to the defect code.

[0058] In one optional embodiment, a defective code dataset is obtained. For example, for code already in the repository, the system connects to the enterprise's source code version control system and existing defect management system to extract defect data and obtain the developer's code submission history by parsing the source code repository's commit history, establishing a mapping relationship. For unrepository and intercepted process code, the system connects to the enterprise's code quality system and code review system to obtain the intercepted code defects by analyzing code quality reports and code review records. For local development activities, the system connects to the operation log data of the development IDE plugin to obtain the code issues intercepted by local IDE alerts.

[0059] Because the raw defect data obtained may contain noise, duplication, and inconsistencies, rigorous data cleaning is required. The cleaning process includes the following steps: Invalid data filtering: The system filters invalid defect records according to predefined rules, including: defects with a status of "WONTFIX" (usually due to business decisions rather than technical reasons), low-confidence defects reported by automated scanning tools (such as confidence levels below 70%), non-code defects caused by environmental issues (such as network failures or configuration errors), and duplicate defect reports (based on deduplication of the same code location and error type).

[0060] Defect attribution analysis: For defects where the responsible party is not clearly identified, the system accurately attributes the defect to the source code version control system by connecting to the system and analyzing who last modified the defective line of code; for defects with a large scope (such as those involving multiple files), the system determines the primary responsible party by combining the commit history and code review records; if the defect is caused by multiple people collaborating, the system allocates the responsibility ratio according to the weight of the code modifications (such as the percentage of lines modified).

[0061] Defect pattern clustering: Unsupervised learning algorithms are used to cluster defects and merge similar defects. This includes feature extraction (converting information such as defect type, description text, and code module into TF-IDF vectors), cluster analysis (calculating similarity based on feature vectors, grouping defects with different descriptions but the same essence into one category, such as "Null PointerException" and "Null PointerException"), and pattern labeling: assigning a unique pattern ID to each cluster (e.g., NP-001 represents null pointer exception).

[0062] The above steps are used to obtain the target defect code corresponding to the target object. Then, based on the target defect code and the defect pattern corresponding to the defect code, a target profile is obtained.

[0063] By analyzing the target defect code, we can obtain an overall skill profile of the target object, and also pinpoint its actual mastery level and skill weaknesses in a specific knowledge domain.

[0064] Optionally, in the information processing method provided in this application embodiment, after matching knowledge points based on the target profile and the code defect and knowledge mapping model to obtain matched knowledge information, the method further includes: constructing a mapping rule base between the defect pattern and the knowledge points in the target knowledge base based on the defect pattern and the target knowledge base; constructing a target knowledge graph based on the target knowledge base; and constructing a code defect and knowledge mapping model based on the mapping rule base and the target knowledge graph.

[0065] In an optional embodiment, a predefined mapping rule base for defect patterns and knowledge units is established, for example, the mapping rule base is shown in Table 2.

[0066] Table 2

[0067]

[0068] It should be noted that the priority can be automatically adjusted according to the severity level of the defect: for defects with a severity level of "fatal" or "blocking", the learning priority of the related knowledge points is increased by 1.5 times.

[0069] Due to potential complexities not covered by the rule base, a target knowledge graph is constructed based on the target knowledge base. This target knowledge graph can contain a three-layer structure: knowledge domains (e.g., "secure coding"), knowledge units (e.g., "SQL injection prevention"), and learning resources (e.g., Chapter 3 of the course "Web Security Practice"). For example, graph initialization: First, a blank knowledge graph is created, containing the graph's backbone structure, i.e., nodes representing knowledge domains, such as "secure coding" and "exception handling." Knowledge unit population: Under each knowledge domain node, specific knowledge unit nodes are populated, such as "SQL injection prevention" and "null pointer exception handling," ensuring the graph's content is comprehensive and specific. Learning resource links: Relevant learning resources are linked for each knowledge unit, including but not limited to courses, documents, and practical experiments, ensuring the completeness and practicality of the learning path. Dependency mapping: Dependencies between knowledge points are identified and mapped; for example, "SQL injection prevention" may depend on "input validation," and "deadlock prevention" may depend on "concurrency control fundamentals." Clearly defined dependencies help generate learning paths that conform to the knowledge structure.

[0070] By combining a mapping rule base and a target knowledge graph, a code defect and knowledge mapping model is constructed to ensure that any given defect pattern can quickly find its knowledge domain, knowledge unit, and recommended learning resources.

[0071] By using a mapping rule base and a target knowledge graph, we can more accurately identify and recommend the knowledge points and learning resources that are most relevant to the improvement of the target's skills and are most urgently needed.

[0072] Optionally, in the information processing method provided in this application embodiment, obtaining the target profile based on the target defect code and the defect pattern corresponding to the defect code includes: obtaining a quantitative evaluation matrix of the target object in the knowledge domain where the defect exists based on the target defect code and the defect pattern corresponding to the defect code, wherein the quantitative evaluation matrix includes at least the target object in the knowledge domain where the defect exists, and the target score corresponding to the knowledge domain; generating a weakness heatmap based on the quantitative evaluation matrix and the target defect code case; and obtaining the target profile based on the weakness heatmap and the quantitative evaluation matrix.

[0073] In an optional embodiment, all defective code extracted from the target object's codebase is matched against its corresponding patterns in the defective code dataset. These defects are then categorized according to their respective knowledge domains, such as exception handling, concurrent programming, and database optimization. A set of quantitative metrics is defined for each knowledge domain, such as the number of defects, fix time, and defect recurrence rate. These metrics are used to evaluate the target object's skill level in that domain. The specific calculation methods for the quantitative metrics are as follows: Number of defects: The number of defects encountered by the target object in that domain within a certain period of time. Fix time: The average time required for the target object to fix these defects is calculated and compared with a benchmark (such as the team's average fix time). Defect recurrence rate: The percentage of a defect pattern that reappears in the target object's code after being fixed.

[0074] Based on the above quantitative indicators, a target score is calculated for each knowledge domain, which reflects the skill status of the target object. The calculation formula is: Target score = Baseline score (80) - (Number of defects × 0.5 + Repair time index × 10 + Number of recurrences × 2), where the repair time index = Actual repair time / Team average repair time.

[0075] In an optional embodiment, the quantification evaluation matrix is ​​shown in Table 3.

[0076] Table 3

[0077]

[0078] It should be noted that the trends in Table 3 can be calculated by comparing data from the past three months and calculating the rate of change in scores for each area (e.g., “the score for exception handling decreased by 8%”).

[0079] Then, a two-dimensional heatmap can be designed, using knowledge domains as the dimension and target scores as the values. Different colors represent different score ranges, with darker colors indicating greater skill deficiencies. Linking the deficiency cases under each knowledge domain in the quantitative assessment matrix to the heatmap not only visually displays skill weaknesses but also provides concrete examples.

[0080] In an optional embodiment, the three knowledge areas with the lowest overall scores can be selected as the main weaknesses, and typical defect cases corresponding to each weakness can be listed (such as "database optimization area: pagination query not using indexes"), and then an interactive heatmap can be generated, using color depth to represent the degree of weakness (for example, the darker the red, the weaker the capability).

[0081] Finally, the information from the quantitative evaluation matrix and heatmap is integrated to form a target profile. In addition to quantitative indicators and scores, the profile can also include metadata such as the target's personal information, job title, and work experience to provide comprehensive background information.

[0082] By using quantitative assessment matrices and heatmaps, it is possible to accurately pinpoint the knowledge areas where target individuals have skill gaps, as well as the specific extent of these gaps, providing precise direction for subsequent personalized training.

[0083] Optionally, in the information processing method provided in this application embodiment, the matching of knowledge points based on the target profile and the code defect and knowledge mapping model to obtain the matched knowledge information includes: obtaining multiple target knowledge domains corresponding to the target object and the defect patterns corresponding to each target knowledge domain from the target profile; determining initial knowledge information from the code defect and knowledge mapping model based on the multiple target knowledge domains and the defect patterns corresponding to each target knowledge domain; determining the associated coding environment based on the defect patterns corresponding to each target knowledge domain; and obtaining the matched knowledge information based on the initial knowledge information and the associated coding environment.

[0084] In an optional embodiment, knowledge domains with low skill scores or high defect recurrence rates are identified from the target profile. For each identified target knowledge domain, relevant defect patterns are extracted from the target profile. For example, if "database security" is one of the target knowledge domains, then all defect patterns related to SQL injection, unencrypted data transmission, etc., will be extracted. Based on the extracted target knowledge domains and defect patterns, a code defect-knowledge mapping model is queried to find knowledge points directly associated with these defect patterns. For example, the "SQL injection protection" knowledge unit may be directly related to the SQL-001 defect pattern. Based on the query results, initial knowledge information is constructed, including target knowledge domains, related knowledge point IDs and their descriptions, learning priorities of knowledge units, etc.

[0085] Then, based on the defect pattern and associated practical scenarios (such as "Unused Index → ​​Index Optimization Lab"), an interactive coding environment (i.e., the associated coding environment mentioned above) is provided. For example: Defect SQL-003 → Matching Experiment "Pagination Query Index Optimization Lab" (including a pre-built defect code sandbox). The initial knowledge information is combined with the associated coding environment information to generate a set of matching knowledge information that integrates the characteristics of knowledge domain, knowledge points, and programming environment, ensuring that the recommended learning resources not only meet the needs of skill improvement but are also applicable to actual work scenarios.

[0086] By deepening the application of target profiling, and combining code defect and knowledge mapping model queries with environment adaptability analysis, we have achieved personalized and environment-adaptable learning path recommendations.

[0087] In an optional embodiment, the top 3 knowledge domains with the lowest overall scores (such as "database optimization" and "anomaly handling") are extracted from the developer profile (i.e., the target profile) and associated with specific defect patterns (such as "pagination query not using index"). Priority is used to sort them: P0 (high) > P1 (medium) > P2 (low), prioritizing the resolution of knowledge points associated with high-severity defects. The weighting formula is: Priority weight = (100 - overall score) × priority coefficient (priority coefficient: P0 = 1.5, P1 = 1.2, P2 = 1.0). For example, database optimization weight = (100 - 45) × 1.5 = 82.5. The sorting rule is to select the top 3 domains with the highest weight values; if the weights are the same, they are sorted in descending order of the number of defects.

[0088] Next, knowledge retrieval and resource matching: Basic course matching: Identifying core knowledge points in weak knowledge areas (e.g., "Database Optimization → Index Design Principles"), and matching them with introductory-level resources (micro-lecture videos, documents). For example, extracting defect pattern IDs and matching related knowledge points, filtering basic resources and sorting them by popularity and historical completion rate to obtain the corresponding knowledge resources. Finally, advanced experiment matching: Providing an interactive coding environment based on defect patterns and associated practical scenarios (e.g., "Unused Index → ​​Index Optimization Lab"). For example: Defect SQL-003 → matching experiment "Pagination Query Index Optimization Lab" (including a pre-built defect code sandbox).

[0089] By deepening the application of target profiling, and combining code defect and knowledge mapping model queries with environment adaptability analysis, we have achieved personalized and environment-adaptable learning path recommendations.

[0090] Optionally, in the information processing method provided in this application embodiment, generating a learning path card based on matching knowledge information includes: determining the dependency relationship between knowledge information based on matching knowledge information and code defect and knowledge mapping model; obtaining the experience level corresponding to the target object based on the attribute parameters of the target object; and obtaining the learning path card based on the dependency relationship and experience level.

[0091] In an optional embodiment, dependencies between knowledge points are identified from a code defect and knowledge mapping model based on matching knowledge information. For example, if the "parameterized query" knowledge point depends on "input validation," then the "input validation" course should be scheduled before "parameterized query" in the learning path. The order of the learning path is automatically arranged according to these dependencies to ensure the coherence and depth of the learning content.

[0092] Then, attribute parameters, such as years of work experience and job title, can be extracted from the target object's profile. Based on the extracted attribute parameters and predefined experience level rules (such as junior, intermediate, and senior), the corresponding experience level of the target object can be calculated.

[0093] Finally, by combining the target audience's experience level and the dependencies between knowledge information, the system generates a personalized learning path card. The content and difficulty level of the path card will be adjusted according to the target audience's experience level to ensure that the learning content is challenging but not beyond their capabilities.

[0094] In an alternative embodiment, prerequisite knowledge points are examined through a knowledge graph (i.e., the dependencies between knowledge information are determined, such as mastering "input validation" before learning "parameterized query" (parameterized query --> input validation --> SQL syntax basics --> index design principles --> B+ tree data structure).

[0095] In an optional embodiment, the resource type is dynamically adjusted based on the developer profile's experience level and defect pattern characteristics. For example, as shown in Table 4.

[0096] Table 4

[0097]

[0098] By deepening the analysis of dependencies and calculating the experience level of the target audience, a highly systematic, structured, and personalized learning path card was generated. This ensured that the learning content was closely related to the skill level, learning needs, and development environment preferences of the target audience, thereby improving learning efficiency and satisfaction.

[0099] Optionally, in the information processing method provided in the embodiments of this application, after the learning path card is pushed to the target object, the method further includes: obtaining the target code data output by the target object after learning through a probe; updating the target profile based on the target code data to obtain the updated target profile.

[0100] In an optional embodiment, code quality probes are deployed to track changes in the target object's code quality after learning. These probes are installed in the target object's development environment, including but not limited to IDE probes, CI / CD probes, and production environment monitoring probes, ensuring comprehensive coverage of all stages from code writing and integration testing to production operation. The probes are responsible for collecting new code output from the target object under the guidance of the learning pathcard, either in real-time or periodically, including but not limited to key indicators such as code submission frequency, new defect occurrences, and defect fixing efficiency. The target code data collected by the probes is integrated with the previous target profile to update the target profile.

[0101] In an optional embodiment, the probes are deployed as shown in Table 5.

[0102] Table 5

[0103]

[0104] The probe's real-time monitoring capability ensures that changes in the target's learning effectiveness can be captured instantly, and the content and difficulty of the learning path card can be dynamically adjusted according to the target's latest skill status to ensure that they are always in the best state.

[0105] Optionally, in the information processing method provided in the embodiments of this application, the method further includes: calculating the validity of knowledge in the target knowledge base based on the target code data to obtain a calculation result; adjusting the weights of knowledge in the target knowledge base based on the calculation result to obtain updated weight values ​​corresponding to the knowledge in the target knowledge base; and processing the knowledge in the target knowledge base based on the updated weight values ​​to obtain a processed target knowledge base.

[0106] In an optional embodiment, based on the target code data collected after the learning path card is pushed, including defect occurrence frequency, changes in repair efficiency, and code quality improvement index, a quantitative indicator of knowledge effectiveness is calculated for each knowledge unit based on the changes in target code data after the implementation of its associated learning path card. Based on the calculated knowledge effectiveness results, the weight of each knowledge unit in the knowledge base is automatically adjusted. For example, the weight of high-performing knowledge units can be appropriately increased, while the weight of low-performing units can be decreased. By adjusting the knowledge weights, knowledge units that have consistently performed poorly can be automatically eliminated, while new and more efficient knowledge units can be introduced based on new needs and trends, maintaining the vitality and applicability of the knowledge base. The knowledge units with adjusted weights are integrated into the optimized target knowledge base, ensuring that all learning resources are reasonably sorted and categorized, facilitating subsequent learning path recommendations and personalized matching.

[0107] In an optional embodiment, the knowledge effectiveness in the target knowledge base can be calculated as follows: Recurrence Rate: Recurrence Rate = Number of recurrences of the same type of defect / Total number of defects covered by this path × 100%; Judgment logic: If the same developer repeatedly produces a defect on the same knowledge point (based on defect pattern ID matching), it is counted as a recurrence. Efficiency Gain: Efficiency Gain = (Historical average repair time - Post-training repair time) / Historical average repair time × 100%. Path Effectiveness: Path Effectiveness = (1 - Recurrence Rate) × 0.6 + Efficiency Gain × 0.4.

[0108] In an optional embodiment, if the validity of a path associated with a resource is less than 50% for three consecutive times, the weight is reduced to the initial value of 30%. Resource removal rule: If the weight is less than 40% for 6 consecutive months and the usage rate decreases by 70%, it is marked as an "inefficient resource" and removed from the recommendation pool.

[0109] In an alternative embodiment, a path effectiveness heatmap can be constructed, with the X-axis representing the knowledge domain (e.g., "database optimization"), the Y-axis representing the developer group (beginner / intermediate / advanced), and the color depth representing the path effectiveness score (dark green >75%, light green 50-75%, red <50%).

[0110] It can also construct a defect recurrence trend chart to show the defect recurrence rate comparison curve of the same developer before and after training. For example: before training: recurrence rate 45% → 7 days after training: 20% → 30 days after training: 8%.

[0111] Resource efficiency rankings can also be constructed, as shown in Table 6.

[0112] Table 6

[0113]

[0114] In an alternative embodiment, it can be achieved through, as follows: Figure 3 The diagram illustrates a developer skill enhancement learning path recommendation method based on code defect analysis, comprising a data acquisition layer, an analysis engine layer, a recommendation service layer, and an effectiveness verification layer. The data acquisition layer obtains end-to-end code defect data through multiple channels. The analysis engine layer, the core processing unit, transforms raw defect data into structured knowledge mappings and developer profiles. This layer includes three key steps: data cleaning and deduplication, defect-knowledge mapping model construction, and dynamic developer profile generation. It provides crucial inputs to the recommendation service layer, including developer profiles (such as skill weakness heatmaps and comprehensive scores) and defect-knowledge mapping models (such as knowledge graphs and learning resource libraries), supporting the generation and dynamic optimization of personalized learning paths.

[0115] The recommendation service layer generates personalized, actionable learning paths for developers based on the dynamic developer profiles and defect-knowledge mapping models generated by the analysis engine layer, and dynamically optimizes the recommendation strategy. The effectiveness verification layer tracks the implementation effect of the learning path by deploying code quality probes, quantitatively evaluates the training effectiveness, and dynamically feeds back to the recommendation system to optimize the strategy, forming a complete closed-loop feedback mechanism.

[0116] The information processing method provided in this application embodiment obtains a target profile of a target object, wherein the target profile is constructed at least based on the historical code data output by the target object; performs knowledge point matching based on the target profile and a code defect and knowledge mapping model to obtain matching knowledge information; generates a learning path card based on the matching knowledge information, and pushes the learning path card to the target object, wherein the learning path card includes at least: recommended knowledge resource links and estimated learning time, thereby solving the technical problem in related technologies where recommending learning resources according to the developer's job title leads to relatively low accuracy of resource recommendations.

[0117] This solution collects historical code data from the target developer to construct a comprehensive profile reflecting their skill level, common defect types, and repair efficiency. Based on this profile, a deep matching model between code defects and knowledge mapping is used to pinpoint the most relevant knowledge points and learning resources. The matched knowledge information is then integrated to generate a learning path card, which is subsequently pushed to the target developer. This approach ensures that developers receive personalized recommendations promptly, eliminating the need for them to spend extra effort selecting suitable course resources. The construction of the target profile accurately identifies developers' skill gaps, avoids one-size-fits-all job training, reduces resource mismatch, and thus improves the accuracy of resource recommendations.

[0118] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0119] Example 2

[0120] This application also provides an information processing apparatus. It should be noted that the information processing apparatus of this application can be used to execute the information processing method provided in this application. The information processing apparatus provided in this application will be described below.

[0121] According to an embodiment of this application, an apparatus for implementing the above-described information processing method is also provided, such as... Figure 4 As shown, the device includes: a first acquisition unit 401, a matching unit 402, and a generation unit 403.

[0122] The first acquisition unit 401 is used to acquire a target profile of the target object, wherein the target profile is constructed based at least on the historical code data output by the target object;

[0123] Matching unit 402 is used to match knowledge points based on the target profile and code defects and knowledge mapping model to obtain matching knowledge information;

[0124] The generation unit 403 is used to generate a learning path card based on the matching knowledge information and push the learning path card to the target object. The learning path card includes at least: recommended knowledge resource links and estimated learning time.

[0125] The information processing apparatus provided in this application embodiment acquires a target profile of a target object through a first acquisition unit 401, wherein the target profile is constructed based at least on the historical code data output by the target object; a matching unit 402 performs knowledge point matching based on the target profile and the code defect and knowledge mapping model to obtain matching knowledge information; and a generation unit 403 generates a learning path card based on the matching knowledge information and pushes the learning path card to the target object, wherein the learning path card includes at least: recommended knowledge resource links and estimated learning time, which solves the technical problem in related technologies that recommends learning resources according to the developer's job position, resulting in relatively low accuracy of resource recommendations.

[0126] This solution collects historical code data from the target developer to construct a comprehensive profile reflecting their skill level, common defect types, and repair efficiency. Based on this profile, a deep matching model between code defects and knowledge mapping is used to pinpoint the most relevant knowledge points and learning resources. The matched knowledge information is then integrated to generate a learning path card, which is subsequently pushed to the target developer. This approach ensures that developers receive personalized recommendations promptly, eliminating the need for them to spend extra effort selecting suitable course resources. The construction of the target profile accurately identifies developers' skill gaps, avoids one-size-fits-all job training, reduces resource mismatch, and thus improves the accuracy of resource recommendations.

[0127] Optionally, in the information processing apparatus provided in the embodiments of this application, the first acquisition unit includes: a first acquisition subunit, used to acquire a defect code dataset and aggregate the defect codes in the defect code dataset to obtain a defect pattern corresponding to the defect code; a second acquisition subunit, used to acquire the target defect code corresponding to the target object from the defect code dataset; and a first determination subunit, used to obtain a target profile based on the target defect code and the defect pattern corresponding to the defect code.

[0128] Optionally, in the information processing apparatus provided in this application embodiment, the determining subunit includes: a first determining module, used to obtain a quantitative evaluation matrix of the target object in the knowledge domain where the defect exists based on the target defect code and the defect pattern corresponding to the defect code, wherein the quantitative evaluation matrix includes at least the target object in the knowledge domain where the defect exists, and the target score corresponding to the knowledge domain; a generating module, used to generate a weakness heatmap based on the quantitative evaluation matrix and the target defect code case; and a second determining module, used to obtain a target profile based on the weakness heatmap and the quantitative evaluation matrix.

[0129] Optionally, in the information processing apparatus provided in the embodiments of this application, the apparatus further includes: a first construction unit, configured to, after matching knowledge points based on the target profile and the code defect and knowledge mapping model to obtain matched knowledge information, construct a mapping rule base between the defect pattern and the knowledge points in the target knowledge base based on the defect pattern and the target knowledge base; a second construction unit, configured to construct a target knowledge graph based on the target knowledge base; and a third construction unit, configured to construct a code defect and knowledge mapping model based on the mapping rule base and the target knowledge graph.

[0130] Optionally, in the information processing apparatus provided in this application embodiment, the matching unit includes: a third acquisition subunit, used to acquire multiple target knowledge domains corresponding to the target object and defect patterns corresponding to each target knowledge domain from the target profile; a second determination subunit, used to determine initial knowledge information from the code defect and knowledge mapping model based on the multiple target knowledge domains and the defect patterns corresponding to each target knowledge domain; a third determination subunit, used to determine the associated coding environment based on the defect patterns corresponding to each target knowledge domain; and a fourth determination subunit, used to obtain matching knowledge information based on the initial knowledge information and the associated coding environment.

[0131] Optionally, in the information processing apparatus provided in this application embodiment, the generation unit includes: a fifth determining subunit, used to determine the dependency relationship between knowledge information based on matching knowledge information and code defect and knowledge mapping model; a first processing subunit, used to obtain the experience level corresponding to the target object based on the attribute parameters of the target object; and a second processing subunit, used to obtain a learning path card based on the dependency relationship and experience level.

[0132] Optionally, in the information processing apparatus provided in the embodiments of this application, the apparatus further includes: a second acquisition unit, used to acquire target code data output by the target object after learning by a probe after the learning path card is pushed to the target object; and an update unit, used to update the target profile based on the target code data to obtain an updated target profile.

[0133] Optionally, in the information processing apparatus provided in the embodiments of this application, the apparatus further includes: a calculation unit, configured to calculate the validity of knowledge in the target knowledge base based on target code data, and obtain a calculation result; an adjustment unit, configured to adjust the weights of knowledge in the target knowledge base based on the calculation result, and obtain updated weight values ​​corresponding to the knowledge in the target knowledge base; and to process the knowledge in the target knowledge base based on the updated weight values, and obtain a processed target knowledge base.

[0134] It should be noted that the first acquisition unit 401, matching unit 402, and generation unit 403 mentioned above correspond to steps S201 to S203 in Embodiment 1. The three units and their corresponding steps implement the same instances and application scenarios, but are not limited to the content disclosed in Embodiment 1. It should be noted that the above modules or units can be hardware or software components stored in memory (e.g., memory 104) and processed by one or more processors (e.g., processors 102a, 102b, ..., 102n). The above units can also be part of a device and run in the computer terminal 10 provided in Embodiment 1.

[0135] Example 3

[0136] Embodiments of this application may provide an electronic device. Figure 5 This is a structural block diagram of an electronic device according to an embodiment of this application. Figure 5 As shown, the electronic device may include: one or more ( Figure 5 (Only one is shown) processor 502, memory 504, memory controller, and peripheral interface, wherein the peripheral interface is connected to the radio frequency module, audio module and display.

[0137] The memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the methods and apparatus in the embodiments of this application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, thereby implementing the above-described methods. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0138] The processor can access information and applications stored in the memory via a transmission device to perform the following steps: obtaining a target profile of the target object, wherein the target profile is constructed based at least on the historical code data output by the target object; matching knowledge points based on the target profile and the code defects and knowledge mapping model to obtain matching knowledge information; generating a learning path card based on the matching knowledge information and pushing the learning path card to the target object, wherein the learning path card includes at least: recommended knowledge resource links and estimated learning time.

[0139] The processor can access information and applications stored in the memory via a transmission device to perform the following steps: obtaining a target profile of the target object includes: acquiring a defect code dataset and aggregating the defect codes in the defect code dataset to obtain the defect patterns corresponding to the defect codes; acquiring the target defect code corresponding to the target object from the defect code dataset; and obtaining the target profile based on the target defect code and the defect pattern corresponding to the defect code.

[0140] The processor can access information and applications stored in the memory via a transmission device to perform the following steps: Based on the target defect code and the corresponding defect pattern, obtain a target profile including: based on the target defect code and the corresponding defect pattern, obtain a quantitative evaluation matrix of the target object in the knowledge domain where the defect exists, wherein the quantitative evaluation matrix includes at least the target object in the knowledge domain where the defect exists, and the target score corresponding to that knowledge domain; generate a weakness heatmap based on the quantitative evaluation matrix and target defect code examples; and obtain the target profile based on the weakness heatmap and the quantitative evaluation matrix.

[0141] The processor can access information and applications stored in the memory via a transmission device to perform the following steps: After matching knowledge points based on the target profile and the code defect and knowledge mapping model to obtain the matched knowledge information, the method further includes: constructing a mapping rule base between the defect pattern and the knowledge points in the target knowledge base based on the defect pattern and the target knowledge base; constructing a target knowledge graph based on the target knowledge base; and constructing a code defect and knowledge mapping model based on the mapping rule base and the target knowledge graph.

[0142] The processor can access information and applications stored in memory via a transmission device to perform the following steps: matching knowledge points based on the target profile and code defect and knowledge mapping model to obtain matching knowledge information, including: obtaining multiple target knowledge domains corresponding to the target object and defect patterns corresponding to each target knowledge domain from the target profile; determining initial knowledge information from the code defect and knowledge mapping model based on the multiple target knowledge domains and defect patterns corresponding to each target knowledge domain; determining the associated coding environment based on the defect patterns corresponding to each target knowledge domain; and obtaining matching knowledge information based on the initial knowledge information and the associated coding environment.

[0143] The processor can access information and applications stored in memory via a transmission device to perform the following steps: generating a learning path card based on matching knowledge information, including: determining the dependencies between knowledge information based on matching knowledge information and a code defect-knowledge mapping model; obtaining the experience level corresponding to the target object based on the attribute parameters of the target object; and obtaining the learning path card based on the dependencies and the experience level.

[0144] The processor can access the information and application stored in the memory via the transmission device to perform the following steps: After pushing the learning path card to the target object, the method further includes: obtaining the target code data output by the target object after learning through a probe; updating the target profile based on the target code data to obtain the updated target profile.

[0145] The processor can invoke information and application programs stored in the memory through a transmission device to execute the following steps: The method further includes: calculating the validity of knowledge in the target knowledge base based on the target code data to obtain the calculation result; adjusting the weights of knowledge in the target knowledge base based on the calculation result to obtain the updated weight values ​​corresponding to the knowledge in the target knowledge base; and processing the knowledge in the target knowledge base based on the updated weight values ​​to obtain the processed target knowledge base.

[0146] Those skilled in the art will understand that Figure 5 The structure shown is for illustrative purposes only. Electronic devices can also be smartphones, tablets, handheld computers, mobile internet devices (MIDs), PADs, and other terminal devices. Figure 5 This does not limit the structure of the aforementioned electronic device. For example, electronic devices may also include components that are more... Figure 5 The more or fewer components shown (such as network interfaces, display devices, etc.), or having the same Figure 5 The different configurations shown.

[0147] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a computer-readable storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0148] Example 4

[0149] Embodiments of this application also provide a computer-readable storage medium. Optionally, in this embodiment, the storage medium can be used to store the program code executed by the information processing method provided in Embodiment 1.

[0150] Optionally, in this embodiment, the storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any mobile terminal in a group of mobile terminals.

[0151] This application also provides a computer program product that, when executed on a data processing device, is suitable for performing steps of an information processing method.

[0152] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0153] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0154] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0155] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0156] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0157] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0158] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. An information processing method, characterized in that, include: Obtain a target profile of the target object, wherein the target profile is constructed based at least on the historical code data output by the target object; Based on the target profile and the code defect and knowledge mapping model, knowledge points are matched to obtain matching knowledge information; Based on the matched knowledge information, a learning path card is generated and pushed to the target object. The learning path card includes at least: recommended knowledge resource links and estimated learning time.

2. The method according to claim 1, characterized in that, Obtaining the target profile of the target object includes: Obtain a defect code dataset and aggregate the defect codes in the defect code dataset to obtain the defect patterns corresponding to the defect codes; Obtain the target defect code corresponding to the target object from the defect code dataset; The target profile is obtained based on the target defect code and the defect pattern corresponding to the defect code.

3. The method according to claim 2, characterized in that, Based on the target defect code and the corresponding defect pattern, the target profile is obtained as follows: Based on the target defect code and the defect pattern corresponding to the defect code, a quantitative evaluation matrix of the target object in the knowledge domain with defects is obtained, wherein the quantitative evaluation matrix includes at least the target object in the knowledge domain with defects, and the target score corresponding to the knowledge domain; Based on the quantitative evaluation matrix and the target defect code examples, a weakness heatmap is generated; The target profile is obtained based on the weakness heatmap and the quantitative evaluation matrix.

4. The method according to claim 2, characterized in that, After matching knowledge points based on the target profile and code defects with the knowledge mapping model to obtain matched knowledge information, the method further includes: Based on the defect patterns and the target knowledge base, a mapping rule base between the defect patterns and the knowledge points in the target knowledge base is constructed; Based on the target knowledge base, construct a target knowledge graph; Based on the mapping rule base and the target knowledge graph, the code defect and knowledge mapping model is constructed.

5. The method according to claim 4, characterized in that, Based on the target profile and the code defect and knowledge mapping model, knowledge point matching is performed to obtain the matched knowledge information, including: Obtain multiple target knowledge domains corresponding to the target object and the defect patterns corresponding to each target knowledge domain from the target profile; Based on the multiple target knowledge domains and the defect patterns corresponding to each target knowledge domain, initial knowledge information is determined from the code defect and knowledge mapping model; Based on the defect patterns corresponding to each target knowledge domain, determine the associated coding environment; The matching knowledge information is obtained based on the initial knowledge information and the associated encoding environment.

6. The method according to claim 1, characterized in that, Based on the matched knowledge information, the learning path card is generated as follows: Based on the matching knowledge information and the code defect and knowledge mapping model, the dependencies between knowledge information are determined; Based on the attribute parameters of the target object, the experience level corresponding to the target object is obtained; The learning path card is obtained based on the dependencies and the experience level.

7. The method according to claim 1, characterized in that, After pushing the learning path card to the target object, the method further includes: The target code data output by the target object after learning is obtained through a probe; The target profile is updated based on the target code data to obtain the updated target profile.

8. The method according to claim 7, characterized in that, The method further includes: The validity of knowledge in the target knowledge base is calculated based on the target code data to obtain the calculation results; Based on the calculation results, the weights of the knowledge in the target knowledge base are adjusted to obtain the updated weight values ​​corresponding to the knowledge in the target knowledge base; Based on the updated weight values, the knowledge in the target knowledge base is processed to obtain the processed target knowledge base.

9. An information processing device, characterized in that, include: The first acquisition unit is used to acquire a target profile of the target object, wherein the target profile is constructed based at least on the historical code data output by the target object; The matching unit is used to match knowledge points based on the target profile and the code defect and knowledge mapping model to obtain matching knowledge information. The generation unit is used to generate a learning path card based on the matching knowledge information and push the learning path card to the target object, wherein the learning path card includes at least: recommended knowledge resource links and estimated learning time.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored executable program, wherein, when the executable program is executed, it controls the device on which the computer-readable storage medium is located to perform the information processing method according to any one of claims 1 to 8.

11. An electronic device, characterized in that, include: Memory, which stores executable programs; A processor for running the program, wherein the program, when running, performs the information processing method according to any one of claims 1 to 8.

Images