Web-based App Business Big Data Processing Methods and Systems

Abstract

This application provides a web-based APP business big data processing method and system that extracts requirement knowledge from APP function operation logs using multi-angle, staged information sets. It then uses APP operation and maintenance feature vectors corresponding to different staged information sets as the basis for APP function operation log retrieval, expanding the focus dimensions of APP operation and maintenance feature vectors during retrieval. This improves the targeted processing of different usage scenarios in APP function operation logs, thereby enhancing the accuracy and efficiency of APP function operation log retrieval. Based on this, it can quickly and accurately obtain APP function code development logs, generating development optimization plans for the APP to be updated. This allows for efficient APP development and maintenance at the requirement knowledge level through development optimization plans.

Description

Technical Field

[0001] This application relates to the field of APP technology, and in particular to a web-based APP business big data processing method and system. Background Technology

[0002] For app development and maintenance in web scenarios, based on past experience, the code written for platform-specific integration accounts for approximately 20% of the total code. However, this approach isolates 100% of the code for separate secondary development and maintenance. This leads to significant duplication of development work across multiple platforms, increasing development costs and maintenance difficulty. Traditional technologies place all platform integration code together and rely on UserAgent-based judgments, easily resulting in code redundancy. Therefore, improving app development efficiency is a current technical challenge. Summary of the Invention

[0003] To address the technical problems existing in related technologies, this application provides a Web-based APP business big data processing method and system.

[0004] In a first aspect, embodiments of this application provide a Web-based APP business big data processing method, applied to an APP function development processing system. The method includes at least: determining a requirement knowledge relationship network based on the target APP function operation logs, and performing APP function operation log retrieval in conjunction with the Web platform characteristic vector corresponding to the requirement knowledge relationship network to obtain operation log retrieval information; wherein the operation log retrieval information includes the APP function code development logs of the target APP function operation logs; and generating a development optimization scheme for the APP to be updated in conjunction with the APP function code development logs.

[0005] For some independently implementable technical solutions, the step of determining the requirement knowledge relationship network based on the target APP's functional operation logs and retrieving the APP's functional operation logs in conjunction with the Web platform characteristic vector corresponding to the requirement knowledge relationship network to obtain operation log retrieval information; wherein, the operation log retrieval information includes the APP functional code development logs of the target APP's functional operation logs, including: extracting requirement knowledge from the target APP's functional operation logs to obtain a first requirement knowledge relationship network of the target APP's functional operation logs, the first requirement knowledge relationship network reflecting the APP operation and maintenance feature vector of the first-stage information set in the target APP's functional operation logs; and performing local interest prediction on the target APP's functional operation logs based on the first requirement knowledge relationship network to obtain the local interest corresponding to the target APP's functional operation logs. The prediction results show that the staged information set of the local prediction results is a second staged information set, and the second staged information set is different from the first staged information set. Demand knowledge is extracted from the local prediction results to obtain a second demand knowledge relationship network. This second demand knowledge relationship network reflects the APP operation and maintenance feature vector of the second staged information set in the local prediction results. A first Web platform characteristic vector is obtained based on the first demand knowledge relationship network, and a second Web platform characteristic vector is obtained based on the second demand knowledge relationship network. APP function operation logs are retrieved based on the first and second Web platform characteristic vectors to obtain operation log retrieval information. The operation log retrieval information includes the APP function code development log of the target APP function operation log.

[0006] For some independently implementable technical solutions, the step of performing local interest prediction on the target APP function operation log based on the first demand knowledge relationship network to obtain the local prediction result corresponding to the target APP function operation log includes: obtaining a first APP session item set corresponding to the target APP function operation log based on the first demand knowledge relationship network, wherein the staged information set reflected by the first APP session item set is the first staged information set; obtaining a second APP session item set based on the first APP session item set, wherein the staged information set reflected by the second APP session item set is the second staged information set; and obtaining the local prediction result based on the second APP session item set and the target APP function operation log.

[0007] For some independently implementable technical solutions, obtaining the first APP session item set corresponding to the target APP function operation log based on the first requirement knowledge relationship network includes:

[0008] A basic APP session item set is obtained based on the first requirement knowledge relationship network of each functional state, wherein the feature value of the basic APP session item set is a label with association; based on the overall feature value of the basic APP session item set, each feature value in the basic APP session item set is downsampled to obtain the first APP session item set; obtaining the second APP session item set based on the first APP session item set includes: adjusting the feature value of the first APP session item set to obtain the second APP session item set.

[0009] For some independently implementable technical solutions, obtaining the local prediction result based on the second APP session item set and the target APP function operation log includes: transforming the feature values ​​in the second APP session item set from the demand knowledge matrix to the APP function operation log list to obtain the APP session item set corresponding to the APP function operation log; and using the APP session item set corresponding to the APP function operation log to process the session items of the target APP function operation log to obtain the local prediction result.

[0010] For some independently implementable technical solutions, the step of retrieving APP function operation logs based on the first Web platform feature vector and the second Web platform feature vector to obtain operation log retrieval information includes: combining the first Web platform feature vector and the second Web platform feature vector to obtain a target optimized Web platform feature vector; determining the comparison result between the target optimized Web platform feature vector and the corresponding optimized Web platform feature vector in the APP function operation logs of the remote development system platform; and determining the operation log retrieval information based on the comparison result.

[0011] For some independently implementable technical solutions, after retrieving the APP function operation log based on the first Web platform feature vector and the second Web platform feature vector to obtain the operation log retrieval information, the method further includes: in response to the absence of an APP function operation log consistent with the target APP function operation log in the remote development system platform, associating and uploading the target APP function operation log and the target optimized Web platform feature vector to the remote development system platform.

[0012] For some independently implementable technical solutions, the first demand knowledge relationship network and the second demand knowledge relationship network are extracted by the demand extraction unit of the demand knowledge extraction algorithm, and the first Web platform characteristic vector and the second Web platform characteristic vector are obtained by the classification unit of the demand knowledge extraction algorithm.

[0013] For some independently implementable technical solutions, the method further includes: extracting requirement knowledge from the sample APP function operation log group using the requirement knowledge extraction algorithm to obtain a sample requirement knowledge relationship network group corresponding to the sample APP function operation log group, wherein the sample APP function operation log group contains at least two sample APP function operation logs, and the sample requirement knowledge relationship network group contains sample requirement knowledge relationship networks corresponding to each of the sample APP function operation logs; performing local interest prediction on the sample APP function operation log group based on the sample requirement knowledge relationship network group to obtain a sample local prediction result group corresponding to the sample APP function operation log group, wherein the sample local prediction result group contains sample local prediction results corresponding to each of the sample APP function operation logs; and extracting requirement knowledge from the sample APP function operation log group using the requirement knowledge extraction algorithm to obtain a sample requirement knowledge relationship network group corresponding to the sample APP function operation log group. For example, demand knowledge is extracted from the local prediction result group to obtain the prediction demand knowledge relationship network group corresponding to the local prediction result group. The prediction demand knowledge relationship network group contains the sample prediction demand knowledge relationship network corresponding to each of the local prediction results. The demand knowledge extraction algorithm is used to obtain the sample Web platform feature vector group corresponding to the sample demand knowledge relationship network group and the prediction Web platform feature vector group corresponding to the prediction demand knowledge relationship network group. The sample Web platform feature vector group contains the sample Web platform feature vectors of each of the sample APP function operation logs, and the prediction Web platform feature vector group contains the prediction Web platform feature vectors of each of the local prediction results. The demand knowledge extraction algorithm is then debugged based on the sample Web platform feature vector group and the prediction Web platform feature vector group.

[0014] Secondly, this application also provides an APP function development and processing system, including a processor and a memory; the processor and the memory are communicatively connected, and the processor is used to read a computer program from the memory and execute it to implement the method described above.

[0015] In this embodiment of the application, when retrieving the function operation log of a target APP, the requirement knowledge is extracted from the function operation log of the target APP, and local interest prediction is performed on the function operation log of the target APP based on the extracted requirement knowledge relationship network. This yields local prediction results that carry different stages of information sets from the function operation log of the target APP. Then, the function operation log is retrieved based on the Web platform characteristic vectors corresponding to the function operation log of the target APP and the local prediction results, and the operation log retrieval information is obtained.

[0016] Applied to the embodiments of this application, this method achieves the extraction of requirement knowledge from APP function operation logs with multi-angle, staged information sets. It then uses APP operation and maintenance feature vectors corresponding to different staged information sets as the basis for APP function operation log retrieval, expanding the focus dimensions of APP operation and maintenance feature vectors during retrieval. This improves the targeted processing of different usage scenarios in the APP function operation logs, thereby enhancing the accuracy and efficiency of APP function operation log retrieval. Based on this, it can quickly and accurately obtain APP function code development logs, generating development optimization plans for the APP to be updated. This allows for efficient APP development and maintenance at the requirement knowledge level through development optimization plans. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the specification, serve to explain the principles of this application.

[0018] Figure 1 This is a schematic diagram of the hardware structure of an APP function development and processing system provided in an embodiment of this application.

[0019] Figure 2 This is a flowchart illustrating a web-based APP business big data processing method provided in an embodiment of this application.

[0020] Figure 3 This is a schematic diagram of the communication architecture of an application environment for a web-based APP business big data processing method provided in this application embodiment. Detailed Implementation

[0021] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0022] It should be noted that the terms "first," "second," etc., in the specification, claims, and drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0023] The method embodiments provided in this application can be executed in an APP function development and processing system, a computer device, or a similar computing device. Taking running on an APP function development and processing system as an example, Figure 1This is a hardware structure block diagram of an APP function development and processing system that implements a Web-based APP business big data processing method according to an embodiment of this application. For example... Figure 1 As shown, the APP function development processing system 10 may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data are also shown. Optionally, the aforementioned APP function development processing system may further include a transmission device 106 for communication functions. 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 APP function development processing system. For example, the APP function development processing system 10 may also include... Figure 1 The more or fewer components shown, or having the same Figure 1 The different debugging methods shown.

[0024] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to a web-based APP business big data processing method in this embodiment. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thus implementing the above-described method. The memory 104 may include high-speed random access memory and 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 APP function development and processing system 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.

[0025] 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 APP function development processing system 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.

[0026] Based on this, please refer to Figure 2 , Figure 2This is a flowchart illustrating a Web-based APP business big data processing method provided by an embodiment of the present invention. The method is applied to an APP function development and processing system, and further, the method may include at least the technical solutions recorded in steps 10 and 20.

[0027] Step 10: Determine the requirement knowledge relationship network based on the target APP function operation log, and perform APP function operation log retrieval in combination with the Web platform characteristic vector corresponding to the requirement knowledge relationship network to obtain operation log retrieval information.

[0028] The demand knowledge relationship network can be understood as the demand characteristics generated when users use the APP. The Web platform characteristic vector can be understood as a feature vector. The operation log retrieval information includes the APP function code development log of the target APP's function operation log. The APP function code development log can be understood as relevant records that are related to the target APP's function operation log.

[0029] In one illustrative embodiment, step 10 above records the determination of the requirement knowledge relationship network based on the target APP function operation log, and combines the Web platform characteristic vector corresponding to the requirement knowledge relationship network to perform APP function operation log retrieval to obtain operation log retrieval information; wherein, the operation log retrieval information includes the APP function code development log of the target APP function operation log, which may include, for example, the content recorded in steps 101-105 below.

[0030] Step 101: Extract the requirement knowledge from the target APP function operation log to obtain the first requirement knowledge relationship network of the target APP function operation log. The first requirement knowledge relationship network reflects the APP operation and maintenance feature vector of the first stage information set in the target APP function operation log.

[0031] Step 102: Perform local interest prediction on the target APP function operation log based on the first demand knowledge relationship network to obtain the local prediction result corresponding to the target APP function operation log. The staged information set of the local prediction result is the second staged information set, and the second staged information set is different from the first staged information set.

[0032] In one illustrative embodiment, the local interest prediction of the target APP function operation log based on the first demand knowledge relationship network recorded in step 102 above, to obtain the local prediction result corresponding to the target APP function operation log, may include, for example, the content recorded in steps 1021-1023 below.

[0033] Step 1021: Obtain the first APP session item set corresponding to the target APP function operation log based on the first requirement knowledge relationship network. The first APP session item set reflects the staged information set as the first staged information set.

[0034] For one illustrative embodiment, the first APP session item set corresponding to the target APP function operation log recorded in step 1021 above, based on the first requirement knowledge relationship network, may include the following: obtaining a basic APP session item set based on the first requirement knowledge relationship network for each functional state, wherein the feature value in the basic APP session item set is a related label; downsampling processing is performed on each feature value in the basic APP session item set based on the overall feature value of the basic APP session item set to obtain the first APP session item set; obtaining a second APP session item set based on the first APP session item set includes: adjusting the feature values ​​in the first APP session item set to obtain the second APP session item set.

[0035] In this way, downsampling of each feature value in the obtained basic APP session event set can improve the accuracy and quality of the first APP session event set.

[0036] Step 1022: Obtain a second APP session item set based on the first APP session item set. The second APP session item set reflects the staged information set as the second staged information set.

[0037] Step 1023: Obtain the local prediction result based on the second APP session item set and the target APP function operation log.

[0038] In one illustrative embodiment, the partial prediction result recorded in step 1023 above, which is based on the second APP session item set and the target APP function operation log, may include the following: transforming the feature values ​​in the second APP session item set from the demand knowledge matrix to the APP function operation log list to obtain the APP session item set corresponding to the APP function operation log; and performing session item processing on the target APP function operation log using the APP session item set corresponding to the APP function operation log to obtain the partial prediction result.

[0039] In this way, by processing a series of session items in the target APP's function operation log through the APP session item set corresponding to the APP function operation log, a relatively complete local prediction result can be obtained, while avoiding errors in obtaining the local prediction result.

[0040] When implementing the content recorded in steps 1021-1023, the reliability and accuracy of obtaining the local prediction results based on the second APP session item set and the target APP function operation log can be improved.

[0041] Step 103: Extract demand knowledge from the local prediction results to obtain the second demand knowledge relationship network of the local prediction results. The second demand knowledge relationship network reflects the APP operation and maintenance feature vector of the second stage information set in the local prediction results.

[0042] Step 104: Obtain the first Web platform characteristic vector based on the first requirement knowledge relationship network, and obtain the second Web platform characteristic vector based on the second requirement knowledge relationship network.

[0043] Step 105: Perform APP function operation log retrieval based on the first Web platform feature vector and the second Web platform feature vector to obtain operation log retrieval information, which includes the APP function code development log of the target APP function operation log.

[0044] In this embodiment of the application, the first demand knowledge relationship network and the second demand knowledge relationship network are extracted by the demand extraction unit of the demand knowledge extraction algorithm, and the first Web platform feature vector and the second Web platform feature vector are obtained by the classification unit of the demand knowledge extraction algorithm.

[0045] In one illustrative embodiment, step 105, which records the APP function operation log retrieval based on the first Web platform feature vector and the second Web platform feature vector to obtain operation log retrieval information, may exemplary include the following: combining (concatenating, fusing, etc.) the first Web platform feature vector and the second Web platform feature vector to obtain a target optimized Web platform feature vector; determining the comparison result between the target optimized Web platform feature vector and the corresponding optimized Web platform feature vector in the APP function operation log of the remote development system platform; and determining the operation log retrieval information based on the comparison result. This reduces the possibility of errors in the operation log retrieval information.

[0046] In one exemplary embodiment, after step 105 records the APP function operation log retrieval based on the first Web platform feature vector and the second Web platform feature vector to obtain operation log retrieval information, the method may further include the following technical solution: In response to the absence of an APP function operation log consistent with the target APP function operation log in the remote development system platform, the target APP function operation log and the target optimized Web platform feature vector are associated and uploaded to the remote development system platform. This enriches the APP function operation log in the remote development system platform and facilitates subsequent querying of the APP function operation log.

[0047] In implementing the content recorded in steps 101-105, the requirements knowledge of the APP function operation logs from multiple perspectives and phased information sets was extracted. The APP function operation logs were retrieved based on the APP operation and maintenance feature vectors corresponding to different phased information sets. This expanded the focus dimensions of the APP operation and maintenance feature vectors during APP function operation log retrieval, improved the targeted processing of different usage scenarios in the APP function operation logs, and thus improved the accuracy and efficiency of APP function operation log retrieval.

[0048] Step 20: Generate a development optimization plan for the APP to be updated by combining the APP function code development log.

[0049] In one illustrative embodiment, based on the above, the method may also include the technical solutions recorded in steps 30-70.

[0050] Step 30: Extract the requirement knowledge from the sample APP function operation log group using the requirement knowledge extraction algorithm to obtain the sample requirement knowledge relationship network group corresponding to the sample APP function operation log group. The sample APP function operation log group contains no less than two sample APP function operation logs, and the sample requirement knowledge relationship network group contains the sample requirement knowledge relationship network corresponding to each sample APP function operation log.

[0051] Step 40: Based on the sample requirement knowledge relationship network group (sample requirement knowledge relationship network group), perform local interest prediction on the sample APP function operation log group to obtain the sample local prediction result group corresponding to the sample APP function operation log group. The sample local prediction result group contains the sample local prediction results corresponding to each sample APP function operation log.

[0052] Step 50: Extract the demand knowledge from the sample local prediction result group using the demand knowledge extraction algorithm to obtain the prediction demand knowledge relationship network group corresponding to the sample local prediction result group. The prediction demand knowledge relationship network group contains the sample prediction demand knowledge relationship network corresponding to each sample local prediction result.

[0053] Step 60: Obtain the sample Web platform feature vector group corresponding to the sample requirement knowledge relationship network group and the predicted Web platform feature vector group corresponding to the predicted requirement knowledge relationship network group through the requirement knowledge extraction algorithm. The sample Web platform feature vector group contains the sample Web platform feature vectors of the function operation logs of each sample APP, and the predicted Web platform feature vector group contains the predicted Web platform feature vectors of the local prediction results of each sample.

[0054] Step 70: Debug the requirement knowledge extraction algorithm based on the sample Web platform feature vector group and the predicted Web platform feature vector group.

[0055] When implementing the technical solutions recorded in steps 30-70, the requirement knowledge extraction algorithm is iteratively debugged using the sample Web platform feature vector group and the predicted Web platform feature vector group. This can improve the stability and anti-interference ability of the requirement knowledge extraction algorithm, thereby ensuring the performance of the algorithm.

[0056] In summary, implementing the technical solutions recorded in steps 10 and 20 enables the extraction of requirement knowledge from the APP function operation logs using multi-dimensional, phased information sets. It also allows for APP function operation log retrieval based on the APP operation and maintenance feature vectors corresponding to different phased information sets. This expands the focus dimensions of the APP operation and maintenance feature vectors during retrieval, improving the targeted processing of different usage scenarios within the APP function operation logs. Consequently, it enhances the accuracy and efficiency of APP function operation log retrieval. Furthermore, it enables the rapid and accurate acquisition of APP function code development logs, allowing for the generation of development optimization plans for the APP to be updated. This allows for efficient APP development and maintenance at the requirement knowledge level through development optimization plans.

[0057] like Figure 3 As shown, based on the same or similar inventive concepts described above, this application also provides an architecture diagram of an application environment 30 for a Web-based APP business big data processing method, including an APP function development and processing system 10 and a remote development system platform 20 that communicate with each other. The APP function development and processing system 10 and the remote development system platform 20 implement or partially implement the technical solutions described in the above method embodiments during runtime.

[0058] Furthermore, a readable storage medium is provided on which a program is stored, which, when executed by a processor, implements the above-described method.

[0059] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can also be implemented in other ways. The apparatus and method embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0060] In addition, the functional modules in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0061] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they 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 a 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, a media service server 10, or a 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 USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks. It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to include non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. In the absence of further restrictions, an element defined by the phrase "comprising a..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0062] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A web-based APP business big data processing method, characterized in that, Applied to an APP function development and processing system, the method includes at least the following: Based on the target APP's function operation logs, a requirement knowledge relationship network is determined, and the APP's function operation logs are retrieved by combining the Web platform characteristic vectors corresponding to the requirement knowledge relationship network, resulting in operation log retrieval information; wherein, the operation log retrieval information includes the APP function code development logs of the target APP's function operation logs; Based on the APP's functional code development logs, a development optimization plan for the APP to be updated is generated; The process involves determining the requirement knowledge network based on the target APP's function operation logs, and then performing APP function operation log retrieval in conjunction with the Web platform characteristic vector corresponding to the requirement knowledge network to obtain operation log retrieval information. This operation log retrieval information includes the APP function code development logs of the target APP's function operation logs, including: The target APP's function operation log is subjected to requirement knowledge extraction to obtain the first requirement knowledge relationship network of the target APP's function operation log. The first requirement knowledge relationship network reflects the APP operation and maintenance feature vector of the first stage information set in the target APP's function operation log. Based on the first demand knowledge relationship network, local interest prediction is performed on the target APP function operation log to obtain the local prediction result corresponding to the target APP function operation log. The staged information set of the local prediction result is the second staged information set, and the second staged information set is different from the first staged information set. Demand knowledge is extracted from the local prediction results to obtain a second demand knowledge relationship network of the local prediction results. The second demand knowledge relationship network reflects the APP operation and maintenance feature vector of the second stage information set in the local prediction results. A first Web platform feature vector is obtained based on the first requirement knowledge relationship network, and a second Web platform feature vector is obtained based on the second requirement knowledge relationship network; Based on the first Web platform feature vector and the second Web platform feature vector, the APP function operation log is retrieved to obtain operation log retrieval information, which includes the APP function code development log of the target APP function operation log. The first demand knowledge relationship network and the second demand knowledge relationship network are extracted by the demand extraction unit of the demand knowledge extraction algorithm, and the first Web platform characteristic vector and the second Web platform characteristic vector are obtained by the classification unit of the demand knowledge extraction algorithm. The method further includes: The requirement knowledge extraction algorithm is used to extract requirement knowledge from the sample APP function operation log group to obtain the sample requirement knowledge relationship network group corresponding to the sample APP function operation log group. The sample APP function operation log group contains no less than two sample APP function operation logs, and the sample requirement knowledge relationship network group contains the sample requirement knowledge relationship network corresponding to each sample APP function operation log. Based on the sample requirement knowledge relationship network group, local interest prediction is performed on the sample APP function operation log group to obtain the sample local prediction result group corresponding to the sample APP function operation log group. The sample local prediction result group contains the sample local prediction results corresponding to each sample APP function operation log. The requirement knowledge extraction algorithm is used to extract the requirement knowledge from the sample local prediction result group to obtain the prediction requirement knowledge relationship network group corresponding to the sample local prediction result group. The prediction requirement knowledge relationship network group contains the sample prediction requirement knowledge relationship network corresponding to each sample local prediction result. The requirement knowledge extraction algorithm obtains the sample Web platform feature vector group corresponding to the sample requirement knowledge relationship network group and the predicted Web platform feature vector group corresponding to the predicted requirement knowledge relationship network group. The sample Web platform feature vector group contains the sample Web platform feature vectors of the function operation logs of each sample APP and the predicted Web platform feature vector group contains the predicted Web platform feature vectors of the local prediction results of each sample. Based on the sample Web platform feature vector group and the predicted Web platform feature vector group, the requirement knowledge extraction algorithm is debugged.

2. The method as described in claim 1, characterized in that, The step of performing local interest prediction on the target APP function operation log based on the first demand knowledge relationship network to obtain the local prediction result corresponding to the target APP function operation log includes: Based on the first requirement knowledge relationship network, obtain the first APP session item set corresponding to the target APP function operation log, and the first APP session item set reflects the staged information set as the first staged information set; A second APP session item set is obtained based on the first APP session item set, and the staged information set reflected by the second APP session item set is the second staged information set; The partial prediction result is obtained based on the second APP session item set and the target APP function operation log.

3. The method as described in claim 2, characterized in that, The step of obtaining the first APP session item set corresponding to the target APP function operation log based on the first requirement knowledge relationship network includes: obtaining a basic APP session item set based on the first requirement knowledge relationship network of each function state, wherein the feature value of the basic APP session item set is a related label; and downsampling each feature value of the basic APP session item set based on the overall feature value of the basic APP session item set to obtain the first APP session item set. The step of obtaining the second APP session item set based on the first APP session item set includes: adjusting the feature values ​​in the first APP session item set to obtain the second APP session item set.

4. The method as described in claim 2, characterized in that, The step of obtaining the local prediction result based on the second APP session item set and the target APP function operation log includes: Transform the feature values ​​in the second APP session item set from the demand knowledge matrix to the APP function operation log list to obtain the APP session item set corresponding to the APP function operation log; The target APP's function operation log is processed using the APP session item set corresponding to the APP function operation log to obtain the local prediction result.

5. The method as described in claim 1, characterized in that, The step of retrieving APP function operation logs based on the first Web platform characteristic vector and the second Web platform characteristic vector to obtain operation log retrieval information includes: The first Web platform feature vector and the second Web platform feature vector are combined to obtain the target optimized Web platform feature vector; Determine the comparison result between the target optimized Web platform feature vector and the corresponding optimized Web platform feature vector in the APP function operation log of the remote development system platform; determine the operation log retrieval information based on the comparison result.

6. The method as described in claim 5, characterized in that, After obtaining the operation log retrieval information by retrieving the APP function operation log based on the first Web platform characteristic vector and the second Web platform characteristic vector, the method further includes: If no APP function operation log is found in the remote development system platform that matches the target APP function operation log, the target APP function operation log and the target optimized Web platform feature vector are associated and uploaded to the remote development system platform.

7. An APP function development and processing system, characterized in that, It includes a processor and a memory; the processor and the memory are communicatively connected, and the processor is configured to read a computer program from the memory and execute it to implement the method described in any one of claims 1-6.

Images