Method and apparatus for network request log marking, electronic device, and storage medium

Abstract

The present application relates to the field of computer technology, and discloses a method for labeling network request logs, including: obtaining network request logs to be trained and several factory-installed system APPs; the network request logs to be trained are labeled with APP tags and user identifiers; constructing an APP labeling model by using each factory-installed system APP and the network request logs to be trained; and labeling APP tags by using the APP labeling model. In this way, the constructed APP labeling model can perform labeling in combination with the actual situation, improving the accuracy of the APP tags labeled for the network request logs. The present application also discloses an apparatus, an electronic device, and a storage medium for labeling network request logs.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and for example, to a method and device, an electronic device, and a storage medium for labeling a network request log. Background Art

[0002] With the rise of mobile Internet, mobile big data has emerged. Mobile big data has high commercial value. The use of users' APPs (applications) in mobile big data can objectively reflect users' interests, hobbies, behavioral habits, etc., so that products of interest to users can be further recommended to users based on their interests. However, there is no corresponding APP information in the user's network request logs currently collected, so it is necessary to add corresponding APP tags to the user's network request logs. In related technologies, a small number of network request logs with website domain names and APP tags are usually collected, and then the APP tag with the most associations with the website domain name is directly used as the APP corresponding to the website domain name, forming a correspondence list between the website domain name and the APP, and labeling the network request logs according to the correspondence list. However, directly using the correspondence list

[0003] The APP tag is marked for the network request log, which is not combined with the actual situation.

[0004] The accuracy of the marked APP labels is low. Summary of the invention

[0005] In order to provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. The summary is not an extensive review, nor is it intended to identify key / critical components or delineate the scope of protection of these embodiments, but rather serves as a prelude to the detailed description that follows.

[0006] The embodiments of the present disclosure provide a method and device, an electronic device, and a storage medium for labeling a network request log, so as to improve the accuracy of APP labels annotated for the network request log.

[0007] In some embodiments, the method for labeling network request logs includes: obtaining a network request log to be trained and several system factory APPs; the network request log to be trained is labeled with an APP label and a user identifier; using each of the system factory APPs and the network request log to be trained to build an APP labeling model; and labeling the APP label using the APP labeling model.

[0008] In some embodiments, the apparatus for network request log tagging includes: an acquisition module configured to acquire the network request logs to be trained and several system factory-installed APPs; the network request logs to be trained are labeled with APP tags and user identifiers; a construction module configured to construct an APP tagging model by using each of the system factory-installed APPs and the network request logs to be trained; a tagging module configured to label APP tags by using the APP tagging model.

[0009] In some embodiments, the electronic device includes a processor and a memory storing program instructions, and the processor is configured to execute the above-mentioned method for network request log tagging when running the program instructions.

[0010] In some embodiments, for the storage medium, when the program instructions are running, the above-mentioned method for network request log tagging is executed.

[0011] The method, apparatus, electronic device, and storage medium for network request log tagging provided by the embodiments of the present disclosure can achieve the following technical effects: By acquiring the network request logs to be trained and several system factory-installed APPs, constructing an APP tagging model by using each of the system factory-installed APPs and the network request logs to be trained, and labeling APP tags by using the APP tagging model. In this way, the constructed APP tagging model can perform tagging in combination with the actual situation, improving the accuracy of the APP tags labeled for the network request logs.

[0012] The above general description and the following description are only exemplary and explanatory, and are not used to limit the present application. Description of the Drawings

[0013] One or more embodiments are exemplarily illustrated by corresponding drawings. These exemplary illustrations and the drawings do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings are shown as similar elements. The drawings do not constitute a scale limitation, and among them:

[0014] Figure 1 is a schematic diagram of a method for network request log tagging provided by an embodiment of the present disclosure;

[0015] Figure 2 is a schematic diagram of a second method for network request log tagging provided by an embodiment of the present disclosure;

[0016] Figure 3 is a schematic diagram of a third method for network request log tagging provided by an embodiment of the present disclosure;

[0017] Figure 4 is a schematic diagram of a fourth method for network request log tagging provided by an embodiment of the present disclosure;

[0018] Figure 5 It is a schematic diagram of a device for marking network request logs provided by an embodiment of the present disclosure;

[0019] Figure 6 It is a schematic diagram of an electronic device provided by an embodiment of the present disclosure. Detailed implementation manners

[0020] In order to more comprehensively understand the features and technical content of the embodiments of the present disclosure, the implementation of the embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings. The attached drawings are for reference and illustration only, and are not used to limit the embodiments of the present disclosure. In the following technical description, for the sake of explanation, numerous details are provided to give a thorough understanding of the disclosed embodiments. However, one or more embodiments may still be implemented without these details. In other cases, well-known structures and devices may be shown in a simplified manner to simplify the drawings.

[0021] In the specification and claims of the embodiments of the present disclosure and the above-mentioned drawings, terms such as "first" and "second" are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that such used data may be interchanged under appropriate circumstances so as to implement the embodiments of the present disclosure described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion.

[0022] Unless otherwise specified, the term "plurality" means two or more.

[0023] In the embodiments of the present disclosure, the character " / " indicates that the objects before and after are in an "or" relationship. For example, A / B means: A or B.

[0024] The term "and / or" is an associative relationship describing an object, indicating that three relationships may exist. For example, A and / or B means: A or B, or, A and B these three relationships.

[0025] This application is applied to marking APP tags for network request logs. By obtaining the network request logs to be trained and several system factory APPs. An APP marking model is constructed using each system factory APP and the network request logs to be trained. The APP tags are marked using the APP marking model. In this way, the constructed APP marking model can perform marking in combination with the actual situation, improving the accuracy of the APP tags marked for the network request logs.

[0026] Combined with Figure 1 As shown, the embodiments of the present disclosure provide a method for marking network request logs, including:

[0027] Step S101, the electronic device obtains the network request logs to be trained and several system factory-installed APPs. The network request logs to be trained are labeled with APP tags and user identifiers.

[0028] Step S102, the electronic device constructs an APP tagging model by using each system factory-installed APP and the network request logs to be trained.

[0029] Step S103, the electronic device uses the APP tagging model to label the APP tags.

[0030] By adopting the method for network request log tagging provided by the embodiments of the present disclosure, by obtaining the network request logs to be trained and several system factory-installed APPs, constructing an APP tagging model by using each system factory-installed APP and the network request logs to be trained, and using the APP tagging model to label the APP tags. In this way, the constructed APP tagging model can perform tagging in combination with the actual situation, improving the accuracy of the APP tags labeled for the network request logs.

[0031] The system factory-installed APPs are the APPs that come with the system when it leaves the factory and cannot be uninstalled, such as: calendar, clock, weather, calculator, etc. The network request logs include website domain names. The network request logs to be trained are network request logs labeled with user identifiers and APP tags. In some embodiments, the network request logs labeled with user identifiers, for example:

[0032] 1630399183,p3-webcast.douyinpic.com、

[0033] 1630399186,api5-normal-c-lf.amemv.com、

[0034] 1630399184,mon11-misc-lf.amemv.com、

[0035] 1630399190,p9-webcast.douyinpic.com、1630399204,short.weixin.qq.com, etc.,

[0036] Among them, 1630399183 is the user identifier, and p3-webcast.douyinpic.com is the network request log. The user identifier is the unique code of the device that sends the network request log. The user identifier, for example: the mobile phone IMEI (International Mobile Equipment Identity).

[0037] Optionally, an APP labeling model is constructed using the factory-installed APPs of each system and the training network request logs, including: adjusting the APP labels annotated in the training network request logs according to the factory-installed APPs of each system to obtain the first training data. Splitting the first training data according to the user identifier and a preset sliding window to obtain several second training data. Constructing an APP labeling model using each second training data.

[0038] As shown in Figure 2 An embodiment of the present disclosure provides a method for labeling network request logs, including:

[0039] Step S201, the electronic device obtains the training network request logs and several factory-installed APPs of the system. The training network request logs are annotated with APP labels and user identifiers.

[0040] Step S202, the electronic device adjusts the APP labels annotated in the training network request logs according to the factory-installed APPs of each system to obtain the first training data.

[0041] Step S203, the electronic device splits the first training data according to the user identifier and a preset sliding window to obtain several second training data.

[0042] Step S204, the electronic device constructs an APP labeling model using each second training data.

[0043] Step S205, the electronic device labels the APP labels using the APP labeling model.

[0044] Using the method for labeling network request logs provided by the embodiment of the present disclosure, by obtaining the training network request logs and several factory-installed APPs of the system. Adjusting the APP labels annotated in the training network request logs according to the factory-installed APPs of each system to obtain the first training data. Splitting the first training data according to the user identifier and a preset sliding window to obtain several second training data. Constructing an APP labeling model using each second training data. Labeling the APP labels using the APP labeling model. In this way, the constructed APP labeling model can perform labeling in combination with the actual situation, improving the accuracy of the APP labels annotated for the network request logs.

[0045] Optionally, adjust the APP tags marked in the network request log to be trained according to the factory-installed APPs of each system to obtain the first data to be trained, including: determining the APP tags that are the same as the factory-installed APPs of each system as the tags to be replaced. Use the preset alternative tags to replace the tags to be replaced marked in the network request log to be trained to obtain the first data to be trained. Among them, the factory-installed APPs of the system are the APPs that come with the system when it leaves the factory and cannot be uninstalled, such as: Calendar, Clock, Weather, Calculator, etc. The APP tag is the name of the APP, such as: Douyin, WeChat, etc. The preset alternative tag is a combination of characters and Chinese characters that are not APP names or pure characters, such as: Non-APP, Non-application, OS_APP, etc. The tag to be replaced is the APP tag in the network request log to be trained that is the same as the factory-installed APP of the system. In this way, since the network request logs corresponding to the factory-installed APPs of the system cannot be filtered out when obtaining the network request logs, using the preset alternative tags to replace the tags to be replaced marked in the network request log to be trained does not require accurately identifying which factory-installed APP the network request log belongs to. It can reduce the computational complexity of the APP labeling model and build the APP labeling model more quickly.

[0046] In some embodiments, the factory-installed APPs of the system obtained are "Clock", "Calendar" and "Calculator". Obtain the network request log to be trained, for example: 1630399182,203.119.211.140,Calculator; where Calculator is the APP tag of the network request log 203.119.211.140, and 1630399182 is the user identifier of the network request log 203.119.211.140. The APP tag "Calculator" of the network request log is the same as the factory-installed APP "Calculator" of the system, and "Calculator" is determined as the tag to be replaced. Use the preset alternative tag "OS_APP" to replace the tag to be replaced "Calculator". The first data to be trained obtained is 1630399182,203.119.211.140,OS_APP.

[0047] Optionally, the first data to be trained is segmented according to the user identifier and a preset sliding window to obtain a number of second data to be trained, including: dividing the first data to be trained into a number of alternative training data according to the user identifier; respectively segmenting each alternative training data by using the preset first sliding window to obtain the corresponding second data to be trained for each alternative training data. Among them, after the alternative training data is segmented by using the preset first sliding window, an alternative training data segment corresponding to the alternative training data is obtained. The alternative training data segments arranged in a preset order are determined as the second data to be trained corresponding to the alternative training data. The preset first sliding window, for example: the time window is 30 seconds and the sliding length is 20 seconds. The preset order is the order of segmentation by the first sliding window. In this way, the first data to be trained is classified according to the user identifier to obtain the alternative training data of each user. Then the alternative training data is segmented to obtain the second data to be trained. It can be ensured that a single second data to be trained is the network request log to be trained belonging to the same user. It can be ensured that when constructing the APP labeling model, the APP labeling model can sequentially combine the usage habits of each user for model training, making the constructed APP labeling model more accurate when performing APP labeling.

[0048] Optionally, an APP labeling model is constructed by using each second data to be trained, including: inputting each second data to be trained into a preset CRF (Conditional Random Field) conditional random field model to obtain the APP labeling model. In this way, the CRF model can combine the context usage of the user, so that the trained APP labeling model is more accurate when identifying APP labels.

[0049] Optionally, the APP labeling model is used to label APP labels, including: obtaining the network request log to be labeled; inputting the network request log to be labeled into the APP labeling model to label the APP labels. Among them, the network request log to be labeled is the network request log without an APP label.

[0050] Optionally, inputting the network request log to be labeled into the APP labeling model to label the APP labels includes: segmenting the network request log to be labeled by using the preset second sliding window to obtain each to-be-labeled request log segment; sequentially inputting each to-be-labeled request log segment into the APP labeling model to label the APP labels. Among them, the preset second sliding window is the same as the preset first sliding window. In this way, the network request log to be labeled is segmented so that the length of the network request log to be labeled is the same as the length of the second data to be trained for training. It can be ensured that the APP labeling model is more accurate when labeling APP labels.

[0051] Further, input each to-be-annotated request log segment into the APP tagging model in sequence to tag APP labels, including: input each to-be-annotated request log segment into the APP tagging model in sequence according to the splitting order of the second sliding window to tag APP labels.

[0052] Combined with Figure 3 As shown, the embodiment of the present disclosure provides a method for tagging network request logs, including:

[0053] Step S301, the electronic device obtains the to-be-trained network request logs and several system factory-out APPs. The to-be-trained network request logs are tagged with APP labels and user identifiers.

[0054] Step S302, the electronic device constructs an APP tagging model by using each system factory-out APP and the to-be-trained network request logs.

[0055] Step S303, the electronic device obtains the to-be-annotated network request logs.

[0056] Step S304, the electronic device splits the to-be-annotated network request logs by using a preset second sliding window to obtain each to-be-annotated request log segment.

[0057] Step S305, the electronic device inputs each to-be-annotated request log segment into the APP tagging model in sequence to tag APP labels.

[0058] By adopting the method for tagging network request logs provided by the embodiment of the present disclosure, by obtaining the to-be-trained network request logs and several system factory-out APPs, constructing an APP tagging model by using each system factory-out APP and the to-be-trained network request logs, obtaining the to-be-annotated network request logs, splitting the to-be-annotated network request logs by using a preset second sliding window to obtain each to-be-annotated request log segment, and inputting each to-be-annotated request log segment into the APP tagging model in sequence to tag APP labels. In this way, the constructed APP tagging model can perform tagging in combination with the actual situation, improving the accuracy of the APP labels tagged for the network request logs. At the same time, splitting the to-be-annotated network request logs makes the length of the to-be-annotated network request logs the same as the length of the second to-be-trained data for training, enabling the APP tagging model to be more accurate when tagging APP labels.

[0059] Optionally, after tagging the APP labels by using the APP tagging model, it further includes: presenting the tagged APP labels to the user.

[0060] Optionally, presenting the tagged APP labels to the user includes: pushing the tagged APP labels to a preset client to trigger the client to present the tagged APP labels.

[0061] Optionally, the labeled APP tags are displayed to the user, including: sending the labeled APP tags to a preset display screen, and triggering the display screen to display the labeled APP tags.

[0062] Combined with Figure 4 As shown, an embodiment of the present disclosure provides a method for labeling network request logs, including:

[0063] Step S401, the electronic device obtains the network request logs to be trained and several system factory-installed APPs. The network request logs to be trained are labeled with APP tags and user identifiers.

[0064] Step S402, the electronic device constructs an APP labeling model by using each system factory-installed APP and the network request logs to be trained.

[0065] Step S403, the electronic device labels the APP tags by using the APP labeling model.

[0066] Step S404, the electronic device displays the labeled APP tags to the user.

[0067] By using the method for labeling network request logs provided by the embodiment of the present disclosure, by obtaining the network request logs to be trained and several system factory-installed APPs, constructing an APP labeling model by using each system factory-installed APP and the network request logs to be trained, and labeling the APP tags by using the APP labeling model. In this way, the constructed APP labeling model can perform labeling in combination with the actual situation, improving the accuracy of the APP tags labeled for the network request logs. At the same time, the labeled APP tags are displayed to the user, facilitating the user to view the APP tags, and being used to implement a more accurate user portrait according to the APP tags, further enhancing the user experience, increasing user stickiness, and targeted marketing to users. Thus, data mining is completed in the field of data capabilities technology.

[0068] In some embodiments, the network request logs to be trained labeled with APP tags and user identifiers are obtained in the following manner: installing a dedicated APP tag application on the electronic device with the user's consent. The APP tag application can directly collect the network request logs and which APP the network request logs come from. The APP tag application labels the corresponding APP tags and user identifiers for the network request logs. The user identifier is used to distinguish whether the network request logs come from the electronic devices of the same user. Thus, the network request logs to be trained labeled with APP tags and user identifiers are obtained.

[0069] Combined with Figure 5As shown in the figure, an embodiment of the present disclosure discloses a device for network request log tagging, including: an acquisition module 501, a construction module 502, and a tagging module 503. The acquisition module is configured to acquire the network request logs to be trained and several system factory-installed APPs; the network request logs to be trained are labeled with APP tags and user identifiers; the construction module is configured to construct an APP tagging model by using each system factory-installed APP and the network request logs to be trained; the tagging module is configured to tag the APP tags by using the APP tagging model.

[0070] By using the device for network request log tagging provided by the embodiment of the present disclosure, the acquisition module acquires the network request logs to be trained and several system factory-installed APPs. The construction module constructs an APP tagging model by using each system factory-installed APP and the network request logs to be trained. The tagging module tags the APP tags by using the APP tagging model. In this way, the constructed APP tagging model can perform tagging in combination with the actual situation, improving the accuracy of the APP tags labeled for the network request logs.

[0071] Optionally, the construction module is further configured to construct an APP tagging model by using each system factory-installed APP and the network request logs to be trained in the following manner: adjusting the APP tags labeled for the network request logs to be trained according to each system factory-installed APP to obtain first training data to be trained; splitting the first training data to be trained according to the user identifier and a preset sliding window to obtain several second training data to be trained; constructing an APP tagging model by using each second training data to be trained.

[0072] Optionally, the construction module is further configured to adjust the APP tags labeled for the network request logs to be trained according to each system factory-installed APP in the following manner to obtain first training data to be trained: determining the APP tags identical to each system factory-installed APP as the tags to be replaced; replacing the tags to be replaced labeled for the network request logs to be trained by using preset alternative tags to obtain first training data to be trained.

[0073] Optionally, the construction module is further configured to split the first training data to be trained according to the user identifier and a preset sliding window in the following manner to obtain several second training data to be trained: dividing the first training data to be trained into several alternative training data according to the user identifier; respectively splitting each alternative training data by using a preset first sliding window to obtain each second training data corresponding to each alternative training data.

[0074] Optionally, the construction module is further configured to construct an APP tagging model by using each second training data to be trained in the following manner: inputting each second training data to be trained into a preset CRF conditional random field model to obtain an APP tagging model.

[0075] Optionally, the tagging module HIA is configured to tag APP labels by using the APP tagging model in the following manner: obtain the network request logs to be tagged; input the network request logs to be tagged into the APP tagging model to tag APP labels.

[0076] Optionally, the tagging module is further configured to input the network request logs to be tagged into the APP tagging model to tag APP labels by the following method: segment the network request logs to be tagged by using a preset second sliding window to obtain each request log segment to be tagged; input each request log segment to be tagged into the APP tagging model in sequence to tag APP labels.

[0077] Combined Figure 6 As shown in the figure, an embodiment of the present disclosure provides an electronic device, including a processor 600 and a memory 601. Optionally, the device may further include a communication interface 602 and a bus 603. Among them, the processor 600, the communication interface 602, and the memory 601 can complete mutual communication through the bus 603. The communication interface 602 can be used for information transmission. The processor 600 can call the logic instructions in the memory 601 to execute the method for tagging network request logs in the above embodiment.

[0078] In addition, when the logic instructions in the above-mentioned memory 601 are implemented in the form of a software functional unit and sold or used as an independent product, they can be stored in a computer-readable storage medium.

[0079] The memory 601, as a computer-readable storage medium, can be used to store software programs and computer-executable programs, such as the program instructions / modules corresponding to the method in the embodiment of the present disclosure. The processor 600 executes functional applications and data processing by running the program instructions / modules stored in the memory 601, that is, implements the method for tagging network request logs in the above embodiment.

[0080] The memory 601 may include a program storage area and a data storage area. Among them, the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created according to the use of the electronic device, etc. In addition, the memory 601 may include a high-speed random access memory and may also include a non-volatile memory.

[0081] Optionally, the electronic device is a computer or a server.

[0082] By using the electronic device according to the embodiments of the present disclosure, the network request logs to be trained and several system factory-installed APPs are obtained. An APP tagging model is constructed by using each system factory-installed APP and the network request logs to be trained. The APP tags are labeled by using the APP tagging model. In this way, the constructed APP tagging model can perform tagging in combination with the actual situation, improving the accuracy of the APP tags labeled for the network request logs.

[0083] The embodiments of the present disclosure provide a storage medium storing program instructions, and when the program instructions are running, they execute the method for tagging network request logs described above.

[0084] The embodiments of the present disclosure provide a computer program product, where the computer program product includes a computer program stored on a computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer is made to execute the method for tagging network request logs described above.

[0085] The above computer-readable storage medium may be a transient computer-readable storage medium or a non-transient computer-readable storage medium.

[0086] The technical solution of the embodiments of the present disclosure can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes one or more instructions for causing a computer device (which may be a personal computer, an electronic device, or a network device, etc.) to execute all or part of the steps of the method described in the embodiments of the present disclosure. The foregoing storage medium may be a non-transient storage medium, including: various media capable of storing program codes such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disc, or may also be a transient storage medium.

[0087] The above description and the accompanying drawings fully illustrate the embodiments of the present disclosure, enabling those skilled in the art to practice them. Other embodiments may include structural, logical, electrical, process, and other changes. Embodiments merely represent possible variations. Unless explicitly required, individual components and functions are optional, and the order of operations may vary. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. Moreover, the terms used in this application are only for describing embodiments and do not limit the claims. As used in the description of the embodiments and the claims, unless the context clearly indicates otherwise, the singular forms "a", "an", and "the" are intended to also include the plural forms. Similarly, as used in this application, the term "and / or" refers to any and all possible combinations of one or more of the associated listed items. Additionally, when used in this application, the term "comprise" and its variants "comprises" and / or "comprising" etc. mean the presence of the stated features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or groups of these. Without further limitation, an element defined by the statement "comprising one..." does not exclude the presence of additional identical elements in the process, method, or device comprising the element. Herein, each embodiment may focus on the differences from other embodiments, and the same or similar parts among the embodiments may be referred to each other. For the methods, products, etc. disclosed in the embodiments, if they correspond to the method parts disclosed in the embodiments, the relevant parts may refer to the description of the method parts.

[0088] Those skilled in the art will recognize that the units and algorithm steps of each example described in connection with the embodiments disclosed herein can be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software may depend on the specific application and design constraints of the technical solution. The skilled person may use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of the embodiments of the present disclosure. The skilled person can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0089] In the embodiments disclosed herein, the disclosed methods, products (including but not limited to devices, equipment, etc.) can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units can be merely a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Additionally, the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect coupling or communication connection of devices or units can be in electrical, mechanical, or other forms. The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to implement this embodiment. Additionally, in the embodiments of the present disclosure, the various functional units can be integrated in one processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit.

[0090] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram can represent a module, a program segment, or a part of code that contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions marked in the blocks can occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks can actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, depending on the functions involved. In the descriptions corresponding to the flowcharts and block diagrams in the accompanying drawings, the operations or steps corresponding to different blocks can also occur in a different order than disclosed in the description. Sometimes, there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, depending on the functions involved. Each block in the block diagram and / or flowchart, as well as combinations of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system that performs the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

Claims

1. A method for network request log tagging, characterized in that, including: obtaining a network request log to be trained and a number of factory-installed system APPs; the network request log to be trained is labeled with an APP label and a user identifier; using each of the factory-installed system APPs and the network request log to be trained to construct an APP labeling model; using the APP labeling model to label APP labels; using each of the factory-installed system APPs and the network request log to be trained to construct an APP labeling model, including: adjusting the APP label labeled on the network request log to be trained according to each of the factory-installed system APPs to obtain first training data to be trained; segmenting the first training data to be trained according to the user identifier and a preset sliding window to obtain a number of second training data to be trained; using each of the second training data to be trained to construct an APP labeling model; adjusting the APP label labeled on the network request log to be trained according to each of the factory-installed system APPs to obtain first training data to be trained, including: determining the APP label identical to each factory-installed system APP as a label to be replaced; using a preset alternative label to replace the label to be replaced labeled on the network request log to be trained to obtain first training data to be trained.

2. The method according to claim 1, wherein segmenting the first training data to be trained according to the user identifier and a preset sliding window to obtain a number of second training data to be trained, including: dividing the first training data to be trained into a number of alternative training data according to the user identifier; respectively segmenting each of the alternative training data using a preset first sliding window to obtain each of the second training data to be trained corresponding to each of the alternative training data.

3. The method according to claim 1, characterized in that, using each of the second training data to be trained to construct an APP labeling model, including: inputting each of the second training data to be trained into a preset CRF conditional random field model to obtain an APP labeling model.

4. The method according to claim 1, wherein using the APP labeling model to label APP labels, including: obtaining a network request log to be labeled; inputting the network request log to be labeled into the APP labeling model to label APP labels.

5. The method according to claim 4, characterized in that inputting the network request log to be labeled into the APP labeling model to label APP labels, including: segmenting the network request log to be labeled using a preset second sliding window to obtain each fragment of the network request log to be labeled; sequentially inputting each fragment of the network request log to be labeled into the APP labeling model to label APP labels.

6. A device for network request log marking, characterized in that, including: an obtaining module configured to obtain a network request log to be trained and a number of factory-installed system APPs; the network request log to be trained is labeled with an APP label and a user identifier; a constructing module configured to use each of the factory-installed system APPs and the network request log to be trained to construct an APP labeling model; a labeling module configured to use the APP labeling model to label APP labels; the constructing module is further configured to use each factory-installed system APP and the network request log to be trained to construct an APP labeling model in the following manner: adjusting the APP label labeled on the network request log to be trained according to each factory-installed system APP to obtain first training data to be trained; segmenting the first training data to be trained according to the user identifier and a preset sliding window to obtain a number of second training data to be trained; using each of the second training data to be trained to construct an APP labeling model; The building block is also configured to obtain first training data by adjusting the APP labels marked in the network request logs to be trained according to the factory-installed APPs of each system in the following manner: determining the APP labels identical to the factory-installed APPs of each system as the labels to be replaced; using the preset alternative labels to replace the labels to be replaced marked in the network request logs to be trained, so as to obtain first training data.

7. An electronic device, comprising a processor and a memory storing program instructions, characterized in that, The processor is configured to execute the method for network request log marking according to any one of claims 1 to 5 when running the program instructions.

8. A storage medium stores program instructions, characterized in that, When running, the program instructions execute the method for network request log marking according to any one of claims 1 to 5.

Images