CN113486241A - Service preference analysis method and device - Google Patents
Service preference analysis method and device Download PDFInfo
- Publication number
- CN113486241A CN113486241A CN202110774755.7A CN202110774755A CN113486241A CN 113486241 A CN113486241 A CN 113486241A CN 202110774755 A CN202110774755 A CN 202110774755A CN 113486241 A CN113486241 A CN 113486241A
- Authority
- CN
- China
- Prior art keywords
- stage
- user
- application software
- access
- service
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 121
- 238000000034 method Methods 0.000 claims abstract description 67
- 238000005457 optimization Methods 0.000 claims description 13
- 238000012163 sequencing technique Methods 0.000 claims description 10
- 238000010276 construction Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 description 32
- 238000012549 training Methods 0.000 description 16
- 238000012790 confirmation Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- RWSOTUBLDIXVET-UHFFFAOYSA-N Dihydrogen sulfide Chemical compound S RWSOTUBLDIXVET-UHFFFAOYSA-N 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
Abstract
The invention provides a service preference analysis method and a device, wherein the method comprises the following steps: when detecting that the user effectively accesses the application software, generating an access path for the user to access the application software; extracting a first stage, a second stage and a third stage in the access path, and setting the second stage as a key stage; acquiring an access log uploaded by application software; determining each target service module accessed by the user in the key stage based on the application log, and generating a module execution path corresponding to each target service module; combining the execution paths of the first stage, the third stage and each module into a complete access path for the user to access the application software; and inputting the complete access path into the pre-judging model to obtain a service preference value corresponding to each service model in the application software output by the pre-judging model. By applying the method, the preference degree of the user to each service can be determined according to the analysis of the access path of the user to access the application software, so that the related service can be accurately recommended to the user.
Description
Technical Field
The present invention relates to the technical field of data analysis, and in particular, to a method and an apparatus for analyzing service preference.
Background
With the development of banking business, banks provide functions of handling business online and push out application software of handling business online in order to provide more convenient services for users. With the increase of online users, banks frequently push out new business functions to meet the business requirements of users in order to meet the diversity of users.
In order to improve the use experience of the user, the application software of the bank collects the service data of the user and recommends related services for the user. In most cases, the analysis of the user's business preference is based only on the user's historical successful transaction data, thereby inferring the user's business preference. However, in the prior art, only through historical successful transaction data analysis, the idea of the user for other unsuccessful transaction services is not considered, which causes the service recommended to the user by the application software to be relatively limited, and the user is easy to miss the activities of some services.
Disclosure of Invention
In view of the above, the present invention provides a service preference analysis method, by which a preference degree of a user for each service is determined by comprehensively analyzing an access path of a user accessing application software, so as to accurately recommend a relevant service to the user.
The invention also provides a service preference analysis device which is used for ensuring the realization and the application of the method in practice.
A service preference analysis method comprises the following steps:
when detecting that a user effectively accesses application software, generating an access path for the user to access the application software, wherein the application software comprises a plurality of business modules, and each business module corresponds to each business of a bank one by one;
extracting a first stage, a second stage and a third stage in the access path, and setting the second stage as a key stage, wherein the first stage is a stage before the user enters a home page of a service module of the application software for the first time, the second stage is a stage when the user circulates in at least one service module of the application software, and the third stage is a stage when the user leaves the last accessed service module and exits the application software;
acquiring an access log uploaded by the application software;
determining each service module visited by the user in the key stage as a target service module based on the application log, and generating a module execution path corresponding to each target service module;
combining the first stage, the third stage and the execution paths of the modules into a complete access path for the user to access the application software;
and inputting the complete access path into a preset pre-judgment model to obtain a service preference value corresponding to each service model in the application software output by the pre-judgment model.
The above method, optionally, further includes:
when the user is detected to exit the application software, acquiring access information uploaded by the application software;
analyzing the access information to obtain each timestamp contained in the access information;
detecting whether each timestamp contains a timestamp carrying a first identification bit, wherein the timestamp carrying the first identification bit is the operation time for executing the service operation when the user executes the service operation corresponding to any service module in the application software;
if each timestamp contains a timestamp carrying a first identification bit, determining that the user effectively accesses the application software;
and if the timestamps do not contain the timestamp carrying the first identification bit, determining that the user has invalid access to the application software.
Optionally, the generating an access path for the user to access the application software includes:
sequencing the timestamps according to a time sequence;
dividing each sequenced timestamp into a first access time interval, a second access time interval and a third access time interval according to the time sequence, wherein the second access time interval comprises all timestamps carrying first identification bits;
setting the stage of the user accessing the application software in the first access time interval as a first stage, the stage of the user accessing the application software in the second access time interval as a second stage, and the stage of the user accessing the application software in the third access time interval as a third stage;
and constructing an access path of the user for accessing the application software based on the first stage, the second stage and the third stage.
Optionally, in the method, the determining, based on the access log, that each service module that the user has accessed in the key phase is a target service module, and generating a module execution path corresponding to each target service module includes:
determining a service module associated with each timestamp carrying a first identification bit in the access log;
determining the service module associated with each timestamp carrying the first identification bit as a target service module visited by the user in the key stage;
reading each execution node corresponding to each target service module in the access log;
and generating a module execution path corresponding to each target service module based on each execution node corresponding to each target service module.
The above method, optionally, further includes:
acquiring a preset service analysis model;
inputting the complete access path into the service analysis model, and triggering the service analysis model to perform service operation analysis on each target service module accessed in the complete access path to obtain a service analysis result; the service operation analysis comprises funnel analysis, error reporting analysis, dwell time analysis and browsing frequency analysis;
and generating service index information corresponding to each target service module based on the service analysis result, and sending the service index information to an optimization server, so that the optimization server optimizes the service corresponding to each target service module based on the service index information.
A service preference analysis apparatus comprising:
the system comprises a first generation unit, a second generation unit and a third generation unit, wherein the first generation unit is used for generating an access path for a user to access application software when the user is detected to effectively access the application software, the application software comprises a plurality of business modules, and each business module corresponds to each business of a bank one by one;
an extracting unit, configured to extract a first stage, a second stage, and a third stage in the access path, and set the second stage as a key stage, where the first stage is a stage before the user enters a home page of a service module of the application software for the first time, the second stage is a stage in which the user circulates in at least one service module of the application software, and the third stage is a stage in which the user exits from a last accessed service module to exit the application software;
the first acquisition unit is used for acquiring the access log uploaded by the application software;
a second generating unit, configured to determine, based on the application log, that each service module that the user has accessed in the key phase is a target service module, and generate a module execution path corresponding to each target service module;
a merging unit, configured to merge the first stage, the third stage, and the execution paths of the modules into a complete access path for the user to access the application software;
and the analysis unit is used for inputting the complete access path into a preset prejudgment model and obtaining a service preference value corresponding to each service model in the application software output by the prejudgment model.
The above apparatus, optionally, further comprises:
the second acquisition unit is used for acquiring the access information uploaded by the application software when the user is detected to quit the application software;
the analysis unit is used for analyzing the access information to obtain each timestamp contained in the access information;
a detecting unit, configured to detect whether each timestamp includes a timestamp carrying a first identification bit, where the timestamp carrying the first identification bit is an operation time for executing a service operation corresponding to an arbitrary service module when the user executes the service operation in the application software;
the first determining unit is used for determining that the user effectively accesses the application software if each timestamp contains a timestamp carrying a first identification bit;
and the second determining unit is used for determining that the user has invalid access to the application software if the timestamps do not contain the timestamp carrying the first identification bit.
The above apparatus, optionally, the first generating unit includes:
the sequencing subunit is used for sequencing the timestamps according to a time sequence;
the dividing subunit is used for dividing each sequenced timestamp into a first access time interval, a second access time interval and a third access time interval according to the time sequence, wherein the second access time interval comprises all timestamps carrying the first identification bits;
a setting subunit, configured to set a stage in which the user accesses the application software within the first access time interval as a first stage, a stage in which the user accesses the application software within the second access time interval as a second stage, and a stage in which the user accesses the application software within the third access time interval as a third stage;
and the construction subunit is used for constructing an access path of the user for accessing the application software based on the first phase, the second phase and the third phase.
The above apparatus, optionally, the second generating unit includes:
the first determining subunit is configured to determine a service module associated with each timestamp carrying the first identification bit in the access log;
a second determining subunit, configured to determine, as a target service module that the user has accessed in the key phase, a service module associated with each timestamp carrying the first identification bit;
a reading subunit, configured to read, in the access log, each execution node corresponding to each target service module;
and the generating subunit is configured to generate a module execution path corresponding to each target service module based on each execution node corresponding to each target service module.
The above apparatus, optionally, further comprises:
a third obtaining unit, configured to obtain a preset service analysis model;
the triggering unit is used for inputting the complete access path into the service analysis model, triggering the service analysis model to perform service operation analysis on each target service module accessed in the complete access path, and obtaining a service analysis result; the service operation analysis comprises funnel analysis, error reporting analysis, dwell time analysis and browsing frequency analysis;
and the sending unit is used for generating service index information corresponding to each target service module based on the service analysis result and sending the service index information to the optimization server, so that the optimization server optimizes the service corresponding to each target service module based on the service index information.
A storage medium, the storage medium comprising stored instructions, wherein when the instructions are executed, a device in which the storage medium is located is controlled to execute the service preference analysis method.
An electronic device comprising a memory, and one or more instructions, wherein the one or more instructions are stored in the memory and configured to be executed by the one or more processors to perform the business preference analysis method described above.
Compared with the prior art, the invention has the following advantages:
the invention provides a service preference analysis method, which comprises the following steps: when detecting that a user effectively accesses application software, generating an access path for the user to access the application software, wherein the application software comprises a plurality of business modules, and each business module corresponds to each business of a bank one by one; extracting a first stage, a second stage and a third stage in the access path, and setting the second stage as a key stage; acquiring an access log uploaded by the application software; determining each service module visited by the user in the key stage as a target service module based on the application log, and generating a module execution path corresponding to each target service module; combining the first stage, the third stage and the execution paths of the modules into a complete access path for the user to access the application software; and inputting the complete access path into a preset pre-judgment model to obtain a service preference value corresponding to each service model in the application software output by the pre-judgment model. By applying the method provided by the embodiment of the invention, the preference degree of the user to each service can be determined according to the analysis of the access path of the user accessing the application software, so that the related service can be accurately recommended to the user.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a flowchart of a method for analyzing service preferences according to an embodiment of the present invention;
fig. 2 is a flowchart of another method of a service preference analysis method according to an embodiment of the present invention;
fig. 3 is a flowchart of another method of a service preference analysis method according to an embodiment of the present invention;
fig. 4 is a flowchart of another method of a service preference analysis method according to an embodiment of the present invention;
fig. 5 is a device structure diagram of a service preference analysis device according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In this application, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions, and the terms "comprises", "comprising", or any other variation thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The invention is operational with numerous general purpose or special purpose computing device environments or configurations. For example: personal computers, server computers, hand-held or portable devices, tablet-type devices, multi-processor apparatus, distributed computing environments that include any of the above devices or equipment, and the like.
The embodiment of the present invention provides a service preference analysis method, which can be applied to a plurality of system platforms, wherein an execution subject of the method can be a computer terminal or a processor of various mobile devices, and a flow chart of the method is shown in fig. 1, and specifically includes:
s101: and when detecting that the user effectively accesses the application software, generating an access path for the user to access the application software.
The application software comprises a plurality of business modules, and each business module corresponds to each business of a bank one by one.
In the embodiment of the invention, the process of accessing the application software by the user is divided into two cases of validity and invalidity. Users who access the application software inefficiently are churn customers, and users who access the application software effectively are valid users. The user invalid access means that a user does not click any service module to browse in the process of accessing the application software, and the user valid access means that the user clicks at least one service module to browse in the process of accessing the application software.
S102: and extracting a first stage, a second stage and a third stage in the access path, and setting the second stage as a key stage.
The first stage is a stage before the user enters a home page of the service module of the application software for the first time, the second stage is a stage when the user circulates in at least one service module of the application software, and the third stage is a stage when the user leaves the last accessed service module and exits the application software.
In the embodiment of the invention, the access path is divided into three stages, in the second stage, a user can transfer access among all service modules of the application software, and the same service module can also carry out access for multiple times.
S103: and acquiring an access log uploaded by the application software.
It should be noted that, the access log records all data information of the user accessing the application software this time.
S104: and determining each service module visited by the user in the key stage as a target service module based on the application log, and generating a module execution path corresponding to each target service module.
In the embodiment of the present invention, the access log includes operation information and a corresponding timestamp of each operation executed by the user in the process of accessing the application software, an operation process, an operation result, and the like. The key phase is an important process for accessing each service module by the user, in the key phase, the user accesses at least one service module, and the service module accessed by the user is set as a target service module. In the process of accessing the target service module, the user can browse the service corresponding to the service module, execute input operation, purchase confirmation, transaction cancellation and other operations.
Each operation executed by the user corresponds to one display page, for example: module home page, entry page, input page, confirmation page, success page, and the like. In order to describe the circulation process of the user in each target service module in detail, a module execution path corresponding to each target service module is generated through each data information recorded in the access log.
S105: and combining the first stage, the third stage and the execution paths of the modules into a complete access path for the user to access the application software.
In the embodiment of the invention, the execution path of each module replaces the original second stage, and the first stage and the third stage are combined to generate a complete and detailed access path.
S106: and inputting the complete access path into a preset pre-judgment model to obtain a service preference value corresponding to each service model in the application software output by the pre-judgment model.
In the embodiment of the present invention, before the pre-judging model is applied to pre-judge the service preference value corresponding to each service, machine learning training needs to be performed on the pre-judging model to ensure the calculation accuracy of the model.
Specifically, the process of performing machine learning training on the prejudgment model includes: and presetting a plurality of complete access paths as training data for training the prejudgment model. And taking each service preference value corresponding to each complete access path as a training target of the complete access path. When the pre-judging model is trained, inputting each training data into the pre-judging model to obtain a training result which is output by the pre-judging model each time and corresponds to each training data, calculating a training target and a training result which correspond to the training data, and determining an error value between the training target and the training result. If the error value is larger than the threshold value, the model parameters in the pre-judging model are adjusted according to the set loss function, and the training is finished until the error value between the training result currently output by the pre-judging model and the training target is smaller than the threshold value.
In the service preference analysis method provided by the embodiment of the invention, when detecting that the user effectively accesses the application software, an access path for the user to access the application software is generated. The first, second and third stages in the access path are extracted. The first stage is that in the process of accessing the application software this time, a user enters the application software before accessing the application software for the first time; the second stage is that in the process of accessing the application software, the user circularly accesses each service module; and the third stage is the process from the end of the user accessing all the service modules to the exit of the application software in the process of accessing the application software. And acquiring an access log uploaded by the application software, determining each target service module accessed by the user based on the application log, and generating a module execution path corresponding to each target service module. And combining the first stage, the third stage and each module execution path to obtain a complete access path, and detecting the service preference value of each service of the user according to the complete access path by the pre-judging model.
Optionally, after the service preference value of each service is obtained, each service may be recommended to the user for multiple times in the application software according to the size of the service preference value of the service, and the larger the service preference value is, the more the number and times of recommendation are.
By applying the method provided by the embodiment of the invention, the preference degree of the user to each service is determined according to the comprehensive analysis of the access path of the user to access the application software, so that the related service is accurately recommended to the user.
In the method provided by the embodiment of the present invention, before performing the service preference analysis, it is necessary to determine whether the access of the user to the application software is valid access, so as to perform the subsequent service preference analysis process. Therefore, referring to fig. 2, the embodiment of the present invention may further include:
s201: and when the user is detected to exit the application software, acquiring the access information uploaded by the application software.
In the embodiment of the invention, the application software sends the access state of the user to the server in real time, and when the user quits to access the application software, the application software actively uploads the access log carrying the access information. The access information is obtained when the processor detects that the user exits the application software.
The access information includes a time stamp of each operation performed by the user during the access to the application software, user information, and the like. Wherein the access information belongs to the access log described in S104 above.
S202: and analyzing the access information to obtain each time stamp contained in the access information.
In the embodiment of the present invention, if the access information includes at least two timestamps. When a user clicks to enter the application software, the time stamp of the application software is recorded, and similarly, the corresponding time stamp is marked when the application software exits.
It is understood that the access information is part of the information in the access log, and when the respective timestamps in the access information need to be obtained, the respective timestamps can be directly obtained from the access log.
S203: and detecting whether each timestamp contains a timestamp carrying a first identification bit.
The timestamp carrying the first identification bit is the operation time for executing the service operation when the user executes the service operation corresponding to any service module in the application software.
In the embodiment of the invention, when a user accesses any service module, the application software marks a time stamp, and a first identification bit is embedded in the time stamp to represent the time point corresponding to the time stamp as the time point when the user accesses a certain service module. Therefore, when checking whether the access path is valid, it is necessary to determine whether the user accesses the service module in the application software, that is, whether each timestamp includes a timestamp carrying the first identification bit. If each timestamp contains a timestamp carrying a first identification bit, executing S204; if each timestamp does not include a timestamp carrying the first identification bit, S205 is executed.
S204: determining that the user is actively accessing the application software.
It will be appreciated that when the user effectively accesses the application software, subsequent business preference analysis processes may be performed.
S205: determining that the user has invalid access to the application software.
It will be appreciated that when it is determined that a user has failed access to the application software, it is characterized that the user has not accessed any of the business modules, without the need to analyze the business preferences of the user.
According to the method provided by the embodiment of the invention, when the user exits the application software, a plurality of timestamps are obtained through the access information uploaded by the application software, whether the timestamp of the first identification bit is included in each timestamp is determined, if yes, the user is determined to access the application software as effective access, and the service preference analysis can be continued; otherwise, the service preference analysis is not needed.
For example, when a user accesses a mobile phone bank APP, the user enters a home page of the mobile phone bank APP from a mobile phone homepage, clicks a service module displayed as "fund", leaves the service module, and exits the mobile phone bank APP, and then determines that the user accesses the mobile phone bank APP this time as valid access. Otherwise, when the user accesses the mobile phone bank APP, after entering the home page of the mobile phone bank APP from the home page of the mobile phone bank APP, any business module is not clicked, and the user directly exits the mobile phone bank APP, the fact that the user accesses the mobile phone bank APP is determined to be invalid, and the user is currently determined to be a lost user.
By applying the method provided by the embodiment of the invention, whether the user has effective access to the application software is verified, so that the subsequent service preference analysis process is executed when effective access is determined.
In the method provided in the embodiment of the present invention, after detecting that the user has effectively accessed the application software, a process of generating a corresponding access path is shown in fig. 3, which may specifically include:
s301: and sequencing the timestamps according to a time sequence.
It should be noted that, in the process of accessing the application software, each time an operation is executed by the user, the corresponding timestamp is marked. For example, a timestamp of clicking into a home page of the application software, a timestamp of sliding a home page, a timestamp of clicking into a business module, a timestamp of pushing out the application software, and the like.
S302: and dividing the sorted timestamps into a first access time interval, a second access time interval and a third access time interval according to the time sequence.
And the second access time interval comprises all timestamps carrying the first identification bits.
It is understood that, in the first time interval, the user starts to enter the application software and has not accessed the service module of the application software; in a second time interval, the user is accessing each service module; and in the third time interval, the user finishes accessing each service module and quits the application software.
S303: setting the stage of the user accessing the application software in the first access time interval as a first stage, the stage of the user accessing the application software in the second access time interval as a second stage, and the stage of the user accessing the application software in the third access time interval as a third stage.
It is understood that the first time interval corresponds to the first phase, the second time interval corresponds to the second phase, and the third time interval corresponds to the third phase.
S304: and constructing an access path of the user for accessing the application software based on the first stage, the second stage and the third stage.
In the embodiment of the present invention, the access path is: first phase-second phase-third phase.
In the service preference analysis method provided by the embodiment of the invention, the timestamps in the access information are sequenced according to the time sequence, and the sequenced timestamps are divided into three time intervals. The time interval division rule is as follows: according to the sequencing sequence, generating a first time interval based on each timestamp before the first timestamp carrying the first identification bit; generating a second time interval based on each timestamp between the first timestamp carrying the first identification bit and the last timestamp carrying the first identification bit; a third time interval is generated based on the respective timestamps subsequent to the last timestamp carrying the first identification bit. Setting a user access stage corresponding to a first time interval as a first stage, a user access stage corresponding to a second time interval as a second stage, a user access stage corresponding to a third time interval as a third stage, and finally associating the first stage, the second stage and the third stage to construct an access path.
Further, after the access path is generated, since the second stage is a stage in which the user flows between the service modules, the second stage is set as a key stage. In order to improve the analysis precision of the business preference, the access path needs to be further refined. Therefore, referring to fig. 4, after obtaining the access log, based on the access log, determining each service module that the user has accessed in the key phase as a target service module, and generating a module execution path corresponding to each target service module, which may specifically include:
s401: and determining the service module associated with each timestamp carrying the first identification bit in the access log.
In the embodiment of the invention, the access log records the process and related data of the application service accessed by the user at this time, the access log is associated with the access information, and the service module associated with each timestamp carrying the first identification bit is determined by each timestamp carrying the first identification bit in the access information.
S402: and determining the service module associated with each timestamp carrying the first identification bit as a target service module accessed by the user in the key stage.
In the embodiment of the invention, the accessed service module is determined as the target service module.
S403: and reading each execution node corresponding to each target service module in the access log.
In the embodiment of the present invention, each execution node of the target service module may include a start node, an intermediate node, and an end node. The starting node is a module home page of a target service module for a user to enter, and the intermediate node is a detail page of clicking service details, an input page of checking service information, a confirmation page of purchasing related services and a transaction success page of successful transaction or a transaction failure page of failed transaction in the target service module for the user; the end node is a return page leaving the target traffic module.
S404: and generating a module execution path corresponding to each target service module based on each execution node corresponding to each target service module.
In the embodiment of the present invention, based on the above S403, the module execution path corresponding to each target service module is a module home page, a detail page, an input page, a confirmation page, a success page, or a failure page, and a return page.
In the intermediate node, if the user does not perform the operations of inputting, confirming, transaction success or failure, etc., there is no corresponding flow. For example, when a user accesses a business module, the user only checks business details, and then generates a module execution path corresponding to the business module as a module home page, a detail page, and a return page.
In the service preference analysis method provided by the embodiment of the invention, the service module associated with each timestamp carrying the first identification bit in the access log is determined, and the service module is determined to be the target service module. And reading each execution node of the target service module, analyzing each execution node, and determining the execution flow of each execution node so as to generate a module execution route corresponding to the target service module.
By applying the method provided by the embodiment of the invention, the access path of the user for accessing the application software is further refined, and the accuracy of subsequent analysis of the business preference is improved.
In the method provided by the embodiment of the present invention, in the process of accessing each service module of application software, a user may fail to access or fail to transact a service due to a network or a module parameter, or there is no service that the user likes, and in order to further optimize each service of a bank, each service in the application software needs to be further analyzed according to an access path of the user, so as to further optimize each service and each service module, which specifically includes:
acquiring a preset service analysis model;
inputting the complete access path into the service analysis model, and triggering the service analysis model to perform service operation analysis on each target service module accessed in the complete access path to obtain a service analysis result; the service operation analysis comprises funnel analysis, error reporting analysis, dwell time analysis and browsing frequency analysis;
and generating service index information corresponding to each target service module based on the service analysis result, and sending the service index information to an optimization server, so that the optimization server optimizes the service corresponding to each target service module based on the service index information.
It should be noted that funnel analysis means that the visit volume of each step is counted according to the steps of the standard flow, the conversion rate of the next step is calculated by calculating the "visit volume of the next step/visit volume of this step", and the final successful conversion rate of each step is calculated by calculating the "visit volume of the achievement target page/visit volume of this step"; and finding out specific steps of user loss by transversely comparing the conversion rates, and performing targeted optimization and promotion. Error analysis means that there may be two main reasons for analyzing the customer missing the next process flow according to the user: one is that the client leaves actively; the other is that the client has to leave because of the system error report, and the loss can be managed and analyzed through the existing error report information in the user access process, so that several conditions of the system error report information ranking at the top in each process can be calculated, and then the improvement and the perfection are performed in a targeted manner. The dwell time analysis refers to the dwell time of a user in a certain service module, and the browsing frequency analysis is the frequency of repeatedly accessing the same service module by the user in the process of accessing the application software.
It can be understood that funnel analysis, error reporting analysis, dwell time analysis and browsing frequency analysis are performed on the complete access path through the service analysis model to obtain a service analysis result corresponding to each target service module, and corresponding service index information is generated according to the analysis result. The service index information comprises a subsequent processing scheme for further calculating the analysis result, and after the service index information is sent to the server, the server can adjust and optimize the service according to the service index information.
By applying the method provided by the embodiment of the invention, besides analyzing the service preference of the user, the service index of the service can be analyzed according to the access path so as to further optimize each service of the bank, thereby improving the experience of the subsequent user.
The specific implementation procedures and derivatives thereof of the above embodiments are within the scope of the present invention.
Corresponding to the method described in fig. 1, an embodiment of the present invention further provides a service preference analysis apparatus, which is used for implementing the method in fig. 1 specifically, the service preference analysis apparatus provided in the embodiment of the present invention may be applied to a computer terminal or various mobile devices, and a schematic structural diagram of the service preference analysis apparatus is shown in fig. 5, and specifically includes:
a first generating unit 501, configured to generate an access path for a user to access application software when it is detected that the user effectively accesses the application software, where the application software includes a plurality of service modules, and each service module corresponds to each service of a bank one-to-one;
an extracting unit 502, configured to extract a first stage, a second stage, and a third stage in the access path, and set the second stage as an important stage, where the first stage is a stage before the user enters a home page of a service module of the application software for the first time, the second stage is a stage in which the user circulates in at least one service module of the application software, and the third stage is a stage in which the user exits from a last accessed service module to exit the application software;
a first obtaining unit 503, configured to obtain an access log uploaded by the application software;
a second generating unit 504, configured to determine, based on the application log, that each service module that the user has accessed in the key phase is a target service module, and generate a module execution path corresponding to each target service module;
a merging unit 505, configured to merge the first stage, the third stage, and the execution paths of the modules into a complete access path for the user to access the application software;
an analyzing unit 506, configured to input the complete access path into a preset pre-judgment model, and obtain a service preference value corresponding to each service model in the application software output by the pre-judgment model.
In the service preference analysis device provided by the embodiment of the invention, when detecting that the user effectively accesses the application software, an access path for the user to access the application software at this time is generated. The first, second and third stages in the access path are extracted. The first stage is that in the process of accessing the application software this time, a user enters the application software before accessing the application software for the first time; the second stage is that in the process of accessing the application software, the user circularly accesses each service module; and the third stage is the process from the end of the user accessing all the service modules to the exit of the application software in the process of accessing the application software. And acquiring an access log uploaded by the application software, determining each target service module accessed by the user based on the application log, and generating a module execution path corresponding to each target service module. And combining the first stage, the third stage and each module execution path to obtain a complete access path, and detecting the service preference value of each service of the user according to the complete access path by the pre-judging model.
By applying the device provided by the embodiment of the invention, the preference degree of the user to each service is determined according to the comprehensive analysis of the access path of the user to access the application software, so that the related service is accurately recommended to the user.
The device provided by the embodiment of the invention further comprises:
the second acquisition unit is used for acquiring the access information uploaded by the application software when the user is detected to quit the application software;
the analysis unit is used for analyzing the access information to obtain each timestamp contained in the access information;
a detecting unit, configured to detect whether each timestamp includes a timestamp carrying a first identification bit, where the timestamp carrying the first identification bit is an operation time for executing a service operation corresponding to an arbitrary service module when the user executes the service operation in the application software;
the first determining unit is used for determining that the user effectively accesses the application software if each timestamp contains a timestamp carrying a first identification bit;
and the second determining unit is used for determining that the user has invalid access to the application software if the timestamps do not contain the timestamp carrying the first identification bit.
In the apparatus provided in the embodiment of the present invention, the first generating unit 501 includes:
the sequencing subunit is used for sequencing the timestamps according to a time sequence;
the dividing subunit is used for dividing each sequenced timestamp into a first access time interval, a second access time interval and a third access time interval according to the time sequence, wherein the second access time interval comprises all timestamps carrying the first identification bits;
a setting subunit, configured to set a stage in which the user accesses the application software within the first access time interval as a first stage, a stage in which the user accesses the application software within the second access time interval as a second stage, and a stage in which the user accesses the application software within the third access time interval as a third stage;
and the construction subunit is used for constructing an access path of the user for accessing the application software based on the first phase, the second phase and the third phase.
In the apparatus provided in the embodiment of the present invention, the second generating unit 504 includes:
the first determining subunit is configured to determine a service module associated with each timestamp carrying the first identification bit in the access log;
a second determining subunit, configured to determine, as a target service module that the user has accessed in the key phase, a service module associated with each timestamp carrying the first identification bit;
a reading subunit, configured to read, in the access log, each execution node corresponding to each target service module;
and the generating subunit is configured to generate a module execution path corresponding to each target service module based on each execution node corresponding to each target service module.
The device provided by the embodiment of the invention further comprises:
a third obtaining unit, configured to obtain a preset service analysis model;
the triggering unit is used for inputting the complete access path into the service analysis model, triggering the service analysis model to perform service operation analysis on each target service module accessed in the complete access path, and obtaining a service analysis result; the service operation analysis comprises funnel analysis, error reporting analysis, dwell time analysis and browsing frequency analysis;
and the sending unit is used for generating service index information corresponding to each target service module based on the service analysis result and sending the service index information to the optimization server, so that the optimization server optimizes the service corresponding to each target service module based on the service index information.
The specific working processes of each unit and sub-unit in the service preference analyzing apparatus disclosed in the above embodiment of the present invention may refer to corresponding contents in the service preference analyzing method disclosed in the above embodiment of the present invention, and are not described herein again.
The embodiment of the invention also provides a storage medium, which comprises a stored instruction, wherein when the instruction runs, the equipment where the storage medium is located is controlled to execute the service preference analysis method.
An electronic device is provided in an embodiment of the present invention, and the structural diagram of the electronic device is shown in fig. 6, which specifically includes a memory 601 and one or more instructions 602, where the one or more instructions 602 are stored in the memory 601 and configured to be executed by one or more processors 603 to perform the following operations on the one or more instructions 602:
when detecting that a user effectively accesses application software, generating an access path for the user to access the application software, wherein the application software comprises a plurality of business modules, and each business module corresponds to each business of a bank one by one;
extracting a first stage, a second stage and a third stage in the access path, and setting the second stage as a key stage, wherein the first stage is a stage before the user enters a home page of a service module of the application software for the first time, the second stage is a stage when the user circulates in at least one service module of the application software, and the third stage is a stage when the user leaves the last accessed service module and exits the application software;
acquiring an access log uploaded by the application software;
determining each service module visited by the user in the key stage as a target service module based on the application log, and generating a module execution path corresponding to each target service module;
combining the first stage, the third stage and the execution paths of the modules into a complete access path for the user to access the application software;
and inputting the complete access path into a preset pre-judgment model to obtain a service preference value corresponding to each service model in the application software output by the pre-judgment model.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, the system or system embodiments are substantially similar to the method embodiments and therefore are described in a relatively simple manner, and reference may be made to some of the descriptions of the method embodiments for related points. The above-described system and system embodiments are only illustrative, wherein the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both.
To clearly illustrate this interchangeability of hardware and software, various illustrative components and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A service preference analysis method is characterized by comprising the following steps:
when detecting that a user effectively accesses application software, generating an access path for the user to access the application software, wherein the application software comprises a plurality of business modules, and each business module corresponds to each business of a bank one by one;
extracting a first stage, a second stage and a third stage in the access path, and setting the second stage as a key stage, wherein the first stage is a stage before the user enters a home page of a service module of the application software for the first time, the second stage is a stage when the user circulates in at least one service module of the application software, and the third stage is a stage when the user leaves the last accessed service module and exits the application software;
acquiring an access log uploaded by the application software;
determining each service module visited by the user in the key stage as a target service module based on the application log, and generating a module execution path corresponding to each target service module;
combining the first stage, the third stage and the execution paths of the modules into a complete access path for the user to access the application software;
and inputting the complete access path into a preset pre-judgment model to obtain a service preference value corresponding to each service model in the application software output by the pre-judgment model.
2. The method of claim 1, further comprising:
when the user is detected to exit the application software, acquiring access information uploaded by the application software;
analyzing the access information to obtain each timestamp contained in the access information;
detecting whether each timestamp contains a timestamp carrying a first identification bit, wherein the timestamp carrying the first identification bit is the operation time for executing the service operation when the user executes the service operation corresponding to any service module in the application software;
if each timestamp contains a timestamp carrying a first identification bit, determining that the user effectively accesses the application software;
and if the timestamps do not contain the timestamp carrying the first identification bit, determining that the user has invalid access to the application software.
3. The method of claim 2, wherein generating the access path for the user to access the application software comprises:
sequencing the timestamps according to a time sequence;
dividing each sequenced timestamp into a first access time interval, a second access time interval and a third access time interval according to the time sequence, wherein the second access time interval comprises all timestamps carrying first identification bits;
setting the stage of the user accessing the application software in the first access time interval as a first stage, the stage of the user accessing the application software in the second access time interval as a second stage, and the stage of the user accessing the application software in the third access time interval as a third stage;
and constructing an access path of the user for accessing the application software based on the first stage, the second stage and the third stage.
4. The method according to claim 3, wherein the determining, based on the access log, that each service module that the user has accessed in the emphasis phase is a target service module, and generating a module execution path corresponding to each target service module comprises:
determining a service module associated with each timestamp carrying a first identification bit in the access log;
determining the service module associated with each timestamp carrying the first identification bit as a target service module visited by the user in the key stage;
reading each execution node corresponding to each target service module in the access log;
and generating a module execution path corresponding to each target service module based on each execution node corresponding to each target service module.
5. The method of claim 1, further comprising:
acquiring a preset service analysis model;
inputting the complete access path into the service analysis model, and triggering the service analysis model to perform service operation analysis on each target service module accessed in the complete access path to obtain a service analysis result; the service operation analysis comprises funnel analysis, error reporting analysis, dwell time analysis and browsing frequency analysis;
and generating service index information corresponding to each target service module based on the service analysis result, and sending the service index information to an optimization server, so that the optimization server optimizes the service corresponding to each target service module based on the service index information.
6. A service preference analysis apparatus, comprising:
the system comprises a first generation unit, a second generation unit and a third generation unit, wherein the first generation unit is used for generating an access path for a user to access application software when the user is detected to effectively access the application software, the application software comprises a plurality of business modules, and each business module corresponds to each business of a bank one by one;
an extracting unit, configured to extract a first stage, a second stage, and a third stage in the access path, and set the second stage as a key stage, where the first stage is a stage before the user enters a home page of a service module of the application software for the first time, the second stage is a stage in which the user circulates in at least one service module of the application software, and the third stage is a stage in which the user exits from a last accessed service module to exit the application software;
the first acquisition unit is used for acquiring the access log uploaded by the application software;
a second generating unit, configured to determine, based on the application log, that each service module that the user has accessed in the key phase is a target service module, and generate a module execution path corresponding to each target service module;
a merging unit, configured to merge the first stage, the third stage, and the execution paths of the modules into a complete access path for the user to access the application software;
and the analysis unit is used for inputting the complete access path into a preset prejudgment model and obtaining a service preference value corresponding to each service model in the application software output by the prejudgment model.
7. The apparatus of claim 6, further comprising:
the second acquisition unit is used for acquiring the access information uploaded by the application software when the user is detected to quit the application software;
the analysis unit is used for analyzing the access information to obtain each timestamp contained in the access information;
a detecting unit, configured to detect whether each timestamp includes a timestamp carrying a first identification bit, where the timestamp carrying the first identification bit is an operation time for executing a service operation corresponding to an arbitrary service module when the user executes the service operation in the application software;
the first determining unit is used for determining that the user effectively accesses the application software if each timestamp contains a timestamp carrying a first identification bit;
and the second determining unit is used for determining that the user has invalid access to the application software if the timestamps do not contain the timestamp carrying the first identification bit.
8. The apparatus of claim 7, wherein the first generating unit comprises:
the sequencing subunit is used for sequencing the timestamps according to a time sequence;
the dividing subunit is used for dividing each sequenced timestamp into a first access time interval, a second access time interval and a third access time interval according to the time sequence, wherein the second access time interval comprises all timestamps carrying the first identification bits;
a setting subunit, configured to set a stage in which the user accesses the application software within the first access time interval as a first stage, a stage in which the user accesses the application software within the second access time interval as a second stage, and a stage in which the user accesses the application software within the third access time interval as a third stage;
and the construction subunit is used for constructing an access path of the user for accessing the application software based on the first phase, the second phase and the third phase.
9. The apparatus of claim 8, wherein the second generating unit comprises:
the first determining subunit is configured to determine a service module associated with each timestamp carrying the first identification bit in the access log;
a second determining subunit, configured to determine, as a target service module that the user has accessed in the key phase, a service module associated with each timestamp carrying the first identification bit;
a reading subunit, configured to read, in the access log, each execution node corresponding to each target service module;
and the generating subunit is configured to generate a module execution path corresponding to each target service module based on each execution node corresponding to each target service module.
10. The apparatus of claim 6, further comprising:
a third obtaining unit, configured to obtain a preset service analysis model;
the triggering unit is used for inputting the complete access path into the service analysis model, triggering the service analysis model to perform service operation analysis on each target service module accessed in the complete access path, and obtaining a service analysis result; the service operation analysis comprises funnel analysis, error reporting analysis, dwell time analysis and browsing frequency analysis;
and the sending unit is used for generating service index information corresponding to each target service module based on the service analysis result and sending the service index information to the optimization server, so that the optimization server optimizes the service corresponding to each target service module based on the service index information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110774755.7A CN113486241A (en) | 2021-07-08 | 2021-07-08 | Service preference analysis method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110774755.7A CN113486241A (en) | 2021-07-08 | 2021-07-08 | Service preference analysis method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113486241A true CN113486241A (en) | 2021-10-08 |
Family
ID=77938139
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110774755.7A Pending CN113486241A (en) | 2021-07-08 | 2021-07-08 | Service preference analysis method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113486241A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2011253480A (en) * | 2010-06-04 | 2011-12-15 | Ricoh Co Ltd | Information processor, document management system, document management method, program, recording medium and image processor |
| CN106294559A (en) * | 2016-07-26 | 2017-01-04 | 北京三快在线科技有限公司 | A kind of application traffic analysis method and device |
| CN106897313A (en) * | 2015-12-21 | 2017-06-27 | 中国联合网络通信集团有限公司 | A kind of mass users business preference evaluation method and apparatus |
| CN108335132A (en) * | 2018-01-22 | 2018-07-27 | 中国平安人寿保险股份有限公司 | Analysis method, device, storage medium and the terminal of application program |
| CN111899075A (en) * | 2020-08-11 | 2020-11-06 | 恒瑞通（福建）信息技术有限公司 | Personalized commodity recommendation method and device based on user behaviors |
| CN112288483A (en) * | 2020-10-29 | 2021-01-29 | 北京沃东天骏信息技术有限公司 | Method and device for training model and method and device for generating information |
-
2021
- 2021-07-08 CN CN202110774755.7A patent/CN113486241A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2011253480A (en) * | 2010-06-04 | 2011-12-15 | Ricoh Co Ltd | Information processor, document management system, document management method, program, recording medium and image processor |
| CN106897313A (en) * | 2015-12-21 | 2017-06-27 | 中国联合网络通信集团有限公司 | A kind of mass users business preference evaluation method and apparatus |
| CN106294559A (en) * | 2016-07-26 | 2017-01-04 | 北京三快在线科技有限公司 | A kind of application traffic analysis method and device |
| CN108335132A (en) * | 2018-01-22 | 2018-07-27 | 中国平安人寿保险股份有限公司 | Analysis method, device, storage medium and the terminal of application program |
| CN111899075A (en) * | 2020-08-11 | 2020-11-06 | 恒瑞通（福建）信息技术有限公司 | Personalized commodity recommendation method and device based on user behaviors |
| CN112288483A (en) * | 2020-10-29 | 2021-01-29 | 北京沃东天骏信息技术有限公司 | Method and device for training model and method and device for generating information |
Non-Patent Citations (1)
| Title |
|---|
| 刘颖;彭赓;吕本富;陈杰;梅梅;: "基于Web日志的用户访问路径提取与分析", 情报学报, no. 04, 24 August 2009 (2009-08-24) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108259482B (en) | Network Abnormal data detection method, device, computer equipment and storage medium | |
| US11710054B2 (en) | Information recommendation method, apparatus, and server based on user data in an online forum | |
| CN106294614B (en) | Method and apparatus for accessing business | |
| CN108156237B (en) | Product information pushing method and device, storage medium and computer equipment | |
| EP2748781B1 (en) | Multi-factor identity fingerprinting with user behavior | |
| US9239771B2 (en) | Method and system for collecting and providing application usage analytics | |
| CN110442712B (en) | Risk determination method, risk determination device, server and text examination system | |
| US20200082810A1 (en) | System and method for mapping a customer journey to a category | |
| CN111949803A (en) | Method, device and equipment for detecting network abnormal user based on knowledge graph | |
| WO2019061664A1 (en) | Electronic device, user's internet surfing data-based product recommendation method, and storage medium | |
| CN106485261A (en) | A kind of method and apparatus of image recognition | |
| CN110147495A (en) | Page response method, apparatus, equipment and medium based on Configuration Online | |
| CN111882399A (en) | Service information recommendation method, device, computer system and readable storage medium | |
| CN107231389B (en) | Code scanning operation method and equipment | |
| CN112801670A (en) | Risk assessment method and device for payment operation | |
| CN112330412A (en) | Product recommendation method and device, computer equipment and storage medium | |
| CN113486241A (en) | Service preference analysis method and device | |
| CN109597948A (en) | Access method, system and the storage medium of URL link | |
| CN113961811B (en) | Event map-based conversation recommendation method, device, equipment and medium | |
| US11270241B2 (en) | Systems and methods for discovery of automation opportunities | |
| EP3342130A1 (en) | Secure communications methods for use with entrepreneurial prediction systems and methods | |
| CN111506826A (en) | User recommendation method, device, equipment and storage medium based on intimacy | |
| CN105701175B (en) | A kind of data capture method and device | |
| CA2914898C (en) | A method and survey server for performing a web survey based on behavioral data specific to a web page | |
| CN106716969A (en) | Technologies for pre-action execution |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |