CN111291093B - Method and device for determining functional association rule of service application - Google Patents
Method and device for determining functional association rule of service application Download PDFInfo
- Publication number
- CN111291093B CN111291093B CN202010103622.2A CN202010103622A CN111291093B CN 111291093 B CN111291093 B CN 111291093B CN 202010103622 A CN202010103622 A CN 202010103622A CN 111291093 B CN111291093 B CN 111291093B
- Authority
- CN
- China
- Prior art keywords
- function
- application
- application function
- association rule
- combination
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Fuzzy Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Computer And Data Communications (AREA)
Abstract
The embodiment of the specification provides a method and a device for determining a functional association rule of a service application. In the method, at least one user session data of a service application is acquired, each user session data comprising an application function identifier of each application function used by a user in the user session; a functional association rule between application functions of the business application is determined based on the application function identification in the user session data, the functional association rule being operable to represent an association relationship between two application function combinations. By using the method or the device, the potential problems of the business application in the aspect of application function design can be found.
Description
Technical Field
The embodiment of the specification relates to the technical field of internet, in particular to a method and a device for determining a function association rule between application functions of business applications.
Background
With the continuous enrichment and perfection of the internet product in function, the architecture design of the product is more complex and diversified, but some problems may occur in the user experience of the application product, for example, the user wants to use the a function of the application product, but may enter the interface corresponding to the B function by mistake due to the problem of product design, which causes trouble to the user use.
Illustratively, the user wants to bind a bank card in the mobile wallet, and after the user opens the mobile wallet software, the user first sees the "card package" entry, but after clicking to enter, the user finds the function of not binding the bank card, and the management page of the bank card is in the "bank card" function of the subordinate of "my". This can easily lead to customer complaints about the product design of the client as the user is not looking for the desired function.
In view of the above problems, there is currently no preferred solution in the industry.
Disclosure of Invention
In view of the foregoing, embodiments of the present disclosure provide a method and apparatus for determining a functional association rule between application functions of a service application. By utilizing the method and the device, the association relation between different application function combinations is mined by acquiring a plurality of user session data and determining the function association rule for indicating the association relation between the two application function combinations based on the application function identification in the user session data so as to find the potential problems of the business application in the aspect of application function design.
According to an aspect of the embodiments of the present specification, there is provided a method for determining a function association rule between application functions of a service application, including: acquiring a first number of user session data for a service application, each user session data comprising an application function identification of each application function used by a user in the user session; and determining a function association rule between application functions of the service application based on the application function identification in the user session data, wherein the function association rule is used for indicating that an association relationship exists between two application function combinations.
Optionally, in one example of the above aspect, determining the function association rule between application functions of the service application based on the application function identification in the user session data may include: determining an application function combination set based on the application function identification in the user session data; determining a candidate function association rule set based on the determined application function combination set; for each candidate function association rule, determining the confidence coefficient of the candidate function association rule based on the occurrence times of the first application function combination and the second application function combination corresponding to the candidate function association rule in the user session data and the occurrence times of a third application function combination in the user session data, wherein the third application function combination is composed of the first application function combination and the second application function combination; and determining the candidate function association rule with the determined confidence coefficient larger than a first preset threshold value as a function association rule between service application functions of the service application.
Optionally, in one example of the above aspect, it may further include: determining a frequent set of application function combinations from the set of application function combinations, each subset of application function combinations in the frequent set of application function combinations occurring in the user session data more than a second predetermined threshold, and determining a set of candidate function association rules based on the determined set of application function combinations, comprising: a candidate function association rule set is determined based on the determined application function combination frequent set.
Alternatively, in one example of the above aspect, the application function combination may include an application function combination that is sequentially used.
Alternatively, in one example of the above aspect, the first application function combination may include an application function combination that is sequentially used.
Optionally, in one example of the above aspect, it may further include: and providing the functional association rule for a service application provider so as to enable the service application provider to perform functional association optimization.
Optionally, in one example of the above aspect, the functional association optimization may include: and optimizing the function association logic of the service application.
Optionally, in one example of the above aspect, the functional association optimization may include: when the user is detected to execute the application function operation, if the function association logic of the business application is inconsistent with the function association rule, guiding the application function operation of the user according to the function association rule.
Optionally, in one example of the above aspect, the user session data may include a user identifier, and the functional association rule is a functional association rule corresponding to the user identifier.
According to another aspect of embodiments of the present specification, there is provided an apparatus for determining a function association rule between application functions of a service application, including: a session data acquisition unit that acquires a first number of user session data for a service application, each user session data including an application function identifier of each application function used by a user in the user session; and the function association rule determining unit is used for determining a function association rule between application functions of the service application based on the application function identification in the user session data, wherein the function association rule is used for indicating that an association relationship exists between two application function combinations.
Alternatively, in one example of the above aspect, the functional association rule determining unit may include: an application function combination set determining module for determining an application function combination set based on the application function identifier in the user session data; a candidate rule set determining module that determines a candidate function association rule set based on the determined application function combination set; the confidence degree determining module determines the confidence degree of each candidate function association rule based on the occurrence times of the first application function combination and the second application function combination corresponding to the candidate function association rule in the user session data and the occurrence times of the third application function combination in the user session data, wherein the third application function combination consists of the first application function combination and the second application function combination; and the association rule determining module is used for determining the candidate function association rule with the determined confidence coefficient larger than a first preset threshold value as the function association rule between the service application functions of the service application.
Optionally, in one example of the above aspect, the function association rule determining unit may further include a frequent set determining module, wherein the frequent set determining module determines an application function combination frequent set from the application function combination set, a number of occurrences of each application function combination subset in the application function combination frequent set in the user session data is greater than a second predetermined threshold, and the candidate rule set determining module determines the candidate function association rule set based on the determined application function combination frequent set.
Alternatively, in one example of the above aspect, the application function combination may include an application function combination that is sequentially used.
Alternatively, in one example of the above aspect, the first application function combination may include an application function combination that is sequentially used.
Optionally, in one example of the above aspect, the apparatus may further include a function optimization unit that provides the function association rule to a service application provider for the service application provider to perform function association optimization.
Optionally, in one example of the above aspect, the functional association optimization may include: and optimizing the function association logic of the service application.
Optionally, in one example of the above aspect, the functional association optimization may include: when the user is detected to execute the application function operation, if the function association logic of the business application is inconsistent with the function association rule, guiding the application function operation of the user according to the function association rule.
According to another aspect of embodiments of the present specification, there is also provided a computing device including: at least one processor; and a memory storing instructions that, when executed by the at least one processor, cause the at least one processor to perform the method for determining functional association rules between application functions of a business application as described above.
According to another aspect of embodiments of the present specification, there is also provided a machine-readable storage medium storing executable instructions that, when executed, cause the machine to perform a method for determining functional association rules between application functions of a business application as described above.
Drawings
A further understanding of the nature and advantages of the embodiments herein may be realized by reference to the following drawings. In the drawings, similar components or features may have the same reference numerals. The accompanying drawings are included to provide a further understanding of embodiments of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain, without limitation, the embodiments of the invention. In the drawings:
FIG. 1 illustrates an interface change schematic diagram of an example of a client running a business application according to an embodiment of the present description;
FIG. 2 illustrates a flow chart of an example of a method for determining functional association rules between application functions of a business application according to an embodiment of the present description;
FIG. 3 illustrates a flowchart of one example of a process for determining functional association rules using user session data according to an embodiment of the present disclosure;
FIG. 4 illustrates a flowchart of one example of a process for determining functional association rules using user session data according to an embodiment of the present disclosure;
FIG. 5 shows a flowchart of an example of a functional association optimization process according to an embodiment of the present disclosure;
FIG. 6 illustrates a block diagram of an example of an apparatus for determining functional association rules between application functions of a business application according to an embodiment of the present disclosure;
fig. 7 shows a block diagram of an example of a functional association rule determining unit according to an embodiment of the present specification;
fig. 8 illustrates a hardware architecture diagram of a computing device for determining functional association rules between application functions of a business application according to an embodiment of the present description.
Detailed Description
The subject matter described herein will be discussed below with reference to example embodiments. It should be appreciated that these embodiments are discussed only to enable a person skilled in the art to better understand and thereby practice the subject matter described herein, and are not limiting of the scope, applicability, or examples set forth in the claims. Changes may be made in the function and arrangement of elements discussed without departing from the scope of the embodiments herein. Various examples may omit, replace, or add various procedures or components as desired. In addition, features described with respect to some examples may be combined in other examples as well.
As used herein, the term "comprising" and variations thereof mean open-ended terms, meaning "including, but not limited to. The term "based on" means "based at least in part on". The terms "one embodiment" and "an embodiment" mean "at least one embodiment. The term "another embodiment" means "at least one other embodiment". The terms "first," "second," and the like, may refer to different or the same object. Other definitions, whether explicit or implicit, may be included below. Unless the context clearly indicates otherwise, the definition of a term is consistent throughout this specification.
In this document, the term "session" means that a complete communication process is performed between the client and the server, for example, the whole operation process of "login-use-close" performed by the user for the client may be referred to as a session. Accordingly, the term "user session data" means operation data generated in one session for a user to a client. In addition, the term "user identification" means identification information of the user identity of the client that initiated the session.
The term "business application" means an application program that is run by a client for providing business services. In addition, the term "application function" means various functions possessed by the application program, such as a "taxi" function and a "charge" function, and the like. Accordingly, the term "application function identifier" means a unique identifier of each application function, and in addition, if a user operates a specific application function in one session, the specific application function identifier may exist in user session data corresponding to the session.
The term "buried point" means a preparation work for deployment where a client collects user operation information, such as a deployment operation performed in advance for collecting user operation information for a "drive" function of the client, and deployment operations for different application functions may be represented by different buried point codes, respectively. Therefore, each application function identifier in the user session data can be acquired through the embedded point.
Furthermore, the term "function association rule" means that there is an association relationship between two application function combinations having one or more application functions (or application function identifications). In this context, data mining analysis based on user session data to determine functional association rules can assist a business application provider (e.g., product design developer) in discovering problems with the business application in terms of application functionality design.
Fig. 1 shows a schematic diagram of an interface change of a client running a business application in an example according to an embodiment of the present description.
As shown in fig. 1, controls corresponding to a plurality of alternative application functions (e.g., function a, function c, function e, etc.) are displayed at an interface 100a of a client running a business application. When the user selects "function a" indicated by the control 102 on the page 100a of the client, the client enters the interface 100b corresponding to the function a. Here, for one application function, there may be a corresponding plurality of subordinate interfaces (e.g., 100 b). If a user only operates multiple interfaces subordinate to the same application function (e.g., function a) in one session, only an application function identifier for the application function operated by the user (e.g., function a) may exist in the user session data corresponding to the session.
In some application scenarios, the user expects to use the function c but mistakenly enters the interface corresponding to the function a, so that the user needs to re-think how to select the function to find the expected function, and the user cannot directly and quickly use the expected function, thereby reducing the user experience. In this regard, it can be generally assumed that there is a potential association relationship between the function a and the function c.
In some application scenarios, the function association logic in the existing application function design of the business application is application function a→e (i.e., when application function a is operated, it automatically jumps to application function e). However, such a functional association logic design may be unreasonable, for example, given that most users continue to operate application function c after operating application function a, i.e., there may be a potential association between function a and function c (e.g., AA collection-group sharing-billing), existing application function designs may need to be improved.
In view of this, the embodiments of the present specification aim at least to determine a function association rule corresponding to an association relationship between application functions, thereby finding a problem potentially existing in terms of application function design.
Fig. 2 shows a flowchart of a method for determining a functional association rule between application functions of a business application (hereinafter also referred to as "functional association rule determination method") according to an embodiment of the present specification.
As in flow 200 of fig. 2, in block 210, a first number of user session data for a business application is acquired. Here, the specific value for the first number should not be limited, and may be a determined value or an undetermined value (for example, the number of user session data generated in a set period of time).
In one example of the embodiment of the present specification, application function identifiers of respective application functions used by a user in respective user session data may be collected by way of buried points. For example, if the user uses the function a, the function c and the function e in the service application in one session, the function identification combination { a, c, e } in the user session data can be acquired through the buried point. Further, since the respective application functions are sequentially operated by the user in one session (which correspond to different time stamps), there may be a corresponding use order between the respective function identifiers in the user session data, for example, expressed in a→c→e.
Next, in block 220, functional association rules between application functions of the business application are determined based on the application function identification in the user session data. For example, an application function combination is constructed based on application function identifications appearing in each user session data, and two application function combinations having an association relationship are determined according to the number of occurrences of the application function combination in each user session data, thereby determining a corresponding function association rule.
In one example of the embodiment of the present specification, there may be no specific order of use between each application function in the associated two application function combinations indicated by the function association rule, for example, where the first application function combination is { a, c }, and the second application function combination is { e, j }.
In another example of an embodiment of the present specification, application function combinations that are sequentially used by a user in one session are stored in user session data. Further, one or both of the two application function combinations corresponding to the function association rule determined by using the user session data may include application function combinations that are sequentially used, for example, a first application function combination of a→c and a second application function combination of e→j, or a first application function combination of a→c and a second application function combination of { e, j }.
In some embodiments, a correlation analysis algorithm may be applied to perform a correlation analysis process on application function identifications in user session data, thereby mining out function correlation rules. Here, the association analysis algorithm may be a known association analysis algorithm (e.g., apriori algorithm or FP-growth algorithm, etc.) or a modified association analysis algorithm. Therefore, the function using behavior of the cross-function identifier in the using process of the application is determined through the association analysis algorithm, the function association rule can be determined more efficiently and conveniently, and the function design problem in the business application is found out.
Fig. 3 shows a flow chart for determining functional association rules using user session data according to an embodiment of the present description.
As in flow 300 of fig. 3, in block 310, a set of application function combinations is determined based on the application function identification in the user session data. For example, a first number of application function identifier combinations corresponding to the first number of user session data may be counted, thereby obtaining an application function combination set.
In addition, various application function identifiers related to the first number of user session data can be determined, and different application function identifiers can be combined in various manners, so that a corresponding application function combination set is determined. Illustratively, the application functions in the user session dataset are identified as A, B, C and D. According to one example of an embodiment of the present specification, the corresponding first and/or second application function combination may be determined to be selected from application function combinations such as { a, B, C, D }, { a }, { B }, { a, B, D }, { a, C }, { a, B } and { B, C }. In addition, according to another example of an embodiment of the present specification, there is a sequence between the plurality of application function identifications in the first and/or second application function combinations, for example, a→b→ C, A →c→b or a→c, and so on.
Next, in block 320, a set of candidate function association rules is determined based on the determined set of application function combinations. Here, each candidate function association rule represents an association relationship between two application function combinations, that is, if a first application function combination appears in one session, it is highly likely that a second application function combination also appears in the session.
In one example of an embodiment of the present disclosure, different combinations of application functions in the application function combination set may be integrated to determine a corresponding plurality of candidate function association rules. Illustratively, if the set of application function combinations includes application function combinations { A, B }, { A, D }, and { C, D }, etc., the determined set of candidate function association rules may be { A, B } → { C, D }, or { A, C } → { B, D }, etc.
In another example of an embodiment of the present specification, at least one application function combination may be selected from the set of application function combinations according to a combination set screening condition (e.g., determining whether the number of occurrences of the application function combination in the session data is frequent), and a corresponding candidate function association rule may be determined according to the selected application function combination. Illustratively, when the application function combination satisfying the combination set filtering condition is { a, B, C, D }, the determined candidate function association rule set may be an association relationship between two subsets of { a, B, C, D }, for example { a, B } → { C, D }, or { a, B, C } → { D }, or the like.
In some embodiments, the application function combination is a sequentially used application function combination, such as individual application functions that are sequentially used by the user in one session. Illustratively, if the first application function combination and the second application function combination are application function combinations having a use order, the candidate function association rule represents an order association, such as { A→B } → { C→D }, that is used in the session between the respective application functions. In addition, only the first application function combination corresponding to the function association rule may include the application function combination used sequentially, and the corresponding second application function combination may not have the function use sequence, i.e., the function association rule is { a→b } → { C } or { a→b → { C, D }, and so on.
Next, in block 330, for each candidate function association rule, a confidence level of the candidate function association rule is determined based on the number of occurrences of the first and second application function combinations in the user session data and the number of occurrences of the third application function combination in the user session data corresponding to the candidate function association rule. Here, the third application function combination is composed of the first application function combination and the second application function combination.
Illustratively, when the candidate function association rule R1 is { A, B } → { C, D }, the first application function combination is { A, B }, the second application function combination is { C, D }, and the third application function combination is { A, B, C, D }. In addition, the confidence level of the candidate function association rule R1 may be used to represent the probability that the application function combination { C, D } will appear when the application function combination { a, B } appears during the session, and the specific value may be determined, for example, according to a quotient obtained by dividing the number of occurrences of the third application function combination by the number of occurrences of the first application function combination.
Next, in block 340, the candidate function association rules for which the determined confidence level is greater than the first predetermined threshold are determined as function association rules between the business application functions of the business application. Here, the function association rule is selected from the candidate function association rules through the confidence level, so that the determined function association rule can be ensured to have higher reliability, namely, a stronger association relationship between the first application function combination and the second application function combination corresponding to the function association rule.
As introduced in the examples described above, the candidate set of functional association rules may be determined from the application function combinations of the application function combination set that meet the combination set screening condition. In some embodiments, the combined set screening condition includes a second predetermined threshold. In this way, a frequent set of application function combinations may be determined from the frequent set of application function combinations according to the second predetermined threshold, and each subset of application function combinations in the frequent set of application function combinations occurs more than the second predetermined threshold in the user session data. Illustratively, when the 3 sets { A, B, C } are determined to be application function combination frequent sets, the number of occurrences of respective subsets of { A, B, C } (e.g., the single set { A }, and the 2 sets { A, B }, { A, C }, etc.) in the user session data is greater than a predetermined number of thresholds. It should be understood that the specific value of the predetermined number of times threshold should not be limited herein and may be adjusted according to the application scenario requirements. Then, a candidate function association rule set may be determined based on the determined application function combination frequent set, improving the efficiency of the determination of the candidate function association rule compared to the operation of determining the candidate function association rule set from the application function combination set.
Further, the application function combinations include sequentially used application function combinations. In this way, the function association rule can reflect the association relationship occurring in order between the application functions in the session. For example, when the application function identification combination is a→b→c→d→e, the corresponding candidate function association rule may be expressed as { a→b } → { c→d→e }, or { a→b→c → { d→e }, or the like. The function association rule for indicating the ordered application function combination has a higher reference value for the product design developer than the function association rule corresponding to the unordered application function combination, and can more conveniently and directly realize the post-optimization operation of similar function guide optimization, for example, function guide can be performed from the function B for c→d→e according to { a→b } → { c→d→e }.
In addition, the first application function combination corresponding to the candidate function association rule includes application function combinations used sequentially, and the second application function combination does not have a corresponding use sequence among the application functions. Thus, the candidate function association rule may be { A→B } → { C, D }, which indicates that when application functions A and B occur sequentially, the corresponding application function C or D will be generated. Thus, the functional range of the application function having the association relationship can be found.
Fig. 4 shows a flow chart for determining functional association rules using user session data according to an embodiment of the present description.
As shown in flow 400 of fig. 4, at block 410, all application function identities indicated by respective user session data are determined. Illustratively, the application function identification item sets { A, B, C } and { B, C, D, E } corresponding to two user sessions, respectively, all application function identifications corresponding thereto are A, B, C, D and E.
Next, in block 420, an application function combination set is built based on the respective application function identifications and a frequent set of application function combinations is determined from the application function combination set. Specifically, the function identification item sets (for example, 1 item set, 2 item set and 3 item set, etc.) corresponding to different item numbers are respectively determined by a mode of multiple combined iteration statistics, and frequent item sets are screened from the function identification item sets.
Illustratively, during a first iteration, each individual set is determined and frequent individual sets are filtered based on the number of occurrences (also referred to as support counts) of each individual set in each user session data.
Here, by querying all the function identifiers, each item is counted to obtain a candidate set, resulting in the results shown in table 1A.
Candidate single item set | Support count |
{A} | 6 |
{B} | 7 |
{C} | 6 |
{D} | 2 |
{E} | 2 |
TABLE 1A
Further, by comparing the support count of the item set in table 1A with the support threshold, the item set smaller than the support threshold is rejected. Assuming a support threshold of 2, all the sets of entries in table 1 of this example are greater than the support threshold. The frequent singlets based on table 1A are shown in table 1B.
Frequent single item set | Support count |
{A} | 6 |
{B} | 7 |
{C} | 6 |
{D} | 2 |
{E} | 2 |
TABLE 1B
Next, a second iteration is performed based on the frequent single sets as in table 1B, and the individual frequent single sets are combined (also referred to as "join steps") to produce a candidate 2-item set. Further, by querying the function identifications of the respective candidate 2-item sets, the number of occurrences of each 2-item set was counted to obtain the results shown in table 2A.
Candidate 2 item set | Support count |
{A,B} | 4 |
{A,C} | 4 |
{A,D} | 1 |
{A,E} | 2 |
{B,C} | 4 |
{B,D} | 2 |
{B,E} | 2 |
{C,D} | 0 |
{C,E} | 1 |
{D,E} | 0 |
TABLE 2A
All the support counts less than threshold 2 are culled, resulting in frequent 2 term sets as shown in table 2B.
Frequent 2 item sets | Support count |
{A,B} | 4 |
{A,C} | 4 |
{A,E} | 2 |
{B,C} | 4 |
{B,D} | 2 |
{B,E} | 2 |
TABLE 2B
Next, based on performing the third iteration of the frequent 2 item set as shown in table 2B, the candidate 3 item set is calculated, and the frequent 3 item set is screened from the candidate 3 item set to determine (as shown in table 3), and the specific process may refer to the above example, which is not described herein.
Frequent 3 item sets | Support count |
{A,B,C} | 2 |
{A,B,E} | 2 |
TABLE 3 Table 3
Next, a fourth iteration is continued based on table 3 to get a { a, B, C, E }, but the subset { B, C, E } in this set of terms is a non-frequent set of terms, so there are no frequent 4 sets of terms for the user session data. So far, all frequent item sets are found.
Next, in block 430, a set of candidate function association rules is determined based on the application function combination frequent set, and confidence levels for each candidate function association rule are calculated based on all of the application function combination frequent sets.
Here, the determination process of the candidate function association rule is described taking the frequent item set x= { a, B, C } as an example. Illustratively, the non-empty subsets of X are { A, B }, { A, C }, { B, C }, { A }, { B }, { C }, candidate function association rule sets are determined based on these non-empty subsets, and the confidence level of each candidate function association rule is determined based on all of the frequent item sets in tables 1B, 2B, and 3.
Candidate function association rules | Confidence level |
{A,B}→{C} | Z1=2/4=50% |
{A,C}→{B} | Z2=2/2=100% |
{B,C}→{A} | Z3=2/2=100% |
{C}→{A,B} | Z4=2/6=33% |
{B}→{A,C} | Z5=2/7=29% |
{A}→{B,C} | Z6=2/2=100% |
TABLE 4 Table 4
Taking the candidate function association rule { a, B } → { C } as an example, the calculation process of the confidence level regarding the candidate function association rule may be determined by:
Z1=S(A∪B∪C)/S(A∪B)
by referring to table 3, S (a u B u C) (i.e., support count of { a, B, C } is determined to be 2. In addition, S (A.u.B) ({ support count of A, B }) is 4 by referring to Table 2. Thus, the confidence level Z1 corresponding to the functional association rule { a, B } → { C } can be calculated to be 50%.
Next, in block 440, functional association rules are screened from the respective candidate functional association rules based on the confidence level and a predefined confidence threshold. Here, the respective confidence degrees obtained are compared with the confidence degree threshold value, so that a function association rule for indicating that the application function combinations have a strong association relationship is determined.
In combination with the candidate function rule set shown in table 4, when the confidence threshold is 70%, the candidate rule { a, B } → { C } does not belong to the required association rule, and only three candidate function association rules in table 4 with a corresponding confidence of 100% belong to the required function association rule. However, when the confidence threshold is predefined to be 40%, the candidate rule { A, B } → { C } corresponding to a confidence of 50% will also belong to the required functional association rule. It should be appreciated that the magnitude of the confidence threshold may be adjusted according to the requirements of the application scenario.
There is no order (e.g., { a, B } → { C }) between the respective application functions in the application function combinations corresponding to the candidate function association rules as shown in table 4, which indicates the probability or likelihood that function C will occur simultaneously in a session when application functions a and B are used in that session. However, the order of use of the application functions a and B cannot be known by this function association rule, that is, it cannot be clearly indicated whether the order of use in the session is a→b→c or b→a→c. Therefore, although the rule { a, B } → { C } can narrow the range of application functions for which there is a correlation, it cannot clearly specify the order of use between different application functions. However, in some business scenarios (e.g., function guide design scenarios), function association rules (e.g., { A→B } → { C }) corresponding to sequentially used application function combinations may be more reference value.
Specifically, in the process of screening the function association rules from among the plurality of candidate function association rules determined by the application function combination (e.g., a→b→c) having the order of use, reference may be made to the operation described with reference to block 440 in fig. 4. It should be noted that, the calculation formula of the confidence coefficient corresponding to such candidate function association rule is:
Z2=S(A→B→C)/S(A→B)
wherein Z2 represents the confidence level corresponding to the candidate function association rule { A-B } → { C }, S (A-B-C) represents the support level count corresponding to A-B-C, and S (A-B) represents the support level count corresponding to A-B.
In addition, only one of the first application function combination and the second application function combination corresponding to the candidate function association rule may include an application function combination that is used sequentially, for example { a→b } → { C, D } or { a, B → { c→d }, and the specific calculation formula and the details of the processing operation thereof may be referred to the above related description and will not be repeated herein.
In some application scenarios, the functional design of the business application may be optimized according to the functional association rules. For example, regarding the determined function association rule { a→b } → { c→d }, if it is detected that the sequentially used function a→b occurs in the session, an association optimization process for the sequentially used function c→d (for example, for the function combination c→d, guidance is performed from the function B). In addition, in the function association rule, the first application function combination includes an application function combination used sequentially, and the functions in the second application function combination do not have a sequence, for example, the function association rule { a→b } → { C, D }, so that when the function a→b used sequentially occurs in the session is monitored, it may be indicated that association optimization should be performed for the function C or D, and a function range associated with the application function combination may be determined.
FIG. 5 illustrates a flow chart of functional association optimization according to an embodiment of the present description.
As illustrated in flow 500 of fig. 5, reference may be made to the operations described above with reference to blocks 210 and 220, respectively, of fig. 2 for operations such as blocks 510 and 520. In block 530, the functional association rule is provided to the service application provider for the service application provider to perform functional association optimization, so that the service application provider timely finds problems in application function design, and can perform optimization operation on application function design of the service application in a targeted manner. Further, user complaint data or public opinion information, such as user complaint data which is aimed at a user who expects to use a binding card function but enters a 'card package' interface by mistake, can be comprehensively considered in the process of determining the function association rule, so that problems in application function design are found.
In one example of an embodiment of the present description, the function association optimization operation performed by the service application provider includes optimizing function association logic of the service application. Illustratively, if the current function association logic is A→B→D and the function association rule is { A→B } → { C }, the current function association logic may be modified from A→B→D to A→B→C.
In another example of an embodiment of the present specification, the function association optimization operation performed by the service application provider includes: when the user is detected to execute the application function operation, if the function association logic of the business application is inconsistent with the function association rule, guiding the application function operation of the user according to the function association rule. Illustratively, if the current function association logic is a→b→d and the function association rule is { a→b } → { C }, the user may be guided to operate the application function according to the function association rule { a→b → { C }, when the user is detected to operate the application function.
Regarding an example of guiding a user to operate an application function, on the one hand, a function display interface corresponding to a last application function in a first application function combination corresponding to a function association rule may be selected, and guiding prompt information for a second application function combination may be displayed on the function display interface. For example, for the function association rule { a→b } → { C }, when function a→b occurs in a user session, guidance prompt information for C may be displayed on the display interface of application function B, thereby prompting the guidance user to use application function C. On the other hand, when the first application function combination occurs in the monitored user session, the corresponding function in the second application function combination can be triggered to be executed. For example, for the function association rule { A→B } → { C }, during a session in which the user performs an application function operation, if function A→B occurs, execution of application function C is automatically triggered.
In one example of the embodiment of the present specification, if the first application function combinations corresponding to the plurality of function association rules are the same, for example, the first function association rule is { a→b } → { C } and the second function association rule is { a→b → { D }, the function association rule eventually suitable for being used may be determined by comparing the confidence degrees of the first function association rule and the second function association rule, and according to the result of the confidence degree comparison.
In some implementations, the user session data includes a user identification, and the functional association rule is a functional association rule corresponding to the user identification. That is, different functional association rules can be adopted for different users, so that personalized functional association optimization operation is realized. For example, for user M, the functional association rule { A→B } → { C } may be employed, while for user N, the functional association rule { A→B → { D } may be employed, thereby achieving a personalized functional association optimization effect.
Specifically, the confidence level corresponding to each functional association rule can be adjusted according to the occurrence frequency of different functional identifiers aiming at the user identifier, so that the personalized functional association rule aiming at the user identifier is determined. Illustratively, assume that there is 70% confidence level corresponding to the functional association rule { A→B } → { C }, and 80% confidence level corresponding to the functional association rule { A→B → { D }. At this time, if the frequency of occurrence of the application function C is high and the frequency of occurrence of the application function D is low in the user session data of the user M, the confidence corresponding to the function association rule { a→b } → { C } may rise and the confidence corresponding to the function association rule { a→b → { D } may be exceeded to become the function association rule adopted for the user M.
In some application scenarios, in the function association optimization operation, user groups can be determined according to the function association rule, and the function association optimization operation is performed aiming at the determined user group orientation, so that a specific user group can be recommended to use a new application function, and the oriented delivery and popularization of service functions are facilitated. Specifically, a user condition may be determined according to a function association rule, where the user condition is used to indicate that a first application function combination corresponding to the function association rule is included in a user session data set corresponding to a user identifier, and a second application function combination corresponding to the function association rule is not included in the user session data set. Further, a function delivery operation (e.g., delivering a second application function combination) may be performed on the user identification orientations that satisfy the delivery user condition. For example, if it is determined that the sequentially used application function combination a→b appears multiple times in the user session data set corresponding to the user P by analyzing the user session data of the user P for the function association rule { a→b } → { C }, but the application function identification C never appears in the user session data set, the function association rule { a→b → { C } may be used for the user P, thereby realizing the diversion of the application function C to the user P.
Fig. 6 shows a block diagram of a structure of an apparatus for determining a functional association rule between application functions of a service application (hereinafter also referred to as a functional association rule determining apparatus) in an example according to an embodiment of the present specification.
As shown in fig. 6, the functional association rule determining apparatus 600 includes a session data acquiring unit 610, a functional association rule determining unit 620, and a functional optimizing unit 630.
The session data acquisition unit 610 acquires a first number of user session data for a service application, each user session data including an application function identification of a respective application function used by the user in the user session. The operation of the session data acquisition unit 610 may refer to the operation of block 210 described above with reference to fig. 2.
The function association rule determining unit 620 determines a function association rule between application functions of the service application based on the application function identifier in the user session data, where the function association rule is used to indicate that an association relationship exists between two application function combinations. The operation of the functional association rule determination unit 620 may refer to the operation of block 220 described above with reference to fig. 2.
Further, the application function combinations include sequentially used application function combinations.
The function optimization unit 630 provides the function association rule to a service application provider for the service application provider to perform function association optimization. The operation of the function optimization unit 620 may refer to the operation of block 530 described above with reference to fig. 5.
Further, the functional association optimization includes: and optimizing the function association logic of the service application.
Further, the functional association optimization includes: when the user is detected to execute the application function operation, if the function association logic of the business application is inconsistent with the function association rule, guiding the application function operation of the user according to the function association rule.
It should be understood that the above-described structure of the functional association rule determining apparatus 600 is only for example, and that the functional association rule determining apparatus 600 may have only some of the above-described blocks 610-650, e.g., the qualification filtering unit 650 may not be provided within the functional association rule determining apparatus 600.
Fig. 7 shows a block diagram of a functional association rule determining unit in an example according to an embodiment of the present specification.
As shown in fig. 7, the functional association rule determining unit 620 includes an application functional combination set determining module 621, a candidate rule set determining module 622, a confidence determining module 623, an association rule determining module 624, and a frequent set determining module 625.
The application function combination set determination module 621 determines an application function combination set based on the application function identification in the user session data. The operation of the application function combination set determination module 621 may refer to the operation of block 310 described above with reference to fig. 3.
The candidate rule set determination module 622 determines a candidate function association rule set based on the determined application function combination set. The operation of candidate rule set determination module 622 may refer to the operation of block 320 described above with reference to fig. 3.
The confidence determining module 623 determines, for each candidate functional association rule, a confidence of the candidate functional association rule based on the number of occurrences of the first and second application functional combinations corresponding to the candidate functional association rule in the user session data and the number of occurrences of a third application functional combination in the user session data, the third application functional combination being composed of the first application functional combination and the second application functional combination. The operation of the confidence determination module 623 may refer to the operation of block 330 described above with reference to fig. 3.
The association rule determination module 624 determines the candidate function association rule with the determined confidence level greater than the first predetermined threshold as a function association rule between the business application functions of the business application. The operation of the association rule determination module 624 may refer to the operation of block 340 described above with reference to fig. 3.
The frequent set determination module 625 determines a frequent set of application function combinations from the set of application function combinations, each subset of application function combinations in the frequent set of application function combinations having a number of occurrences in the user session data greater than a second predetermined threshold. At this point, candidate rule set determination module 622 determines a candidate function association rule set based on the determined application function combination frequent set. The operation of the frequent set determination module 625 may refer to the operation of block 420 described above with reference to fig. 4.
It should be understood that the structure of the functional association rule determining unit 620 described above is only for example, and that the functional association rule determining unit 620 may have only some of the blocks 621-625 described above, e.g., the frequent set determining module 625 may not be provided within the functional association rule determining unit 620.
Embodiments of a method and apparatus for determining a function association rule between application functions of a business application according to embodiments of the present specification are described above with reference to fig. 1 to 7. The details mentioned in the above description of the method embodiments apply equally to the embodiments of the device of the present description embodiments. The above means for determining the functional association rules between application functions of the service application may be implemented in hardware, or in software or a combination of hardware and software.
Fig. 8 illustrates a hardware architecture diagram of a computing device 800 for determining functional association rules between application functions of a business application according to an embodiment of the present description. As shown in fig. 8, computing device 800 may include at least one processor 810, memory (e.g., non-volatile memory) 820, memory 830, and communication interface 840, and at least one processor 810, memory 820, memory 830, and communication interface 840 are connected together via bus 860. At least one processor 810 executes at least one computer-readable instruction (i.e., the elements described above as being implemented in software) stored or encoded in memory.
In one embodiment, computer-executable instructions are stored in memory that, when executed, cause the at least one processor 810 to: acquiring a first number of user session data for a service application, each user session data comprising an application function identification of each application function used by a user in the user session; and determining a function association rule between application functions of the service application based on the application function identification in the user session data, wherein the function association rule is used for indicating that an association relationship exists between two application function combinations.
It should be appreciated that the computer-executable instructions stored in memory 820, when executed, cause at least one processor 810 to perform the various operations and functions described above in connection with fig. 2-7 in various embodiments of the present specification.
In the present description embodiments, computing device 800 may include, but is not limited to: personal computers, server computers, workstations, desktop computers, laptop computers, notebook computers, mobile computing devices, smart phones, tablet computers, cellular phones, personal Digital Assistants (PDAs), handsets, messaging devices, wearable computing devices, consumer electronic devices, and the like.
According to one embodiment, a program product, such as a machine-readable medium, is provided. The machine-readable medium may have instructions (i.e., elements described above implemented in software) that, when executed by a machine, cause the machine to perform the various operations and functions described above in connection with fig. 1-8 in various embodiments of the specification. In particular, an apparatus may be provided with a readable storage medium having stored thereon software program code implementing the functions of any of the above embodiments, and having a computer or processor of the apparatus read out and execute instructions stored in the readable storage medium.
In this case, the program code itself read from the readable medium may implement the functions of any of the above-described embodiments, and thus the machine-readable code and the readable storage medium storing the machine-readable code form part of the present invention.
Examples of readable storage media include floppy disks, hard disks, magneto-optical disks, optical disks (e.g., CD-ROMs, CD-R, CD-RWs, DVD-ROMs, DVD-RAMs, DVD-RWs), magnetic tapes, nonvolatile memory cards, and ROMs. Alternatively, the program code may be downloaded from a server computer or cloud by a communications network.
It will be appreciated by those skilled in the art that various changes and modifications can be made to the embodiments disclosed above without departing from the spirit of the invention. Accordingly, the scope of the invention should be limited only by the attached claims.
It should be noted that not all steps or units in the above flowcharts and the structure diagrams of the devices are necessary, and some steps or units may be omitted according to actual needs. The order of execution of the steps is not fixed and may be determined as desired. The apparatus structures described in the above embodiments may be physical structures or logical structures, that is, some units may be implemented by the same physical entity, or some units may be implemented by multiple physical entities, or may be implemented jointly by some components in multiple independent devices.
In the above embodiments, the hardware units or modules may be implemented mechanically or electrically. For example, a hardware unit, module or processor may include permanently dedicated circuitry or logic (e.g., a dedicated processor, FPGA or ASIC) to perform the corresponding operations. The hardware unit or processor may also include programmable logic or circuitry (e.g., a general purpose processor or other programmable processor) that may be temporarily configured by software to perform the corresponding operations. The particular implementation (mechanical, or dedicated permanent, or temporarily set) may be determined based on cost and time considerations.
The detailed description set forth above in connection with the appended drawings describes exemplary embodiments, but does not represent all embodiments that may be implemented or fall within the scope of the claims. The term "exemplary" used throughout this specification means "serving as an example, instance, or illustration," and does not mean "preferred" or "advantageous over other embodiments. The detailed description includes specific details for the purpose of providing an understanding of the described technology. However, the techniques may be practiced without these specific details. In some instances, well-known structures and devices are shown in block diagram form in order to avoid obscuring the concepts of the described embodiments.
The previous description of the disclosure is provided to enable any person skilled in the art to make or use the disclosure. Various modifications to the disclosure will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other variations without departing from the scope of the disclosure. Thus, the disclosure is not limited to the examples and designs described herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (17)
1. A method for determining functional association rules between application functions of a business application, comprising:
acquiring a first number of user session data for a service application, each user session data comprising an application function identifier and a user identifier of each application function used by a user in the user session; and
determining a function association rule between application functions of the service application based on application function identifiers in the first number of user session data, wherein the function association rule is used for indicating that an association relationship exists between two application function combinations;
Wherein determining, based on the application function identifiers in the first number of user session data, a function association rule between application functions of the service application comprises:
determining an application function combination set based on the application function identifiers in the first number of user session data;
determining a set of candidate function association rules based on the determined set of application function combinations, wherein each candidate function association rule is used to represent that the first application function combination and the second application function combination are associated in the same session;
for each candidate function association rule, determining the confidence coefficient of the candidate function association rule based on the occurrence times of the first application function combination and the second application function combination corresponding to the candidate function association rule in the first number of user session data and the occurrence times of a third application function combination in the first number of user session data, wherein the third application function combination consists of the first application function combination and the second application function combination, and the confidence coefficient of the candidate function association rule is used for representing the probability that the second application function combination occurs when the first application function combination occurs in the session process; and
And determining the candidate function association rule with the determined confidence coefficient larger than a first preset threshold value as a function association rule between service application functions of the service application.
2. The method of claim 1, further comprising:
determining a frequent set of application function combinations from the set of application function combinations, each subset of application function combinations in the frequent set of application function combinations occurring more than a second predetermined threshold in the first number of user session data, and
based on the determined set of application function combinations, determining a set of candidate function association rules includes:
a candidate function association rule set is determined based on the determined application function combination frequent set.
3. The method of claim 1, wherein the application function combination comprises a sequentially used application function combination.
4. The method of claim 1, wherein the first application function combination comprises a sequentially used application function combination.
5. The method of claim 1, further comprising:
and providing the functional association rule for a service application provider so as to enable the service application provider to perform functional association optimization.
6. The method of claim 5, wherein the functional association optimization comprises:
And optimizing the function association logic of the service application.
7. The method of claim 5, wherein the functional association optimization comprises:
when the user is detected to execute the application function operation, if the function association logic of the business application is inconsistent with the function association rule, guiding the application function operation of the user according to the function association rule.
8. The method of claim 7, wherein the functional association rule is a functional association rule corresponding to the user identification.
9. An apparatus for determining functional association rules between application functions of a business application, comprising:
a session data acquisition unit that acquires a first number of user session data for a service application, each user session data including an application function identifier and a user identifier of each application function used by a user in the user session;
a function association rule determining unit, configured to determine a function association rule between application functions of the service application based on application function identifiers in the first number of user session data, where the function association rule is used to indicate that an association relationship exists between two application function combinations;
Wherein the functional association rule determining unit includes:
an application function combination set determining module that determines an application function combination set based on application function identifiers in the first number of user session data;
a candidate rule set determining module that determines a candidate function association rule set based on the determined application function combination set;
the confidence degree determining module determines the confidence degree of each candidate function association rule based on the occurrence times of the first application function combination and the second application function combination corresponding to the candidate function association rule in the first number of user session data and the occurrence times of the third application function combination in the first number of user session data, wherein the third application function combination consists of the first application function combination and the second application function combination;
and the association rule determining module is used for determining the candidate function association rule with the determined confidence coefficient larger than a first preset threshold value as the function association rule between the service application functions of the service application.
10. The apparatus of claim 9, wherein the functional association rule determination unit further comprises a frequent set determination module,
Wherein the frequent set determination module determines an application function combination frequent set from the application function combination set, the number of occurrences of each application function combination subset in the first number of user session data being greater than a second predetermined threshold, and
the candidate rule set determination module determines a candidate function association rule set based on the determined application function combination frequent set.
11. The apparatus of claim 9, wherein the application function combination comprises a sequentially used application function combination.
12. The apparatus of claim 9, wherein the first application function combination comprises a sequentially used application function combination.
13. The apparatus of claim 9, further comprising:
and the function optimization unit is used for providing the function association rule for a service application provider so as to enable the service application provider to perform function association optimization.
14. The apparatus of claim 13, wherein the functional association optimization comprises:
and optimizing the function association logic of the service application.
15. The apparatus of claim 13, wherein the functional association optimization comprises:
when the user is detected to execute the application function operation, if the function association logic of the business application is inconsistent with the function association rule, guiding the application function operation of the user according to the function association rule.
16. A computing device, comprising:
at least one processor; and
a memory storing instructions that, when executed by the at least one processor, cause the at least one processor to perform the method of any of claims 1 to 8.
17. A machine-readable storage medium storing executable instructions that when executed cause the machine to perform the method of any one of claims 1 to 8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010103622.2A CN111291093B (en) | 2020-02-20 | 2020-02-20 | Method and device for determining functional association rule of service application |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010103622.2A CN111291093B (en) | 2020-02-20 | 2020-02-20 | Method and device for determining functional association rule of service application |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111291093A CN111291093A (en) | 2020-06-16 |
CN111291093B true CN111291093B (en) | 2023-08-08 |
Family
ID=71023229
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010103622.2A Active CN111291093B (en) | 2020-02-20 | 2020-02-20 | Method and device for determining functional association rule of service application |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111291093B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113420240A (en) * | 2021-07-02 | 2021-09-21 | 广州虎牙科技有限公司 | User behavior analysis method and device, electronic equipment and storage medium |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106843723A (en) * | 2016-12-29 | 2017-06-13 | 努比亚技术有限公司 | A kind of application program associates application method and mobile terminal |
CN107943946A (en) * | 2017-11-24 | 2018-04-20 | 重庆科技学院 | Relevance method for digging between test item bank knowledge point based on Apriori algorithm |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7979881B1 (en) * | 2000-03-30 | 2011-07-12 | Microsoft Corporation | System and method for identifying audio/visual programs to be recorded |
EP2537312B1 (en) * | 2010-02-16 | 2013-12-25 | Telefonaktiebolaget L M Ericsson (PUBL) | Facilitating a communication session |
US9858526B2 (en) * | 2013-03-01 | 2018-01-02 | Exelate, Inc. | Method and system using association rules to form custom lists of cookies |
US10885047B2 (en) * | 2016-07-01 | 2021-01-05 | Oracle International Corporation | System and method providing association rule aggregates |
-
2020
- 2020-02-20 CN CN202010103622.2A patent/CN111291093B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106843723A (en) * | 2016-12-29 | 2017-06-13 | 努比亚技术有限公司 | A kind of application program associates application method and mobile terminal |
CN107943946A (en) * | 2017-11-24 | 2018-04-20 | 重庆科技学院 | Relevance method for digging between test item bank knowledge point based on Apriori algorithm |
Also Published As
Publication number | Publication date |
---|---|
CN111291093A (en) | 2020-06-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109035013B (en) | Apparatus and method for detecting abnormal financial transaction and computer readable storage medium | |
US9619758B2 (en) | Method and apparatus for labeling training samples | |
CN109344326B (en) | Social circle mining method and device | |
WO2016155493A1 (en) | Data processing method and apparatus | |
EP3358474B1 (en) | Route search method, device and apparatus, and non-volatile computer storage medium | |
CN110766040B (en) | Method and device for risk clustering of transaction risk data | |
US9584589B2 (en) | Friend recommendation method, apparatus and storage medium | |
EP3582127A1 (en) | Feature information-based user authentication method and device | |
CN108829650B (en) | Card number generation method, device, server and storage medium | |
EP3361704A1 (en) | User data sharing method and device | |
CN111291093B (en) | Method and device for determining functional association rule of service application | |
US11412063B2 (en) | Method and apparatus for setting mobile device identifier | |
CN109168138A (en) | The recognition methods for the number of changing, device and equipment in net | |
CN106777285B (en) | Method and device for clustering labels of user communication consumption data | |
CN106658444A (en) | Short message channel provider selection method and terminal | |
CN105243131B (en) | Path query method and device | |
KR20170132305A (en) | Data processing method and apparatus | |
CN110825717B (en) | Data normalization method, device and medium for identity recognition | |
CN107784363B (en) | Data processing method, device and system | |
CN105160026B (en) | Path query method and device | |
CN109919197B (en) | Random forest model training method and device | |
CN109561406B (en) | SIM card selection method, device, system, electronic equipment and medium | |
JP6774917B2 (en) | Programs, devices and methods for estimating entrainment pressure within a group for a given behavior | |
CN111832034B (en) | Multiparty data fusion method and device | |
CN106663155B (en) | User key identification system, apparatus used therefor, and method of operating the apparatus |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |