User behavior tagging methods and devices, business metric acquisition methods and devices

Abstract

This application discloses a user behavior marking method, apparatus, and service indicator acquisition method and apparatus, belonging to the field of communication technology. The user behavior marking method includes: collecting device service records and package service records of a first user within a preset time period from a communication service system; identifying a first user matching a first preset behavior based on the device service records, and setting a mark value corresponding to the matched first preset behavior for the identified first user; and identifying a first user matching a second preset behavior based on the package service records, and setting a mark value corresponding to the matched second preset behavior for the identified first user. This method marks abnormal user behavior based on the user's service records. The marking results reflect whether the user has preset abnormal behavior and what kind of preset abnormal behavior exists, providing effective data support for subsequently eliminating interference from abnormal behavior records in calculating user service indicator values ​​based on the marking results.

Description

Technical Field

[0001] This application relates to the field of communication technology, and in particular to user behavior marking methods, apparatus, service indicator acquisition methods, apparatus, electronic devices, and computer-readable storage media. Background Technology

[0002] In the telecommunications field, to provide users with more comprehensive and tailored services, telecommunications companies offer a range of service plans based on local population size, household structure, and industry characteristics. For example, through the telecommunications service system, various broadband packages, voice packages, and preferential policies are offered to different user groups. Accurately calculating the business value that service plans bring to the telecommunications service system provides service providers with fundamental data support for improving service content and evaluating business status. Currently, methods for calculating business metrics (such as user revenue increase from telecommunications services) for each user in the telecommunications service system typically include manual statistics and report calculations. However, for massive amounts of business data, manual statistics are not only costly but also inefficient. Report calculations, on the other hand, cannot distinguish the impact of user behavior data on the calculation results, leading to inaccurate business metrics.

[0003] It is evident that the existing methods for obtaining business metrics still need improvement. Summary of the Invention

[0004] This application provides a user behavior marking method, apparatus, business indicator acquisition method, apparatus, electronic device, and computer-readable storage medium, which can identify and mark abnormal user behavior, and further correct user business indicators based on the marking results, thereby helping to improve the accuracy of obtaining user business indicators.

[0005] In a first aspect, embodiments of this application disclose a user behavior tagging method, the method comprising:

[0006] The system collects the service records of the first user within a preset time period from the communication service system, wherein the service records include: device service records and package service records;

[0007] Based on the device service records, identify the first user that matches the first preset behavior, and set a flag value corresponding to the first preset behavior for the identified first user;

[0008] Based on the package service records, identify the first user who matches the second preset behavior, and set a flag value for the identified first user that corresponds to the matched second preset behavior.

[0009] Secondly, embodiments of this application disclose a user behavior tagging device, the device comprising:

[0010] The service record collection module is used to collect the service records of the first user in the communication service system within a preset time period, wherein the service records include: device service records and package service records;

[0011] The first tagging module is used to identify the first user matching the first preset behavior based on the device service records, and to set a tag value corresponding to the first preset behavior for the identified first user.

[0012] The second marking module is used to identify the first user matching the second preset behavior based on the package service record, and to set a marking value for the identified first user corresponding to the matching second preset behavior.

[0013] Thirdly, embodiments of this application disclose a method for obtaining business metrics, the method comprising:

[0014] Based on the first user's business records within the communication business system and the business object information table of the communication business system, the initial business indicator value of the first user is obtained.

[0015] The user behavior tagging method described in the embodiments of this application is used to tag the first user to obtain the tagging result of the first user;

[0016] The initial business indicator value is corrected based on the marking result to obtain the business indicator value of the first user.

[0017] Fourthly, embodiments of this application disclose a business indicator acquisition device, the device comprising:

[0018] The initial business indicator value acquisition module is used to acquire the initial business indicator value of the first user based on the business records of the first user in the communication business system and the business object information table of the communication business system.

[0019] The user behavior tagging module is used to tag the first user using the user behavior tagging method described in the embodiments of this application, and obtain the tagging result of the first user.

[0020] The business indicator value correction module is used to correct the initial business indicator value based on the marking result to obtain the business indicator value of the first user.

[0021] Fifthly, embodiments of this application also disclose an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the user behavior tagging method or business indicator acquisition method described in embodiments of this application.

[0022] Sixthly, embodiments of this application disclose a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, performs the steps of the user behavior tagging method or business indicator acquisition method disclosed in embodiments of this application.

[0023] The user behavior tagging disclosed in this application involves collecting the service records of a first user within a preset time period from a communication service system. These service records include device service records and package service records. Then, based on the device service records, the first user matching a first preset behavior is identified, and a tag value corresponding to the matched first preset behavior is set for the identified first user. Furthermore, based on the package service records, the first user matching a second preset behavior is identified, and a tag value corresponding to the matched second preset behavior is set for the identified first user. This achieves the identification of whether a first user exhibits a preset abnormal behavior, and what type of preset abnormal behavior exists, based on the tagging results. This provides effective data support for subsequently correcting the first user's initial service indicator values ​​based on the user behavior tagging results, thereby effectively eliminating the interference of abnormal behavior records on the calculation of user service indicator values ​​and improving the accuracy of obtaining the first user's service indicator values.

[0024] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0025] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0026] Figure 1 This is a flowchart of the user behavior tagging method disclosed in the embodiments of this application;

[0027] Figure 2This is a schematic diagram of the assembly and disassembly behavior marking process disclosed in the embodiments of this application;

[0028] Figure 3 This is a schematic diagram of the flowchart for marking the rising and falling behavior disclosed in the embodiments of this application;

[0029] Figure 4 This is a flowchart of the business indicator acquisition method disclosed in the embodiments of this application;

[0030] Figure 5 This is one of the schematic diagrams of the object index query process disclosed in the embodiments of this application;

[0031] Figure 6 This is the second schematic diagram of the object index query process disclosed in the embodiments of this application;

[0032] Figure 7 This is a schematic diagram of the user behavior tagging device disclosed in an embodiment of this application;

[0033] Figure 8 This is a schematic diagram of the business indicator acquisition device disclosed in the embodiments of this application;

[0034] Figure 9 A block diagram schematically illustrates an electronic device for performing the method according to this application; and

[0035] Figure 10 A storage unit for holding or carrying program code that implements the method according to this application is schematically shown. Detailed Implementation

[0036] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0037] Reference Figure 1 The user behavior tagging method disclosed in this application includes steps 110 to 130.

[0038] Step 110: Collect the service records of the first user in the communication service system within a preset time period, wherein the service records include: device service records and package service records.

[0039] The business record refers to the business data stored by the communication service system for each user (i.e., the first user) who has conducted business with the communication service provider. The business record includes, but is not limited to: user identifier, corresponding superior user (i.e., the second user), the business object and related information, processing time, and business address. The related information may include, for example, package type, package billing type, validity period, integration type, discount type, preferential identifier, and business object priority. In some embodiments, certain business objects require real-name registration; accordingly, the business record also includes the first user's identity information.

[0040] In the embodiments of this application, the user information stored in the business records is information authorized for use by the user.

[0041] The business objects mentioned include, but are not limited to: the packages subscribed by the first user, and the preferential items given to the first user by the service provider.

[0042] The preset time period can be set according to specific needs, for example, the preset time period can be the most recent 90 days.

[0043] The equipment service records include, but are not limited to, one or more of the following: installation, dismantling, and relocation. The package service records include, but are not limited to, one or more of the following: package addition, package cancellation, and package change records.

[0044] In the embodiments of this application, based on the business records collected in this step, the preset abnormal behaviors of the first user are identified and marked. The preset abnormal behaviors include: a first preset behavior and a second preset behavior. The first preset behavior further includes: user reorganization behavior and installation / disassembly behavior. The second preset behavior further includes: package reorganization behavior and upgrade / downgrade behavior.

[0045] The marking methods for the first and second preset behaviors are described below.

[0046] Step 120: Based on the device service record, identify the first user that matches the first preset behavior, and set a flag value corresponding to the first user and the matched first preset behavior.

[0047] As mentioned above, the device service records include: installation, disassembly, and relocation records. Optionally, the first preset behavior includes, but is not limited to, user reconfiguration behavior and one-to-one installation / disassembly behavior. In specific implementation, the first user may exhibit one, two, or none of the above-mentioned first preset behaviors. In specific implementation, it is necessary to identify which first user exhibits the above-mentioned first preset behavior and what type of first preset behavior based on the installation, disassembly, and relocation records of the first user in the communication service system within a preset time period, and to set a flag value for the first user exhibiting the first preset behavior based on the identification results. If the first user is identified to have user reconfiguration behavior, a flag value matching the user reconfiguration behavior is set for the first user (e.g., denoted as "first flag value"). If the first user exhibits one-to-one installation / disassembly behavior, a flag value matching the one-to-one installation / disassembly behavior is set for the first user (e.g., denoted as "second flag value"). That is, if a first user does not exhibit any of the above-mentioned first preset behaviors, no corresponding flag value is set; if a first user exhibits both of the above-mentioned first preset behaviors, two flag values ​​are set for the first user.

[0048] The identification method for each of the first preset behaviors is further explained below.

[0049] (a) Installation and dismantling behavior

[0050] Optionally, the step of identifying the first user matching the first preset behavior based on the device service records, and setting a tag value corresponding to the first preset behavior for the identified first user, includes: performing a second user affiliation judgment, identity information similarity judgment, and service address similarity judgment based on the first user's installation, disassembly, and relocation records to obtain a first judgment result; in response to the first judgment result indicating that at least two first users belong to the same second user or are associated with the same identity information, and the at least two first users have at least two records with the same service address but different service types, setting a tag value corresponding to the installation and disassembly behavior for the at least two first users.

[0051] The following is combined with Figure 2 The process for identifying the installation and disassembly behavior is explained.

[0052] In the embodiments of this application, each second user may be associated with one or more first users. In an optional scenario, the first user may be the end user of the communication service, such as an internet user or a telephone service user, while the second user may be a branch of the telecommunications company that handles the business for the first user.

[0053] After collecting installation, removal, and relocation records from the communication service system within the last 90 days in the aforementioned steps, second user attribution determination, identity information similarity determination, and service address similarity determination are performed based on the collected records. Examples of the implementation methods for each determination operation are given below.

[0054] In some embodiments of this application, based on the installation, dismantling, and relocation records of the first user, the second user's affiliation is determined, the identity information is similar, and the business address is similar, to obtain a first determination result, including the following four determination methods.

[0055] The first method involves comparing the similarity of the service address in each installation record with that in each dismantling record, determining whether the user identifier of the corresponding second user is the same, and determining whether the identity information of the corresponding first user is the same.

[0056] For example, for each installation record, the business address (such as the installation address) in that installation record is completely compared with the business address (such as the dismantling address) in each dismantling record to calculate the similarity between the current installation address and the dismantling address. Specifically, the business address data can be compared sequentially, starting from city, then administrative district, then street, and finally house number, to obtain the field similarity of each field. Then, the field similarities are weighted and summed using preset weights for each field to obtain the similarity between the two business addresses.

[0057] In other embodiments of this application, other methods may be used to determine the similarity between two service addresses, which will not be listed one by one in the embodiments of this application.

[0058] For example, for each installation record, the user identifier of the second user in the installation record is compared with the user identifier of the second user in each dismantling record to determine whether the second users corresponding to the two business records are the same.

[0059] For example, for each installation record, the identity information (such as ID number) of the first user in the installation record is compared with the identity information (such as ID number) of the first user in each dismantling record to determine whether the first user corresponding to the two business records is the same.

[0060] For each installation record, after comparing the business address, the user identifier of the second user, and the identity information of the first user with each dismantling record, the similarity of the business address between any installation record and a dismantling record can be obtained, as well as the first user belonging to each second user (i.e., the first user with the same identity information).

[0061] The second method involves comparing the similarity of the service addresses before and after the relocation for each relocation record, determining whether the user identifier of the corresponding second user is the same, and determining whether the identity information of the corresponding first user is the same.

[0062] For example, for each relocation record, a complete comparison is performed between the service address before and after the relocation in that record to calculate the similarity of the service addresses before and after the relocation for the current relocation record. The method for comparing service addresses before and after the relocation is the same as the comparison method for installation and removal addresses described earlier, and will not be repeated here.

[0063] For example, for each relocation record, the user identifier of the second user before the relocation is compared with the user identifier of the second user after the relocation to determine whether the second user is the same before and after the relocation.

[0064] For example, for each relocation record, the identity information of the first user before the relocation is compared with the identity information of the first user after the relocation to determine whether the first user is the same before and after the relocation.

[0065] For each relocation record, after comparing the service address, the user ID of the second user, and the identity information of the first user, we can obtain any relocation record and the similarity of the service addresses before and after, as well as the first user belonging to each second user (i.e., the first user with the same identity information).

[0066] The third method involves comparing the similarity between the service address of each installation record and the post-migration service address of each relocation record, determining whether the user identifier of the second user is the same, and determining whether the identity information of the first user is the same.

[0067] For example, for each installation record, the service address (i.e., the installation address) in the installation record is completely compared with the service address after relocation in each relocation record to calculate the similarity between the installation address and the service address after relocation in the current installation record. The method for comparing the installation address and the service address after relocation is the same as the comparison method for the installation address and the disconnection address mentioned above, and will not be repeated here.

[0068] For example, for each installation record, the user identifier of the second user before the relocation is compared with the user identifier of the second user after the relocation to determine whether the second user is the same before and after the relocation.

[0069] For example, for each installation record, the identity information of the first user in the installation record is compared with the identity information of the first user after the relocation in each relocation record to determine whether the installation record and the relocation record belong to the same first user.

[0070] For each installation record and relocation record, after comparing the service address, the user ID of the second user, and the identity information of the first user, we can obtain the similarity of the service address after relocation for any installation record and relocation record, as well as the first user belonging to each second user (i.e., the first user with the same identity information).

[0071] The fourth method involves comparing the similarity between the service address of each disconnection record and the service address after relocation of each relocation record, determining whether the user identifier of the corresponding second user is the same, and determining whether the identity information of the corresponding first user is the same.

[0072] For example, for each disconnection record, the service address in the disconnection record is completely compared with the service address after relocation in each relocation record to calculate the similarity between the disconnection address and the service address after relocation in the current disconnection record. The method for comparing the disconnection address and the service address after relocation is the same as the comparison method for installation address and disconnection address mentioned above, and will not be repeated here.

[0073] For example, for each dismantling record, the user identifier of the second user in the dismantling record is compared with the user identifier of the second user after the relocation. If the second user in the dismantling record and the relocation record are the same, then the dismantling record and the relocation record belong to the same second user.

[0074] For example, for each dismantling record, the identity information of the first user in the dismantling record is compared with the identity information of the first user after the relocation in each relocation record to determine whether the dismantling record and the relocation record belong to the same first user.

[0075] For each disconnection and relocation record, after comparing the service address, the user ID of the second user, and the identity information of the first user, we can obtain the similarity of the service address after relocation for any disconnection and relocation record, as well as the first user belonging to each second user (i.e., the first user with the same identity information).

[0076] By using the four methods described above, a comprehensive comparison of service addresses for different service types and the addresses before and after relocation services can be made from different perspectives. This allows us to obtain the similarity of service addresses for service records that may involve abnormal services, as well as the service records belonging to each first user and each first user belonging to each second service. Then, for each second user, the aforementioned service records of each first user belonging to that second user are traversed. All groups of service records with a similarity greater than or equal to a preset similarity threshold are found. Further, it is determined whether one or more groups of service records found include a group of service records belonging to different service types. If so, it can be assumed that the first user has engaged in installation and dismantling behavior, and a flag value corresponding to the installation and dismantling behavior is set for the first user, such as setting a "second flag value" for the first user; otherwise, it is assumed that the user has not engaged in installation and dismantling behavior.

[0077] For example, if a first user under a second user installs a service at address 1 and then removes the service at address 1 within 90 days, it can be considered that the first user has engaged in both installation and removal. As another example, if a first user under a second user installs a service at address 1, moves the service to address 2, and then removes the service at address 2, it can also be considered that the first user has engaged in both installation and removal.

[0078] In some embodiments of this application, after setting the "second flag value" for the first user, the first user can also be set with a first-to-disassemble-then-install flag or a first-to-install-then-disassemble flag according to the order of completion time in the installation record, disassembly record, and relocation record, for downstream applications to perform data analysis.

[0079] (ii) User Reorganization Behavior

[0080] Optionally, the first preset behavior includes: identifying the first user matching the first preset behavior based on the device service records, and setting a flag value corresponding to the first preset behavior for the identified first user, including: performing a second user affiliation judgment based on the first user's installation, disassembly, and relocation records, identifying the first user matching the user reorganization behavior, and setting a flag value corresponding to the user reorganization behavior for the identified first user.

[0081] For example, when judging the installation, disconnection, and relocation records in the communication service system within the last 90 days, if a first user has at least two records of different service types within the last 90 days, then the user identifier of the second user corresponding to the at least two different service types is further obtained, and then the second user's affiliation is determined. For example, it is determined whether the user identifiers of the second users corresponding to the installation and disconnection records in the at least two different service types are the same. If they are different, it is considered that the first user has engaged in user reorganization behavior, and a flag value corresponding to the user reorganization behavior is set for the first user, such as setting a "first flag value" for the first user. Specifically, if a user (i.e., the first user) firstly installs a service under customer A within 90 days, then disconnects the service, and then installs a service under customer B, then the user is identified as engaging in user reorganization behavior. Here, "customer" refers to a higher-level user that includes multiple users.

[0082] Step 130: Based on the package service record, identify the first user that matches the second preset behavior, and set a flag value for the identified first user that corresponds to the matched second preset behavior.

[0083] In the specific implementation process, the first user may exhibit one, two, or none of the aforementioned second preset behaviors. During implementation, it is necessary to identify which first user exhibits the aforementioned second preset behavior and, if so, which type of behavior, based on the first user's package addition, cancellation, and change records within a preset time period in the communication service system. A flag value is then set for the first user exhibiting the second preset behavior based on the identification results. If the first user is identified to have package reorganization behavior, a flag value matching the package reorganization behavior is set for that first user (e.g., denoted as the "fourth flag value"). If the first user exhibits both an increase and a decrease behavior, a flag value matching the increase and decrease behavior is set for that first user (e.g., denoted as the "third flag value").

[0084] The following is combined with Figure 3 The process for identifying the installation and disassembly behavior is explained.

[0085] (III) One rise and one fall behavior

[0086] As mentioned above, the package service record includes one or more of the following records: package addition, package cancellation, and package change. Optionally, the second preset behavior includes an upgrade and a downgrade behavior. The step of identifying the first user matching the second preset behavior based on the package service record and setting a flag value corresponding to the matched second preset behavior for the identified first user includes: obtaining the change value of the first user's package value based on one or more of the package addition, package cancellation, and package change records; determining the package change type matched by the first user's package service record based on the comparison result of the change value and a preset change threshold, wherein the package change type includes any one or more of the following: upgrade type, lateral move type, and downgrade type; in response to the existence of at least one package service record matching the upgrade type and at least one package service record matching the downgrade type in the first user's package service record at the same time, a flag value corresponding to the upgrade and downgrade behavior is set for the first user.

[0087] After collecting data on new, canceled, and changed service packages from the communication service system within the past 90 days in the aforementioned steps, the change in package value for each first user is calculated based on the collected package-related records. Target upgrade and target downgrade records are then determined based on the change in package value. Finally, the number of target upgrade and downgrade records is used to determine if the first user has engaged in both upgrade and downgrade behavior. Examples of the implementation methods for each determination operation are given below.

[0088] In some optional embodiments, for each first user, the change in package value for the relevant records of the package change for that first user is calculated separately. In the actual calculation of the change in package value, for packages of different service types, the package value before and after the change can be calculated separately according to different package value calculation methods.

[0089] For example, for bundled products, the discounted value of the primary Tianyi Card (i.e., the account corresponding to the bundled product) is first calculated, and then it is further determined whether the supplementary card is free. If the supplementary card is not free, the discounted values ​​of the primary and supplementary cards and the value of the value-added package are calculated together, and the values ​​of other products are recorded as 0 to obtain the current month's package value for the first user. If the supplementary card is free, the discounted value of the primary Tianyi Card is directly used as the current month's package value for the first user. Then, based on the calculated current month's package value for the first user, the package value for the first user in the previous month, and the package value in the month before last, the difference between the current month's package value and the package values ​​of the previous month and / or the month before last is calculated as the package value change value for the first user's package-related records where a package change has occurred.

[0090] For example, for non-integrated products, for each first user, the value of all individual products and value-added packages for the current month can be calculated to obtain the current month's package value for that first user. Then, based on the calculated current month's package value for that first user, the package value for the previous month, and the package value for the month before last, the difference between the current month's package value and the package values ​​for the previous month and / or the month before last is calculated as the package value change value for the first user's package-related records where a package change has occurred.

[0091] In some alternative embodiments, other methods can be used to calculate the difference between the change in the current monthly package value of the first user and the change in the package value of the previous month and / or the month before last, based on the records of new packages, canceled packages, and changed packages within a preset time period, in order to obtain the change in package value. This application does not limit the method for calculating the monthly package value of the first user, nor does it limit the reference method for the package value of the previous month or the month before last when calculating the change in package value. Those skilled in the art can also use other methods to calculate the monthly package value of the first user and the change in package value.

[0092] Furthermore, if the change value is greater than the first preset change threshold, the service package record can be determined to be of the upgrade type; if the change value is less than the second preset change threshold, the service package record can be determined to be of the downgrade type; if the change value is less than or equal to the first preset change threshold and greater than or equal to the second preset change threshold, the service package record can be determined to be of the same type. The first preset change threshold is greater than the second preset change threshold, and the specific values ​​of the first preset change threshold and the second preset change threshold are set according to the service requirements.

[0093] If a first user's service plan records contain one or more upgrade-type and one or more downgrade-type service plan records simultaneously, then the first user is considered to have engaged in upgrade-downgrade behavior, and a flag value corresponding to the upgrade-downgrade behavior is set for the first user, such as a "third flag value". If a first user's service plan records do not contain both upgrade-type and downgrade-type service plan records simultaneously, then the first user is considered not to have engaged in upgrade-downgrade behavior.

[0094] For a specific example, if a user subscribes to a new package at a price of 'a' yuan, and in the second month, subscribes to a package change at a price of 'b' yuan, and in the third month, subscribes to a package change at a price of 'c' yuan, where b > a > c, and 'ba' is greater than a first preset change threshold (e.g., 10 yuan), and 'cb' is less than a second preset change threshold (e.g., -10 yuan), then the user is considered to have engaged in a change behavior of adding a new package and adjusting the price, and a flag value corresponding to the change behavior is set for the user.

[0095] Using the above method, a first user with an increase and decrease behavior in the communication service system can be identified, and a tag value corresponding to the increase and decrease behavior, such as a "third tag value", can be set for the identified first user.

[0096] (iv) Package Restructuring

[0097] As mentioned above, the package service record includes one or more of the following records: package addition, package cancellation, and package change. Optionally, the second preset behavior includes: package reorganization behavior. The step of identifying the first user matching the second preset behavior based on the package service record and setting a flag value corresponding to the matched second preset behavior for the identified first user includes: comparing and judging the second user associated with the same package and the packages associated with the same first user based on one or more of the package addition, package cancellation, and package change records to obtain a second judgment result; in response to the second judgment result indicating that the target first user is associated with different packages before and after the package change or that the target first user associated with the same package is associated with different second users before and after the package change, then setting a flag value corresponding to the package reorganization behavior for the target first user.

[0098] After collecting data on new, canceled, and changed service packages from the communication service system within the last 90 days, the system further determines whether the primary user's affiliation within the package has changed, and whether the primary user within the package has changed. For example, for each package change record, the system obtains the user identifier of the primary user before and after the change, and compares whether the user identifiers are the same. If they are different, and the primary user has not canceled the package, then the primary user is considered to have undergone package restructuring. If they are the same, the system further determines whether the primary user's user identifier belongs to a different secondary user before and after the service time of the package change record. If the primary user's user identifier belongs to a different secondary user before and after the service time of the package change record, then the primary user is considered to have undergone package restructuring; otherwise, the primary user is considered not to have undergone package restructuring. For the primary user who has undergone package restructuring, a flag value corresponding to the package restructuring behavior is set for the target primary user, such as a "fourth flag value".

[0099] In some embodiments of this application, other methods may be used to determine whether the first user has engaged in package reorganization behavior, which will not be listed one by one in the embodiments of this application.

[0100] After determining whether the first user exhibits one or more of the aforementioned behaviors based on device service records and package change records, each first user may be assigned one or more of the aforementioned flag values, or may not be assigned any flag value, depending on the determination result. Each flag value indicates that the first user has exhibited corresponding abnormal behavior.

[0101] The above describes a specific implementation method for marking abnormal behavior of a first user based on service records in a communication service system. Those skilled in the art should understand that steps 120 and 130 are two steps executed in parallel, and their execution order can be interchanged. This application does not restrict which preset behavior is marked first.

[0102] Optionally, in some embodiments of this application, the method further includes: outputting the marking result of a first preset behavior, and / or, outputting the marking result of a second preset behavior. For example, outputting description information for all first users marked as a "disassemble and reassemble" behavior, the description information including but not limited to: service address, user identifier, behavior type, disassembly time, and reassembly time information. Another example is outputting description information for all first users marked as a "raise and lower" behavior, the description information including but not limited to: service address, user identifier, behavior type, package change time, number of changes, package value difference, and one or more other information. Yet another example is outputting description information for user reassembly behavior, the description information including but not limited to: reassembly time, service address, user identifier of the first user, user identifier of the second user, and one or more other information.

[0103] In some embodiments of this application, the steps of the above method can be scheduled to run at regular intervals using a preset tool, thereby outputting the latest and more accurate marking results. The start time, frequency, and number of repeated runs for errors can all be customized. For example, two update frequencies can be defined: daily update and monthly archiving. The daily update start time is 9:00 AM daily, the monthly archiving time is 8:00 PM on the 7th of each month, and the number of repeated runs for errors is 10.

[0104] In summary, this application discloses a user behavior tagging method. It collects the service records of a first user within a preset time period from a communication service system. These service records include device service records and package service records. Then, based on the device service records, it identifies the first user matching a first preset behavior and sets a tag value corresponding to the matched first preset behavior for the identified first user. Furthermore, based on the package service records, it identifies the first user matching a second preset behavior and sets a tag value corresponding to the matched second preset behavior for the identified first user. This method identifies whether a first user exhibits a preset abnormal behavior and, if so, what type of preset abnormal behavior exists. This provides effective data support for subsequently correcting the first user's initial service indicator values ​​based on the user behavior tagging results. This effectively eliminates the interference of abnormal behavior records on the calculation of user service indicator values ​​and improves the accuracy of obtaining the first user's service indicator values.

[0105] Based on the above embodiments, referring to Figure 4 This application also discloses a method for obtaining business indicator values, the method including steps 410 to 430.

[0106] Step 410: Obtain the initial service indicator value of the first user based on the service record of the first user in the communication service system and the service object information table of the communication service system.

[0107] Optionally, the business object information table includes, but is not limited to, one or more of the following: a basic package configuration table, a current package instance table, and a historical package instance table for storing current package instance information of regular products; a group package tier table; and one or more special product information tables for storing product information of special products.

[0108] The conventional products may include, for example, communication service packages such as call plans, data plans, and broadband plans. The product information of the conventional products includes, but is not limited to, one or more of the following: package type, original service indicators, etc. The special products include, but are not limited to, non-mainstream products such as SDH (Synchronous Digital Hierarchy) circuits and MSTP (Multi-Service Transport Platform) circuits. The product information of the special products includes, but is not limited to, one or more of the following: product type, original service indicators, etc.

[0109] The basic package configuration table stores configuration information for mainstream packages, such as package identifiers, package types, and original service indicators. In some embodiments, the service provider pre-configures mainstream packages and stores them in the basic package configuration table, facilitating quick retrieval of the user's used package when querying package information. For non-mainstream conventional products, the communication service system uses one or more additional information tables for storage. For example, an in-use package instance table and a historical package instance table are used to store product information for special products currently in use and not currently in use in the communication service system, respectively. The group package tier table stores product information such as package identifiers and original service indicators for other types of conventional products.

[0110] By querying the aforementioned business object information table, the original value indicators of the business objects used by each first user can be obtained, as well as product information such as the priority, integration relationship, and billing type of each business object. Then, based on the above information, the initial business indicator value of each first user can be calculated.

[0111] In some embodiments of this application, obtaining the initial business indicator value of the first user based on the business records of the first user in the communication service system and the business object information table of the communication service system includes: obtaining the business records of the first user in the communication service system, wherein the business records include at least one business object in use; sequentially querying the business object information table according to a preset query order to obtain the object indicator values ​​corresponding to the at least one business object respectively; and performing a fusion calculation on the object indicator values ​​corresponding to the at least one business object of the first user according to a preset object indicator value calculation strategy to obtain the initial business indicator value of the first user.

[0112] First, the service records of each first user are retrieved from the communication service system. The communication service system uses the user identifier as an index to query one or more service records for a specific first user. These service records include, but are not limited to: installation records, disconnection records, relocation records, and package activation records, package cancellation records, package change records, and package expiration records. After obtaining the service records of each first user, each service record is parsed and synthesized to obtain the service records of each first user within a preset time period (e.g., the most recent 3 months). Furthermore, by parsing the service records of each first user within the preset time period, relevant product information such as product identifiers, product types, billing types, discount identifiers, and discount information for the services handled or used by each first user within the preset time period can be obtained.

[0113] Next, based on the product identifier in the business records of each first user within a preset time period, the business object information table in the communication business system can be queried to obtain the object indicator values ​​of each business object.

[0114] The following is combined with Figure 5 and Figure 6 The specific implementation methods for obtaining business objects are illustrated with examples.

[0115] In the embodiments of this application, Figure 5 and Figure 6 The business indicator query process shown is implemented through program code and then encapsulated for each query call.

[0116] like Figure 5As shown, the process begins by using product information related to user metrics such as product identifiers and discount types from the first user's business records as input to query the basic package configuration table. If an object metric value corresponding to one or more product information items is found in the basic package configuration table, that object metric value is read (e.g., querying the package price or discount price corresponding to the product identifier) ​​and used to calculate the user's initial business metric value. If no object metric values ​​corresponding to all input product identifiers, discount types, etc., are found in the basic package configuration table, the remaining inputs (e.g., remaining discount identifiers) are queried in the in-use package instance table. For example, the parameters of each field in the in-use package instance table are scanned to search for object metric values ​​that match the remaining inputs. The searched object metric values ​​are then used to calculate the user's initial business metric value. If, after querying the in-use package instance table, no corresponding object metric value is found for some inputs, the object metric values ​​are queried sequentially in the historical package instance table and the group package tier table, following the aforementioned method.

[0117] If, after querying the group's package tiers table, all product information related to user indicator values ​​such as product identifiers and discount identifiers has been found to have corresponding target indicator values, then the user's initial business indicator value is calculated based on the target indicator values ​​obtained from the aforementioned tables.

[0118] In some optional embodiments, the business handled by the first user may involve special products. In this case, it is necessary to further query the special product information table to obtain the object index value of the special product handled or used by the first user.

[0119] like Figure 6 As shown, by scanning the special product instance table and various extended tables of regular products in the communication service system, the object indicator values ​​of the special products handled or used by the first user can be queried. These scanned object indicator values ​​are then used to calculate the user's initial service indicator value. For example, these object indicator values ​​include, but are not limited to: monthly amount payable to the peer, local intra-regional monthly fee, local inter-regional monthly fee, local long-distance monthly fee, international monthly fee, international peer monthly fee, network usage monthly fee, etc. If no relevant monthly fee is found, the user's incurred fees for the current month are calculated and used as part of the product value to calculate the user's initial service indicator value.

[0120] Following the aforementioned method, for each first user, based on the first user's business records, the relevant product information tables of the communication business system are queried, and then the object indicator values ​​of different business objects, such as product price and preferential price, are obtained from each product information table.

[0121] Next, based on the object indicator values ​​of the relevant business objects in the business records of the first user read from each product information table, the initial business indicator value of the first user is calculated according to the preset object indicator value calculation strategy.

[0122] In some embodiments of this application, two different functions are encapsulated to calculate the initial business indicator values ​​for the first user. One function, based on the calculated object indicator values ​​for each business object (e.g., a service package) of the first user, determines the first user's main single-product package, integrated package, special subsidy, and general subsidy, along with their initial business indicator values, from all the first user's business objects according to the matching priority of each business object. The other function defines the main package, main subsidy, and their initial business indicator values ​​for other associated business objects within the determined integrated package.

[0123] Priority is a user-defined priority system for communication business systems, based on the product manager's understanding of all applicable discounts, discount meanings, business experience, and common sense. For example, if a broadband user subscribes to both a bundled 199 package and a 99 monthly package, according to the user's custom rules, the primary single-product package is the 199 package (because the monthly package is the fee for continued use after the bundled 199 package expires). A single-product package refers to the primary package for a single user, such as the aforementioned 99 monthly package. A bundled package refers to a package shared by several primary users under a secondary user, such as a bundled package that includes China Telecom and broadband products. These products share the bundled package, but each still has its own individual single-product package, with priority given to the bundled package's rates. Special subsidies refer to additional subsidies that can be added on top of existing discounts, such as 20% off for government and enterprise users. Ordinary subsidies refer to subsidies other than special subsidies, such as call charge subsidies and handset purchase subsidies.

[0124] The object indicator value calculation strategy is defined according to the specific business charging rules. For example, for a certain first user, the price of the main single product package after deducting various discounts can be used as the initial business indicator value for the first user.

[0125] For a detailed implementation of the method for calculating the initial business indicator value of the first user according to the object indicator value calculation strategy, please refer to the prior art, and it will not be repeated here.

[0126] The storage format and location of product information in the product information table within the communication service system are existing technologies and will not be elaborated here. The method for obtaining the first user's service records and the included data content are also existing technologies and will not be elaborated here.

[0127] This step calculates the initial service indicator value for each first user. As the calculation process described above shows, the initial service indicator value for a first user is calculated based on the records of the first user's activated and used service objects in the service log. For example, for a first user who activated an M-yuan package and enjoyed an N-yuan discount, the calculated initial service indicator value is MN. As another example, for a first user who activated an M-yuan package, enjoyed an N-yuan discount, then canceled the M-yuan package and reactivated a P-yuan package, the calculated initial service indicator value is P. The calculation result for the second scenario ignores the discount for that first user, leading to inaccurate calculation of the overall service indicator for the communication service system.

[0128] Step 420: Based on the service records of the communication service system within a preset time period, the user is tagged to obtain the tagging result of the user.

[0129] In the actual operation of a communication service system, there may be some abnormal operation records that interfere with the calculation of the overall service indicators of the communication service system. Therefore, it is necessary to identify whether the first user has any abnormal operations based on the first user's service records, and what type of abnormal operations they are. The user should be marked according to the identification results, so that the initial service indicator value of the user can be corrected based on the marked user in the future, thereby improving the accuracy of the user's service indicator value calculation.

[0130] Optionally, the user is tagged based on the service records of the communication service system within a preset time period to obtain the user's tagging result. This includes: collecting the service records of the communication service system within a preset time period, wherein the service records include: device service records and package service records; identifying the first user matching a first preset behavior based on the device service records, and setting a tag value corresponding to the first preset behavior for the identified first user; and identifying the first user matching a second preset behavior based on the package service records, and setting a tag value corresponding to the second preset behavior for the identified first user.

[0131] The specific implementation method for collecting the business records of the communication service system within a preset time period is as described in the previous embodiments, and will not be repeated here.

[0132] The specific implementation method for identifying the first user matching the first preset behavior based on the device service records and setting the flag value corresponding to the first preset behavior for the identified first user is as described in the previous embodiments, and will not be repeated here.

[0133] The specific implementation method for identifying the first user matching the second preset behavior based on the package service record and setting the flag value corresponding to the matched second preset behavior for the identified first user is as described in the previous embodiment, and will not be repeated here.

[0134] Step 430: Correct the initial business indicator value according to the marking result to obtain the business indicator value of the first user.

[0135] Next, for each first user, based on the tag value set for that first user in the aforementioned steps, the correction value for the initial business metrics is obtained, thereby obtaining the business metric value for that first user.

[0136] In some optional embodiments, the step of correcting the initial business indicator value based on the marking result to obtain the business indicator value of the first user includes: in response to the marking result including a marking value corresponding to an installation and dismantling behavior, obtaining a second business indicator correction value based on the business records of the first user corresponding to the installation and dismantling behavior; in response to the marking result including a marking value corresponding to an increase and decrease behavior, obtaining a first business indicator correction value based on the business records of the first user corresponding to the increase and decrease behavior; in response to the marking result including a marking value corresponding to a user restructuring behavior, obtaining a third business indicator correction value; in response to the marking result including a marking value corresponding to a package restructuring behavior, obtaining a fourth business indicator correction value; and correcting the initial business indicator value of the corresponding first user based on one or more of the obtained first business indicator correction value, second business indicator correction value, third business indicator correction value, and fourth business indicator correction value to obtain the business indicator value of the first user.

[0137] Optionally, the second business indicator correction value includes: the commission of the superior user of the first user associated with the package business record corresponding to the one-up-one-down behavior, the subsidy, discount, etc. of the package business record corresponding to the one-up-one-down behavior.

[0138] Optionally, the first business indicator correction value includes one or more of the following: commissions of the superior user of the first user associated with the installation and relocation record corresponding to the installation and relocation behavior, subsidies and discounts of the first user associated with the installation and relocation record corresponding to the installation and relocation behavior.

[0139] For example, if a first user is assigned a flag value corresponding to an installation and dismantling action and a flag value corresponding to an upgrade and downgrade action, then the commission corresponding to the installation record of the first user performing the installation and dismantling action is used as the first business indicator correction value, and the commission corresponding to the package addition record or package change record of the first user performing the upgrade and downgrade action is used as the second business indicator correction value. Then, the first business indicator correction value and the second business indicator correction value are subtracted from the first user's initial business indicator value, and the result is used as the first user's business indicator value.

[0140] For example, if a first user is assigned a flag value corresponding to an installation and removal action, then the commission corresponding to the installation record of the first user engaging in this installation and removal action is used as the first business indicator correction value. This first business indicator correction value is then subtracted from the first user's initial business indicator value, and the result is used as the first user's business indicator value. Specifically, a second user initially only had first user A with an initial business indicator value of 100. Within three months, this second user added a first user B, also with a value of 100, and received a new installation commission of 30. The business address similarity between first user A and first user B is greater than a preset similarity threshold (e.g., 90%). However, within three months, first user A was removed. At this point, the second user still effectively only has one first user. Since first user A was involved in fraudulent installation activities, when calculating the value increase of first user B to the communication service system, the lost commission needs to be deducted for the value calculation result to be accurate.

[0141] In other embodiments of this application, other methods may be used to correct the initial business indicator value of the corresponding first user based on one or more of the obtained first business indicator correction value, second business indicator correction value, third business indicator correction value and fourth business indicator correction value, according to specific correction requirements, so as to obtain the business indicator value of the first user. The specific correction methods are not limited in the embodiments of this application, and are not listed one by one in this embodiment.

[0142] In some embodiments of this application, the method may further include: processing the business value of the first user. Optionally, the output information may include, but is not limited to, one or more of the following: the user identifier of the first user, the set tag value, the initial business value, the corrected business value, etc.

[0143] In summary, the business indicator acquisition method disclosed in this application obtains the initial business indicator value of the first user based on the business records of the first user in the communication business system and the business object information table of the communication business system. Then, the first user is tagged based on the business records within a preset time period, and the first user with preset abnormal behavior is tagged to obtain the tagging result of the first user. Then, the initial business indicator value of the first user with abnormal behavior is corrected according to the abnormal behavior indicated by the tagging result based on the tagging result to obtain the business indicator value of the first user. The interference introduced by abnormal user behavior records is eliminated from the business indicator value, thereby improving the accuracy of obtaining the user's business indicator value.

[0144] Accordingly, embodiments of this application also disclose an abnormal behavior recognition device, such as... Figure 7 As shown, the device includes:

[0145] The service record collection module 710 is used to collect the service records of the first user in the communication service system within a preset time period, wherein the service records include: device service records and package service records;

[0146] The first tagging module 720 is used to identify the first user matching the first preset behavior according to the device service record, and set a tag value corresponding to the first preset behavior for the identified first user.

[0147] The second marking module 730 is used to identify the first user matching the second preset behavior according to the package service record, and set a marking value corresponding to the matched second preset behavior for the identified first user.

[0148] Optionally, the device service record includes: installation, disassembly, and relocation records; the first preset behavior includes: user reorganization behavior; and the first marking module 720 is further used for:

[0149] Based on the installation, disassembly, and relocation records of the first user, the affiliation of the second user is determined, the first user matching the user reorganization behavior is identified, and a tag value corresponding to the user reorganization behavior is set for the identified first user.

[0150] Optionally, the equipment service record includes: installation, disassembly, and relocation records; the first preset behavior includes: one installation and one disassembly behavior; and the first marking module 720 is further used for:

[0151] Based on the installation, removal, and relocation records provided by the first user, the system performs a second user attribution determination, identity information similarity determination, and service address similarity determination to obtain a first determination result; and...

[0152] In response to the first judgment result indicating that at least two first users belong to the same second user or are associated with the same identity information, and that the at least two first users have at least two records with the same business address but different business types, a flag value corresponding to the installation and dismantling behavior is set for the at least two first users.

[0153] Optionally, the package service record includes one or more of the following records: package addition, package cancellation, package change; the second preset behavior includes: one upgrade and one downgrade behavior; the second marking module 730 is further used for:

[0154] Based on one or more records of package addition, package cancellation, and package change, obtain the change value of the first user's package value;

[0155] Based on the comparison result between the change value and the preset change threshold, the package change type matching the package service record of the first user is determined, wherein the package change type includes any one or more of the following: upgrade type, transfer type, downgrade type;

[0156] If, in response to the existence of at least one service record matching the upgrade type and at least one service record matching the downgrade type in the first user's service plan records, a flag value corresponding to the upgrade and downgrade behavior is set for the first user.

[0157] Optionally, the package service record includes one or more of the following records: package addition, package cancellation, package change; the second preset behavior includes: package reorganization behavior; and the second marking module 730 is further used for:

[0158] Based on one or more records of package addition, package cancellation, and package change, the second user associated with the first user of the same package and the package associated with the same first user are compared and judged to obtain a second judgment result.

[0159] In response to the second judgment result indicating that the target first user is associated with different packages before and after the package change, or that the target first user associated with the same package belongs to different second users before and after the package change, a flag value corresponding to the package reorganization behavior is set for the target first user.

[0160] The user behavior tagging device disclosed in this embodiment is used to implement the user behavior tagging method described in this application embodiment. The specific implementation methods of each module of the device will not be repeated here, but can be found in the specific implementation methods of the corresponding steps in the method embodiment.

[0161] The user behavior tagging device disclosed in this application collects the service records of a first user within a preset time period from a communication service system. These service records include device service records and package service records. Then, based on the device service records, the device user matching a first preset behavior is identified, and a tag value corresponding to the first preset behavior is set for the identified first user. Furthermore, based on the package service records, the device user matching a second preset behavior is identified, and a tag value corresponding to the second preset behavior is set for the identified first user. This achieves the ability to identify whether a first user exhibits a preset abnormal behavior and, if so, what kind of preset abnormal behavior exists. This provides effective data support for subsequently correcting the first user's initial service indicator values ​​based on the user behavior tagging results, thereby effectively eliminating the interference of abnormal behavior records on the calculation of user service indicator values ​​and improving the accuracy of obtaining the first user's service indicator values.

[0162] Accordingly, embodiments of this application also disclose a business indicator acquisition device, such as... Figure 8 As shown, the device includes:

[0163] The initial business indicator value acquisition module 810 is used to acquire the initial business indicator value of the first user based on the business records of the first user in the communication business system and the business object information table of the communication business system.

[0164] User behavior tagging module 820 is used to tag the first user using the user behavior tagging method described in the embodiments of this application, and obtain the tagging result of the first user.

[0165] The business indicator value correction module 830 is used to correct the initial business indicator value according to the marking result to obtain the business indicator value of the first user.

[0166] Optionally, the business indicator value correction module 830 is further used for:

[0167] In response to the marking result including the marking value corresponding to the installation and disassembly behavior, a second business indicator correction value is obtained based on the business record of the first user corresponding to the installation and disassembly behavior;

[0168] In response to the marking result including the marking value corresponding to the one-up-one-down behavior, the first business indicator correction value is obtained based on the business record of the first user corresponding to the one-up-one-down behavior;

[0169] In response to the tagging result including the tagging value corresponding to the user's reorganization behavior, a third business indicator correction value is obtained;

[0170] In response to the tagging result including the tagging value corresponding to the package reorganization behavior, the fourth business indicator correction value is obtained;

[0171] Based on one or more of the obtained first business indicator correction value, second business indicator correction value, third business indicator correction value and fourth business indicator correction value, the initial business indicator value of the corresponding first user is corrected to obtain the business indicator value of the first user.

[0172] The process of tagging the first user to obtain the tagging result of the first user includes: collecting the service records of the first user in the communication service system within a preset time period, wherein the service records include: device service records and package service records; identifying the first user matching a first preset behavior based on the device service records, and setting a tag value corresponding to the first preset behavior for the identified first user; and identifying the first user matching a second preset behavior based on the package service records, and setting a tag value corresponding to the second preset behavior for the identified first user.

[0173] The business indicator acquisition device disclosed in this application is used to implement the business indicator acquisition method described in this application. The specific implementation methods of each module of the device will not be repeated here, but can be found in the specific implementation methods of the corresponding steps in the method embodiments.

[0174] This application discloses a business indicator acquisition device. It obtains the initial business indicator value of a first user based on the first user's business records within a communication service system and the business object information table of the communication service system. Then, it tags the first user based on the business records within a preset time period in the communication service system, tagged first users exhibiting preset abnormal behaviors to obtain the tagging results for the first user. Finally, it corrects the initial business indicator value of the first user exhibiting abnormal behavior according to the abnormal behavior indicated by the tagging results, thus obtaining the first user's business indicator value. This method eliminates interference introduced by abnormal user behavior records from the business indicator value, thereby improving the accuracy of obtaining the user's business indicator value.

[0175] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus embodiments, since they are fundamentally similar to the method embodiments, the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0176] The above provides a detailed description of a user behavior tagging method and apparatus, and a business indicator acquisition method and apparatus provided by this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method of this application and its core idea. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the idea of ​​this application. Therefore, the content of this specification should not be construed as a limitation of this application.

[0177] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0178] The various component embodiments of this application can be implemented in hardware, or as software modules running on one or more processors, or a combination thereof. Those skilled in the art will understand that microprocessors or digital signal processors (DSPs) can be used in practice to implement some or all of the functions of some or all of the components in the electronic device according to the embodiments of this application. This application can also be implemented as a device or apparatus program (e.g., a computer program and computer program product) for performing part or all of the methods described herein. Such a program implementing this application can be stored on a computer-readable medium, or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, provided on a carrier signal, or provided in any other form.

[0179] For example, Figure 9An electronic device is shown that can implement the methods according to this application. The electronic device can be a PC, mobile terminal, personal digital assistant, tablet computer, etc. The electronic device conventionally includes a processor 910 and a memory 920, and program code 930 stored on the memory 920 and executable on the processor 910. When the processor 910 executes the program code 930, it implements the methods described in the above embodiments. The memory 920 can be a computer program product or a computer-readable medium. The memory 920 can be an electronic memory such as flash memory, EEPROM (Electrically Erasable Programmable Read-Only Memory), EPROM, hard disk, or ROM. The memory 920 has a storage space 9201 for the program code 930 of a computer program for performing any of the method steps described above. For example, the storage space 9201 for the program code 930 can include various computer programs for implementing the various steps in the above methods. The program code 930 is computer-readable code. These computer programs can be read from or written to one or more computer program products. These computer program products include program code carriers such as hard disks, CDs, memory cards, or floppy disks. The computer program includes computer-readable code that, when executed on an electronic device, causes the electronic device to perform the method according to the above embodiments.

[0180] This application also discloses a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the business indicator acquisition method as described in this application.

[0181] Such a computer program product can be a computer-readable storage medium, which can have the same characteristics as... Figure 9 The memory 920 in the illustrated electronic device is similarly arranged as storage segments, storage spaces, etc. Program code can be stored, for example, in a compressed form on the computer-readable storage medium. The computer-readable storage medium is typically as shown in the reference... Figure 10 The portable or fixed storage unit is described above. Typically, the storage unit includes computer-readable code 930', which is code read by a processor and, when executed by the processor, implements the various steps of the method described above.

[0182] The terms "an embodiment," "embodiment," or "one or more embodiments" as used herein mean that a particular feature, structure, or characteristic described in connection with an embodiment is included in at least one embodiment of this application. Furthermore, please note that the examples of the phrase "in one embodiment" do not necessarily all refer to the same embodiment.

[0183] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of this application may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0184] In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. This application can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In a unit claim enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names.

[0185] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A user behavior tagging method, characterized in that, The method includes: The system collects the service records of the first user within a preset time period from the communication service system, wherein the service records include: device service records and package service records; Based on the device service records, identify the first user that matches the first preset behavior, and set a flag value corresponding to the first preset behavior for the identified first user; Based on the package service records, identify the first user that matches the second preset behavior, and set a flag value corresponding to the matched second preset behavior for the identified first user; Wherein, if the device service records include installation, disassembly, and relocation records, and the first preset behavior includes user reorganization behavior, the step of identifying the first user matching the first preset behavior based on the device service records, and setting a flag value corresponding to the matched first preset behavior for the identified first user, includes: Based on the installation, disassembly, and relocation records of the first user, the affiliation of the second user is determined, the first user matching the user reorganization behavior is identified, and a tag value corresponding to the user reorganization behavior is set for the identified first user. When the device service records include installation, disassembly, and relocation records, and the first preset behavior includes one installation and one disassembly behavior, the step of identifying the first user matching the first preset behavior based on the device service records, and setting a flag value corresponding to the matched first preset behavior for the identified first user, includes: Based on the installation, dismantling, and relocation records provided by the first user, the second user's ownership, identity information similarity, and business address similarity are determined to obtain the first determination result. In response to the first judgment result indicating that at least two first users belong to the same second user or are associated with the same identity information, and the at least two first users have at least two records with the same business address but different business types, a tag value corresponding to the installation and dismantling behavior is set for the at least two first users; When the package service record includes one or more of the following records: package addition, package cancellation, package change, and the second preset behavior includes: one upgrade and one downgrade behavior, the step of identifying the first user matching the second preset behavior based on the package service record, and setting a flag value corresponding to the matched second preset behavior for the identified first user, includes: Based on one or more records of package addition, package cancellation, and package change, obtain the change value of the first user's package value; Based on the comparison result between the change value and the preset change threshold, the package change type matching the package service record of the first user is determined, wherein the package change type includes any one or more of the following: upgrade type, transfer type, downgrade type; If, in response to the existence of at least one service record matching the upgrade type and at least one service record matching the downgrade type in the first user's service package records, a flag value corresponding to the upgrade and downgrade behavior is set for the first user; In the case where the package service record includes one or more of the following records: package addition, package cancellation, package change, and the second preset behavior includes: package restructuring, the step of identifying the first user matching the second preset behavior based on the package service record, and setting a flag value corresponding to the matched second preset behavior for the identified first user, includes: Based on one or more records of package addition, package cancellation, and package change, the second user associated with the first user of the same package and the package associated with the same first user are compared and judged to obtain a second judgment result. In response to the second judgment result indicating that the target first user is associated with different packages before and after the package change, or that the target first user associated with the same package belongs to different second users before and after the package change, a flag value corresponding to the package reorganization behavior is set for the target first user.

2. A method for obtaining business metrics, characterized in that, The method includes: Based on the first user's business records within the communication business system and the business object information table of the communication business system, the initial business indicator value of the first user is obtained. The user behavior tagging method as described in claim 1 is used to tag the first user to obtain the tagging result of the first user; The initial business indicator value is corrected based on the marking result to obtain the business indicator value of the first user.

3. The method according to claim 2, characterized in that, The step of correcting the initial business indicator value based on the marking result to obtain the business indicator value of the first user includes: In response to the marking result including the marking value corresponding to the installation and disassembly behavior, a second business indicator correction value is obtained based on the business record of the first user corresponding to the installation and disassembly behavior; In response to the marking result including the marking value corresponding to the one-up-one-down behavior, the first business indicator correction value is obtained based on the business record of the first user corresponding to the one-up-one-down behavior; In response to the tagging result including the tagging value corresponding to the user's reorganization behavior, a third business indicator correction value is obtained; In response to the tagging result including the tagging value corresponding to the package reorganization behavior, the fourth business indicator correction value is obtained; Based on one or more of the obtained first business indicator correction value, second business indicator correction value, third business indicator correction value and fourth business indicator correction value, the initial business indicator value of the corresponding first user is corrected to obtain the business indicator value of the first user.

4. A user behavior tagging device, characterized in that, The device includes: The service record collection module is used to collect the service records of the first user in the communication system within a preset time period, wherein the service records include: device service records and package service records; The first tagging module is used to identify the first user matching the first preset behavior based on the device service records, and to set a tag value corresponding to the first preset behavior for the identified first user. The second marking module is used to identify the first user matching the second preset behavior based on the package service record, and to set a marking value corresponding to the matched second preset behavior for the identified first user. Wherein, in the case that the equipment service records include: installation, disassembly, and relocation records, and the first preset behavior includes: user reconfiguration behavior, the first marking module is further configured to: Based on the installation, disassembly, and relocation records of the first user, the affiliation of the second user is determined, the first user matching the user reorganization behavior is identified, and a tag value corresponding to the user reorganization behavior is set for the identified first user. When the equipment service records include installation, dismantling, and relocation records, and the first preset behavior includes one installation and one dismantling behavior, the first marking module is further used for: Based on the installation, dismantling, and relocation records provided by the first user, the second user's ownership, identity information similarity, and business address similarity are determined to obtain the first determination result. In response to the first judgment result indicating that at least two first users belong to the same second user or are associated with the same identity information, and the at least two first users have at least two records with the same business address but different business types, a tag value corresponding to the installation and dismantling behavior is set for the at least two first users; The service package records include one or more of the following: package addition, package cancellation, and package change. In the case that the second preset behavior includes an increase and a decrease, the second marking module is further used for: Based on one or more records of package addition, package cancellation, and package change, obtain the change value of the first user's package value; Based on the comparison result between the change value and the preset change threshold, the package change type matching the package service record of the first user is determined, wherein the package change type includes any one or more of the following: upgrade type, transfer type, downgrade type; If, in response to the existence of at least one service record matching the upgrade type and at least one service record matching the downgrade type in the first user's service package records, a flag value corresponding to the upgrade and downgrade behavior is set for the first user; The service package record includes one or more of the following: package addition, package cancellation, and package change. In the case that the second preset behavior includes a package restructuring behavior, the second marking module is further used for: Based on one or more records of package addition, package cancellation, and package change, the second user associated with the first user of the same package and the package associated with the same first user are compared and judged to obtain a second judgment result. In response to the second judgment result indicating that the target first user is associated with different packages before and after the package change, or that the target first user associated with the same package belongs to different second users before and after the package change, a flag value corresponding to the package reorganization behavior is set for the target first user.

5. A business indicator acquisition device, characterized in that, The device includes: The initial business indicator value acquisition module is used to acquire the initial business indicator value of the first user based on the business records of the first user in the communication business system and the business object information table of the communication business system. The user behavior tagging module is used to tag the first user using the user behavior tagging method as described in claim 1, and obtain the tagging result of the first user. The business indicator value correction module is used to correct the initial business indicator value based on the marking result to obtain the business indicator value of the first user.

6. An electronic device, comprising a memory, a processor, and program code stored in the memory and executable on the processor, characterized in that, When the processor executes the program code, it implements the method according to any one of claims 1 to 3.

7. A computer-readable storage medium having program code stored thereon, characterized in that, When the program code is executed by the processor, it implements the steps of the method described in any one of claims 1 to 3.

Images