Construction method and device of mobile network call ticket terminal model library, equipment and medium

Abstract

The invention discloses a method, a device, equipment and a medium for constructing a mobile network call ticket terminal model library, and the method comprises the steps: obtaining each piece of call ticket data from an online call ticket of a mobile network, and respectively extracting a terminal model keyword and a TAC corresponding to each piece of call ticket data; according to an extraction result, establishing at least one first mapping relation formed by the terminal model keyword and the TAC; according to each first mapping relationship, querying a pre-constructed terminal model keyword interpretation library, and establishing at least one second mapping relationship consisting of the terminal model keyword, the TAC and the terminal model; and according to each second mapping relationship, constructing to obtain a terminal model library. According to the method, the relationship among the terminal model keyword, the TAC and the terminal model is established through the terminal model keyword interpretation library, and the terminal model library is constructed, so that the internet behavior of the mobile terminal is associated with the label information of the physical world, and the accuracy and efficiency of call ticket data information clustering analysis are improved.

Description

Technical Field

[0001] The present invention relates to the field of big data technology, and in particular to a method, device, equipment and medium for constructing a mobile network call terminal model library. Background Art

[0002] With the rapid development of Internet technology, users' access to the Internet through various mobile terminal devices has become an indispensable part of daily life. Understanding the device models used by users is crucial to providing personalized services.

[0003] In the prior art, traditional Internet call bill data often does not contain the user's device terminal model information. The system based on the network communication service provider can usually only lock the behavior object to the number card inserted into the mobile terminal, resulting in such systems lacking label information in the physical world, thereby reducing the accuracy and efficiency of call bill data information clustering analysis. Summary of the invention

[0004] The present invention provides a method, device, equipment and medium for constructing a mobile network call bill terminal model library to solve the problem of low accuracy and low efficiency of call bill data information clustering analysis caused by the lack of associated physical world label information in the call bill information.

[0005] According to one aspect of an embodiment of the present invention, a method for constructing a mobile network call terminal model library is provided, comprising:

[0006] Obtain each call sheet data from the online call sheet of the mobile network, and extract the terminal model keyword and TAC corresponding to each call sheet data respectively;

[0007] According to the extraction result, establishing at least one first mapping relationship consisting of a terminal model keyword and a TAC;

[0008] According to each first mapping relationship, query a pre-built terminal model keyword interpretation library to establish at least one second mapping relationship consisting of a terminal model keyword, a TAC, and a terminal model;

[0009] According to each second mapping relationship, a terminal model library is constructed.

[0010] According to another aspect of an embodiment of the present invention, there is also provided a device for constructing a mobile network call terminal model library, including:

[0011] The terminal model keyword and TAC extraction module is used to obtain each call bill data in the online call bill of the mobile network, and respectively extract the terminal model keyword and TAC corresponding to each call bill data;

[0012] A first mapping relationship establishing module, used to establish at least one first mapping relationship consisting of a terminal model keyword and a TAC according to the extraction result;

[0013] A second mapping relationship establishment module, used to query a pre-built terminal model keyword interpretation library according to each first mapping relationship, and establish at least one second mapping relationship consisting of a terminal model keyword, a TAC, and a terminal model;

[0014] The terminal model library construction module is used to construct a terminal model library according to each second mapping relationship.

[0015] According to another aspect of an embodiment of the present invention, an electronic device is provided, the electronic device comprising:

[0016] at least one processor; and

[0017] a memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for constructing a mobile network call terminal model library described in any embodiment of the present invention.

[0019] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is also provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for constructing a mobile network call terminal model library described in any embodiment of the present invention when executed.

[0020] According to another aspect of an embodiment of the present invention, a computer program product is provided, including a computer program, wherein when the computer program is executed by a processor, the steps of the method described in any embodiment of the present invention are implemented.

[0021] The technical solution of the embodiment of the present invention obtains each call bill data in the online call bill of the mobile network, and extracts the terminal model keyword and TAC corresponding to each call bill data; according to the extraction result, at least one first mapping relationship consisting of the terminal model keyword and TAC is established; according to each first mapping relationship, a pre-constructed terminal model keyword interpretation library is queried to establish at least one second mapping relationship consisting of the terminal model keyword, TAC and terminal model; according to each second mapping relationship, a terminal model library is constructed. The relationship between the terminal model keyword, TAC and the terminal model is established through the terminal model keyword interpretation library, and the terminal model library is constructed, so as to associate the online behavior of the mobile terminal with the label information of the physical world, thereby improving the accuracy and efficiency of the cluster analysis of the call bill data information.

[0022] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 It is a flowchart of a method for constructing a mobile network call terminal model library according to the first embodiment of the present invention;

[0025] Figure 2 is a flowchart of another method for constructing a mobile network call terminal model library provided in accordance with the second embodiment of the present invention;

[0026] Figure 3 This is an overall flow chart of building a terminal model library with a single call bill data applicable to an embodiment of the present invention;

[0027] Figure 4 This is a schematic diagram of the structure of a device for constructing a mobile network call terminal model library according to Embodiment 3 of the present invention;

[0028] Figure 5 It is a structural schematic diagram of an electronic device for implementing the method for constructing a mobile network call terminal model library according to an embodiment of the present invention. DETAILED DESCRIPTION

[0029] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0030] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0031] Embodiment 1

[0032] Figure 1 This is a flowchart of a method for constructing a mobile network call bill terminal model library provided in the first embodiment of the present invention. This embodiment can be applied to the case where a mobile network call bill terminal model library is constructed based on the characteristic information in the mobile network online call bill and the associated physical world tag information. The method can be executed by a mobile network call bill terminal model library construction device, which can be implemented in the form of hardware and / or software and can generally be configured in an electronic device. Figure 1 As shown, the method includes:

[0033] S110. Acquire each piece of call bill data in the online call bill of the mobile network, and respectively extract the terminal model keyword and TAC corresponding to each piece of call bill data.

[0034] In the embodiment of the present invention, the mobile network can be specifically understood as: a wireless Internet access service achieved by inserting a SIM card, such as cellular networks such as 2G, 3G, 4G and 5G. The Internet bill can be specifically understood as: a document generated by a network operator to record the user's Internet behavior and usage when the user uses a mobile data network for Internet activities. Each Internet bill data usually includes information such as number, IMEI (International Mobile Equipment Identity), International Mobile User Identity IMSI, User-Agent (UA), start / end time, uplink / downlink traffic, duration, etc. There are multiple lines of data in the Internet bill file, and each line of data is a record of a user's Internet access, that is: how much traffic a certain mobile phone number generates when accessing the Internet through a certain card slot of a certain terminal at a certain point in time. The terminal model keyword can be specifically understood as: a special string in UA that can be used to mark the terminal model, which can be a device certification model or a device sales model, or some other special marking symbols, such as operating system code: Android, IOS or Harmony, etc.; browser identifier: Chrome, Safari or Firefox, etc.; version number: Version / 4.0 or IOS / 9.3, etc.

[0035] Specifically, IMEI can be understood as: a mobile phone serial number used to identify each independent mobile phone or other mobile communication device in the mobile phone network. The IMEI code corresponds to each mobile phone one by one, and each mobile phone will be assigned a globally unique IMEI number after assembly. For dual-SIM dual-standby mobile phones, each SIM card slot will have a corresponding IMEI number, that is, there are two IMEI codes.

[0036] The Type Allocation Code (TAC) is the first 8 digits of the IMEI. It is a code that distinguishes the terminal brand and model. The first two digits of the TAC code are the identification of the allocation agency, which is the code of the authorized IMEI code allocation agency, such as 01 for the United States Wireless Communications Industry Association, 35 for the United Kingdom Communications Accreditation Board, and 86 for the China Telecommunications Certification Forum. The last six digits of the TAC code are the device identification code, which is issued by the review agency and is used to identify the trademark and device model. The TAC code is used to ensure the global uniqueness of the device and help network operators accurately identify the device before allowing it to access the network.

[0037] UA can be specifically understood as: a special string header that enables the server to identify the operating system and version, CPU type, browser and version, browser rendering engine, browser language, browser plug-in and other information used by the device. The device certification model can be specifically understood as: the device identifier when registering for the telecommunications equipment network access license, such as V2243A. The device sales model can be specifically understood as: the identifier of different types of devices sold by device manufacturers, usually composed of numbers and letters, used by mobile phone manufacturers to distinguish the types of mobile phones sold to the outside world, such as: iPhone 15Pro Max and HUAWEI Mate60Pro, etc.

[0038] Specifically, each call bill data is obtained from the online call bill of the mobile network, the user agent information is obtained from the online call bill, and a regular expression is used to match and extract the brand or model of the device. According to the brand or model of the device, the corresponding extraction rules are adopted to extract the device authentication model, device sales model or special mark symbol corresponding to each call bill data from the UA as the terminal model keyword, and the first 8 digits of the IMEI in the online call bill are used as the TAC.

[0039] S120: Establish at least one first mapping relationship consisting of a terminal model keyword and a TAC according to the extraction result.

[0040] In the embodiment of the present invention, the first mapping relationship can be specifically understood as: the relationship between the TAC extracted from each call bill data of the Internet call bill and the corresponding terminal model keyword. Among them, since TAC is a type allocation code used to ensure the global uniqueness of the device, one TAC corresponds to one terminal model keyword, and since the last six digits of TAC are the device identification code used to identify the trademark and device model, the same device model can include multiple sold devices, so one terminal model keyword can correspond to multiple TACs.

[0041] Specifically, at least one first mapping relationship consisting of the terminal model keyword and the corresponding TAC is established between the extracted terminal model keywords and the corresponding TACs.

[0042] S130: According to each first mapping relationship, query a pre-built terminal model keyword interpretation library to establish at least one second mapping relationship consisting of a terminal model keyword, a TAC, and a terminal model.

[0043] In the embodiment of the present invention, the terminal model keyword interpretation library can be specifically understood as: a data table that records one-to-one information of the terminal model keyword and the corresponding terminal model, which is a medium that associates the feature information in the call list with the terminal model tag information in the physical world. Among them, the terminal model may include information such as the device sales model corresponding to the terminal model keyword and the corresponding device manufacturer. The second mapping relationship can be specifically understood as: a mapping relationship composed of terminal models that match the TAC and the terminal model keyword.

[0044] S140: Construct a terminal model library according to each second mapping relationship.

[0045] In an embodiment of the present invention, the terminal model library can be specifically understood as: a data table describing the terminal model and terminal model keywords of TAC, for example, it may include TAC, the terminal model keyword corresponding to TAC, the equipment manufacturer corresponding to the terminal model keyword, and the equipment sales model corresponding to the terminal model keyword.

[0046] Specifically, according to the first mapping relationship consisting of each terminal model keyword and the corresponding TAC, by querying and matching each terminal model keyword in the pre-built terminal model keyword interpretation library, at least one second mapping relationship consisting of the terminal model keyword, TAC and terminal model is constructed, and according to each second mapping relationship, a terminal model library is constructed. By constructing a terminal model library, the label information of the associated physical world can be supplemented for the feature information extracted from the call list, such as supplementing the user portrait label of the marketing system (such as analyzing the high-end mobile phone user group, the old replacement user group and the non- / domestic mobile phone group, etc.), supplementing the terminal label of the network security system (such as the manufacturer, model and production batch of the faulty vehicle, etc.) and supplementing the terminal label of the network quality optimization system (such as the terminal model, processor chip baseband and modem, etc.), to achieve better clustering analysis, realize precision marketing, safety hazard distribution debugging and analogy prediction and refined network management.

[0047] The technical solution of the embodiment of the present invention obtains each call bill data in the online call bill of the mobile network, and extracts the terminal model keyword and TAC corresponding to each call bill data; according to the extraction result, at least one first mapping relationship consisting of the terminal model keyword and TAC is established; according to each first mapping relationship, a pre-constructed terminal model keyword interpretation library is queried to establish at least one second mapping relationship consisting of the terminal model keyword, TAC and terminal model; according to each second mapping relationship, a terminal model library is constructed. The relationship between the terminal model keyword, TAC and the terminal model is established through the terminal model keyword interpretation library, and the terminal model library is constructed, so as to associate the online behavior of the mobile terminal with the label information of the physical world, thereby improving the accuracy and efficiency of the cluster analysis of the call bill data information.

[0048] Optionally, in the embodiment of the present invention, respectively extracting the terminal model keyword and TAC corresponding to each call bill data may include:

[0049] Extracting user agent information from the current call log data, and detecting whether the user agent information contains a preset mobile terminal identification name;

[0050] If yes, extract TAC from the IMEI information in the current call log data, and perform regular matching between the user agent information and the feature rules in the terminal feature library;

[0051] If the match is successful, the matched content is obtained as the terminal model keyword.

[0052] In the embodiment of the present invention, the mobile terminal identification name can be specifically understood as: a specific keyword or string used to identify the type or brand of mobile device in UA, such as iPhone, Android or Harmony. The terminal feature library can be specifically understood as: a set of string matching rules used to extract the terminal model keyword in UA. Since the bill file of a specific terminal device brand or model follows a specific structured format, these specific format rules can be pre-updated to the terminal feature library for extracting the terminal model keyword information in UA.

[0053] Specifically, extract the user agent information from the current call bill data, and detect whether the user agent information contains a preset mobile terminal identification name, such as iPhone, Android or Harmony. If not, it means that this call bill data does not come from the mobile terminal, and process the next call bill data. If yes, extract the first 8 digits from the IMEI information in the current call bill data as TAC, and perform regular matching on the user agent information and the feature string matching rules in the terminal feature library. If the match is successful, obtain the successfully matched content as the terminal model keyword, such as the device authentication model, device sales model or special mark symbol. If the match fails, it means that the UA may be modified by the user, some browser plug-ins or Apps, resulting in the UA being empty or other abnormal format strings. In view of the huge amount of call bill data, for these individual call bill data that cannot be extracted normally, a direct discard strategy can be adopted, because their impact on the overall data analysis is minimal. The preset matching rules may not cover all abnormal situations, but this method ensures that most call bill data can be processed efficiently while maintaining the accuracy and efficiency of the analysis.

[0054] Optionally, in the embodiment of the present invention, establishing at least one first mapping relationship consisting of a terminal model keyword and a TAC according to the extraction result may include:

[0055] According to the extraction results, all terminal model keywords corresponding to each TAC are obtained;

[0056] If the first TAC corresponds to only a single first terminal model keyword, directly establishing a first mapping relationship between the first TAC and the first terminal model keyword;

[0057] If the second TAC corresponds to multiple terminal model keywords, the second terminal model keyword is determined from the multiple terminal model keywords according to the occurrence frequencies of the multiple terminal model keywords for the second TAC, and a first mapping relationship between the second TAC and the second terminal model keyword is established.

[0058] In the embodiment of the present invention, the first TAC can be specifically understood as: after obtaining all terminal model keywords corresponding to each TAC, the TAC code corresponding to the terminal model keyword one-to-one. The first terminal model keyword can be specifically understood as: the terminal model keyword corresponding to the first TAC. The second TAC can be specifically understood as: after obtaining all terminal model keywords corresponding to each TAC, the TAC code having a one-to-many relationship with the terminal model keyword. The second terminal model keyword can be specifically understood as: the terminal model keyword corresponding to the second TAC.

[0059] Specifically, according to the extraction results, all terminal model keywords corresponding to each TAC are obtained, and the correspondence between each TAC and the corresponding terminal model keyword is detected. If the first TAC only corresponds to a single first terminal model keyword, a first mapping relationship between the first TAC and the first terminal model keyword is directly established.

[0060] If the second TAC corresponds to multiple terminal model keywords, it means that the UA may be modified by the user, certain browser plug-ins or apps, resulting in the UA being empty or other abnormally formatted strings. It is necessary to count the frequency of occurrence of each terminal model keyword corresponding to the second TAC, and select the terminal model keyword with the highest or second highest frequency as the second terminal model keyword corresponding to the second TAC according to business needs, and establish a first mapping relationship between the second TAC and the second terminal model keyword, ensuring that the TAC and the terminal model keyword are one-to-one, and saving the corresponding frequency at the same time. By saving the highest or second highest frequency data as the second terminal model keyword and the corresponding frequency, it can help verify and analyze whether the terminal model keyword of a specific TAC is accurate. If the frequency of the keyword corresponding to a certain TAC is much lower than the frequency of the keyword corresponding to other TACs, the credibility of the keyword as the correct terminal model keyword is reduced. Therefore, the terminal model keyword with the highest or second highest frequency is selected as the second terminal model keyword to be selected. If the terminal model keyword frequency corresponding to a certain TAC is abnormally low, it may indicate that there are problems in the data collection process or that a new model has appeared on the market. By analyzing the highest and second highest terminal model keywords and determining the second terminal model keyword based on actual business needs, it is helpful to discover and correct data anomalies and ensure the accuracy of the screened second terminal model keyword.

[0061] Optionally, in the embodiment of the present invention, determining the second terminal model keyword from the plurality of terminal model keywords according to the occurrence frequencies of the plurality of terminal model keywords for the second TAC may include:

[0062] Among the plurality of terminal model keywords, a terminal model keyword with the highest occurrence frequency for the second TAC is obtained as the second terminal model keyword.

[0063] Specifically, among multiple terminal model keywords, the terminal model keyword with the highest frequency of occurrence for the second TAC is obtained as the second terminal model keyword. If the terminal model keyword needs to be updated or corrected, the maintenance workload and the possibility of error can be reduced by selecting the keyword with the highest frequency. In addition, in business decisions, more attention is usually paid to mainstream trends and major user groups. The most frequent keywords can better reflect these trends, while the second most frequent keywords may only represent niche or special cases and have limited impact on business decisions.

[0064] Embodiment 2

[0065] Figure 2A flowchart of another method for constructing a mobile network call bill terminal model library provided in Example 2 of the present invention. This embodiment is a refinement of the above-mentioned embodiment, in which a pre-constructed terminal model keyword interpretation library is queried according to each first mapping relationship to establish at least one second mapping relationship consisting of a terminal model keyword, a TAC and a terminal model. Specifically, it includes: using the terminal model keyword in each first mapping relationship to query the terminal model keyword interpretation library respectively, wherein the terminal model keyword interpretation library stores the correspondence between the terminal model keyword and the terminal model; if a matching target terminal model is found in the terminal model keyword interpretation library for the target terminal model keyword in the target first mapping relationship, a second mapping relationship is formed according to the target first mapping relationship and the target terminal model.

[0066] Correspondingly, such as Figure 2 As shown, the method includes:

[0067] S210: Obtain each piece of call bill data from the online call bill of the mobile network, and respectively extract the terminal model keyword and TAC corresponding to each piece of call bill data.

[0068] S220: Establish at least one first mapping relationship consisting of a terminal model keyword and a TAC according to the extraction result.

[0069] S230: Use the terminal model keyword in each first mapping relationship to query the terminal model keyword interpretation library respectively.

[0070] The terminal model keyword interpretation library stores the correspondence between the terminal model keywords and the terminal models.

[0071] Specifically, the terminal model keyword in each first mapping relationship is used to query the terminal model keyword interpretation library respectively to determine the terminal model associated with the terminal model keyword. The terminal model may include the device manufacturer and device sales model, etc., which are determined according to actual business needs. The physical world label information corresponding to the terminal model keyword is not limited to this in the embodiment of the present invention.

[0072] S240: If a matching target terminal model is found in the terminal model keyword interpretation library for the target terminal model keyword in the target first mapping relationship, a second mapping relationship is formed according to the target first mapping relationship and the target terminal model.

[0073] In the embodiment of the present invention, the target first mapping relationship can be specifically understood as: the first mapping relationship currently being processed. The target terminal model keyword can be specifically understood as: the terminal model keyword in the target first mapping relationship. The target terminal model can be specifically understood as: the terminal model matching the target terminal model keyword queried in the terminal model keyword interpretation library.

[0074] Specifically, if a matching target terminal model is found in the terminal model keyword interpretation library for the target terminal model keyword in the target first mapping relationship, a second mapping relationship is formed based on the target first mapping relationship and the target terminal model. If a matching target terminal model is not found, the target terminal model corresponding to the target terminal model keyword in the target first mapping relationship can be found by manual query, and the target terminal model keyword and the target terminal model are added to the terminal model keyword interpretation library for subsequent matching processes.

[0075] S250: Construct a terminal model library according to each second mapping relationship.

[0076] Specifically, according to each second mapping relationship, a terminal model library is constructed, and the terminal model library records TAC, terminal model keywords and corresponding terminal models.

[0077] The technical solution of the embodiment of the present invention is to obtain each call bill data in the online call bill of the mobile network, and respectively extract the terminal model keyword and TAC corresponding to each call bill data; according to the extraction result, establish at least one first mapping relationship composed of the terminal model keyword and the TAC; use the terminal model keyword in each first mapping relationship to query the terminal model keyword interpretation library respectively; if the matching target terminal model is found in the terminal model keyword interpretation library for the target terminal model keyword in the target first mapping relationship, a second mapping relationship is formed according to the target first mapping relationship and the target terminal model; and construct a terminal model library according to each second mapping relationship. By establishing a second mapping relationship between the target first mapping relationship and the target terminal model through the terminal model keyword interpretation library, and constructing a terminal model library according to each second mapping relationship, the online behavior of the mobile terminal is associated with the label information of the physical world, and the accuracy and efficiency of the cluster analysis of call bill data information are improved.

[0078] Furthermore, in the embodiment of the present invention, after using the terminal model keyword in each first mapping relationship to query the terminal model keyword interpretation library respectively, the following may also be included:

[0079] If the target terminal model keyword in the target first mapping relationship is not found in the terminal model keyword interpretation library, an operation of automatically obtaining the target terminal model matching the target terminal model keyword is performed by using a crawler or calling an artificial intelligence AI interface;

[0080] When the target terminal model matching the target terminal model keyword is successfully obtained, the corresponding relationship between the target terminal model keyword and the target terminal model is additionally stored in the terminal model keyword interpretation library.

[0081] Specifically, after using the terminal model keyword in each first mapping relationship to query the terminal model keyword interpretation library respectively, if the target terminal model keyword in the target first mapping relationship is not queried in the terminal model keyword interpretation library, the target terminal model matching the target terminal model keyword is automatically obtained by using a crawler or calling an artificial intelligence AI interface. If the automatic acquisition fails, it can be manually obtained. When the target terminal model matching the target terminal model keyword is successfully obtained, the corresponding relationship between the target terminal model keyword and the target terminal model is added and stored in the terminal model keyword interpretation library. The terminal model keyword and the terminal model in the library are one-to-one, which ensures the uniqueness and integrity of the data, so that the terminal model data can be successfully matched according to the terminal model keyword in the next round of matching. When the target terminal model matching the target terminal model keyword fails to be obtained, given the huge amount of call list data, the individual target terminal model keywords that cannot be matched to the terminal model data have little impact on the construction of the terminal model library, and can be directly discarded to process the terminal model keyword in the next first mapping relationship.

[0082] Furthermore, in the embodiment of the present invention, whenever it is detected that the terminal model keyword interpretation library is updated, the following steps may also be included:

[0083] According to each first mapping relationship for which the second mapping relationship is not successfully established, a pre-built terminal model keyword interpretation library is re-queried to try to establish a new second mapping relationship.

[0084] Specifically, when it is detected that the terminal model keyword interpretation library has been updated, it means that the target terminal model keyword in the target first mapping relationship has not been queried in the terminal model keyword interpretation library, and it is necessary to re-query the pre-built terminal model keyword interpretation library for the target terminal model keyword to establish a second mapping relationship between the target terminal model keyword and the target terminal model, and construct a terminal model library based on each second mapping relationship, so as to save the TAC and the corresponding new data features in the terminal model keyword interpretation library to the terminal model library, obtain a one-to-one correspondence between TAC, terminal model keyword and terminal model, and realize the construction of a terminal model library based on mobile network call records.

[0085] Specific application scenarios

[0086] Some current systems based on network communication service providers can collect and monitor the Internet behavior and security risk behavior of mobile terminals (mobile phones, watches, vehicles, and the Internet of Things, etc.), but such systems can usually only lock the behavior object to the number card inserted in the mobile terminal, and cannot associate the manufacturer and terminal model information of the mobile device where the number card is located. As a result, such systems lack label information in the physical world and cannot perform better cluster analysis, which limits the service provider's ability to identify devices. In order to solve the above problems, an embodiment of the present invention proposes a method for constructing a mobile network call terminal model library. Figure 3 This is an overall flow chart of building a terminal model library for a single call bill data applicable to an embodiment of the present invention, such as Figure 3 As shown, the method may include:

[0087] S310, collecting Internet call records.

[0088] Internet bills are receipts that network operators use to record users' Internet behavior and usage through some technologies when users use mobile data networks to surf the Internet. These data are usually used for traffic billing, network quality analysis, network access tracing and network security analysis.

[0089] The user's Internet bill file is obtained from the file system. Each Internet bill data in the file usually includes information such as number, IMEI, IMSI, UA, start / end time, uplink / downlink traffic, duration, etc. There are multiple lines of data in the Internet bill file, and each line of data is a record of a user's Internet access, that is, how much traffic a certain mobile phone number generates when accessing the Internet through a certain card slot of a certain terminal at a certain time point. In the embodiment of the present invention, IMEI and UA are mainly involved.

[0090] Since the online call bill network communication service provider collects and records log data through technical means, the required call bill files in the embodiment of the present invention can be obtained from the file system, or through FTP (File Transfer Protocol) or SFTP (Secure File Transfer Protocol), etc., as long as such data can be obtained, the embodiment of the present invention does not impose any restrictions on this.

[0091] S320, extracting online call bill information.

[0092] Extract information based on some fields in each data in the online call bill, and extract the following two pieces of information:

[0093] 1.Terminal model keywords

[0094] First, determine whether the UA contains strings such as iPhone, Android, or Harmony to check whether it is a mobile Internet terminal. If so, perform regular matching with the feature rules in the terminal feature library (a string matching algorithm). If the match is successful, it is considered that the terminal model keyword has been extracted. The terminal model keyword can be a device sales model, a terminal certification model, or a special character.

[0095] 2.TAC

[0096] TAC can be obtained based on the IMEI in the online call bill (i.e. extracting the first 8 digits of the IMEI). Under normal circumstances, each TAC can only be attributed to a specific device sales model.

[0097] Table 1 shows the data corresponding to the terminal model keyword and TAC extracted from the online call bill. As shown in Table 1, at this time, each data in the online call bill will generate a data corresponding to the terminal model keyword and TAC.

[0098] Table 1

[0099] Serial number Terminal model keyword TAC 1 REDMI K40 86624105 2 V2243A 86645306 3 iPhone13,2 35306411 4 REDMI K70 PRO 86012607 5 iPhone 14, 5 35188763 6 JEF-TN00 86042605 7 iPhone13,2 35828493 8 ever 35828493 … … …

[0100] Usually one TAC corresponds to one terminal model keyword. Since UA may be modified by the user, certain browser plug-ins or apps, resulting in UA being empty or other abnormally formatted strings, after processing a batch of Internet call records, one TAC may correspond to multiple terminal model keywords, such as the 7th and 8th rows of data in the above table. The subsequent step S330 will extract valid data from the duplicate data in the 7th and 8th rows by merging the calculation method.

[0101] S330, big data merge calculation.

[0102] For a single TAC, the frequency of occurrence of each terminal model keyword is calculated through big data. In the case where one TAC corresponds to one terminal model keyword, the TAC, the corresponding terminal model keyword and the frequency are directly saved. In the case where one TAC corresponds to multiple terminal model keywords, the terminal model keyword with the highest frequency of occurrence is selected as the terminal model keyword corresponding to the TAC to ensure that the TAC and the terminal model keyword are in a one-to-one relationship, and the corresponding frequency is saved at the same time. Table 2 is an example of aggregated statistical frequency based on the two dimensions of TAC and terminal model keyword. Table 3 is the sample data after taking the data with the highest frequency of occurrence based on the TAC number. As shown in Table 3, the 8th row of data in Table 2 will be screened out.

[0103] Table 2

[0104] Serial number Terminal model keyword TAC Frequency of occurrence 1 REDMI K40 86624105 999 2 V2243A 86645306 986 3 iPhone13,2 35306411 999 4 REDMI K70 PRO 86012607 8676 5 iPhone 14, 5 35188763 4356 6 JEF-TN00 86042605 74 7 iPhone13,2 35828493 234 8 ever 35828493 76 … … … …

[0105] Table 3

[0106] Serial number Terminal Keywords TAC Frequency of occurrence 1 REDMI K40 86624105 999 2 V2243A 86645306 986 3 iPhone13,2 35306411 999 4 REDMI K70 PRO 86012607 8676 5 iPhone 14, 5 35188763 4356 6 JEF-TN00 86042605 74 7 iPhone13,2 35828493 234 … … … …

[0107] S340, associate and match according to the terminal model keyword, if the association is successful, execute S350, if the association fails, execute S360.

[0108] Table 4 is the table structure of the terminal model keyword interpretation library. After obtaining the one-to-one relationship between TAC and terminal model keywords, as well as the frequency of occurrence, based on the terminal model keyword interpretation library (the library contains one-to-one information of terminal model keywords, equipment sales models, and equipment manufacturers, as shown in Table 4), the corresponding relationship between TAC, terminal model keywords, frequency, and terminal model can be obtained by using the terminal model keyword as the association condition. Table 5 is a sample of data after association based on the terminal model keyword interpretation library data. As shown in Table 5, the sixth data item is the data that cannot be associated, and the rest of the data is the data that is successfully associated.

[0109] Table 4

[0110] Parameter name Parameter Type Is it necessary Parameter Description keyword varchar True Terminal model keyword vendor_name varchar True Device manufacturer name device_name varchar True Equipment sales model name

[0111] Table 5

[0112] Serial number Terminal Keywords TAC Frequency of occurrence Equipment Manufacturers Equipment sales model 1 REDMI K40 86624105 999 Millet Redmi K40 2 V2243A 86645306 986 vivo iQOO 11 3 iPhone13,2 35306411 999 apple iPhone 12 4 REDMI K70 PRO 86012607 8676 Millet Redmi K70 Pro 5 iPhone14,5 35188763 4356 apple iPhone 15 6 JEF-TN00 86042605 74 7 iPhone13,2 35828493 234 apple iPhone 12 … … … … … …

[0113] If the association is successful according to the terminal model keyword, S350 is executed; if the association fails, S360 is executed.

[0114] S350, terminal model precipitation.

[0115] The successfully associated data is persisted and saved to the terminal model library, which is a data table describing the device manufacturer, device sales model and device model keyword of the TAC code. Table 6 shows the table structure of the terminal model library. Table 7 shows the data sample of the terminal model library.

[0116] Table 6

[0117] Parameter name Parameter Type Is it necessary Parameter Description tac varchar True Type allocation, first 8 digits of IMEI keyword varchar True Terminal model keyword vendor_name varchar True Device manufacturer name device_name varchar True Equipment sales model name pv int True Frequency

[0118] Table 7

[0119] Serial number TAC Terminal model keyword Equipment Manufacturers Equipment sales model Frequency of occurrence 1 86624105 REDMI K40 Millet Redmi K40 999 2 86645306 V2243A vivo iQOO 11 986 3 35306411 iPhone13,2 apple iPhone 12 999 4 86012607 REDMI K70 PRO Millet Redmi K70 Pro 8676 5 35188763 iPhone14,5 apple iPhone 15 4356 6 35828493 iPhone13,2 apple iPhone 12 234 … … … … … …

[0120] S360. Capture terminal model information online through a crawler or an AI interface, and execute S370.

[0121] By using a crawler or AI interface to supplement the terminal model information according to the terminal model keyword, the terminal model information corresponding to the terminal model keyword that cannot be associated is supplemented. It can also be manually searched through a search engine to find the supplement. If the supplement fails, the data is discarded and the next batch of call list data is processed. If the supplement is successful, execute S370.

[0122] S370, sedimentation terminal model keyword interpretation library.

[0123] The terminal model keyword and terminal model information obtained in S360 are added as new data to the terminal model keyword interpretation library, so as to achieve the purpose of updating the terminal model keyword interpretation library with the new data features in the call list. The terminal model keyword and the terminal model in the library are one-to-one, which ensures the uniqueness and integrity of the data, so that the terminal model data can be successfully matched according to the terminal model keyword in the next round of matching.

[0124] After the above steps, we have obtained a one-to-one relationship between TAC and terminal model, and realized the construction of a terminal model library based on mobile network call records.

[0125] The method for constructing a terminal model library based on a mobile online call list proposed in an embodiment of the present invention supports development in languages ​​such as Java, C, C++, and Python, and uses ClickHouse to store and calculate call list data. When the amount of data is small, databases such as MySQL or Hadoop can also be used. Among them, ClickHouse is a column-based database management system (DBMS) for online analytical processing (OLAP).

[0126] The method for constructing a terminal model library based on mobile Internet call bills proposed in the embodiment of the present invention can be used to supplement application scenarios such as user portrait labels for marketing systems, terminal labels for network security systems, and terminal labels for network quality optimization systems.

[0127] For example, in marketing scenarios, the billing system of network communication service providers can collect and calculate the records of Internet access through traffic of number cards, and carry out package marketing without or with a small amount of traffic and customized phone marketing for user groups that do not use traffic. However, there are not enough tags to make user portraits. By combining Internet behavior with the terminal model library, the tags of user portraits can be enriched, such as: high-end mobile phone user groups, old phone replacement user groups, and non- / domestic mobile phone groups, so as to carry out precision marketing and improve marketing effects.

[0128] For example, in network security scenarios, the terminal model library can be used to supplement the annotation data for the network security analysis system of network information service providers and communication regulatory units. Usually, such security analysis systems can find that a certain number card has a security risk, but cannot be associated with the physical object in the physical world. With such a terminal model library, the manufacturer and model information of the device can be associated, such as assisting in analyzing whether there is information theft in Xiaomi SU7, analyzing whether there is remote control in Baidu audio, etc., and statistical analysis presents the network security event situation of various manufacturers and various models. For another example, the security analysis system based on mobile networks, such as the Internet of Vehicles security monitoring system, the Internet of Things security monitoring system, and the mobile Internet security monitoring system, can currently only monitor and discover that a certain car has a security risk through technical means. Through the terminal model library, it can be associated with the physical object in the physical world, that is, it can be found that a certain model of a certain manufacturer has a security risk, and by analogy, whether the same batch of vehicles may have a security risk, and analyze the distribution of security risks of various manufacturers and models and make predictions.

[0129] For example, in the network quality analysis scenario, the terminal model library can supplement the annotation data for the network quality analysis system of the network service provider. Usually, such analysis systems can analyze the network communication quality of a certain number card. If it can be associated with the terminal model library, the network communication quality of the same terminal model can be clustered and analyzed. For example: Is the signal of Huawei mobile phones generally better than that of Apple mobile phones?

[0130] The method for constructing a terminal model library based on a mobile Internet call bill proposed in an embodiment of the present invention can parse UA information in an Internet call bill, and can quickly and efficiently extract terminal model keywords in the UA; can extract and construct a one-to-one relationship between TAC and terminal model keywords through big data technology, and can update the terminal model keywords that cannot be associated and the corresponding terminal models obtained through crawlers, AI interfaces or manually as new data to the terminal model keyword interpretation library, establish the relationship between terminal model keywords, TAC and terminal models through the terminal model keyword interpretation library, construct a terminal model library, and realize associating the Internet behavior of mobile terminals with the label information of the physical world, thereby improving the accuracy and efficiency of cluster analysis of call bill data information.

[0131] Embodiment 3

[0132] Figure 4 The structure diagram of a device for constructing a mobile network call terminal model library provided by the third embodiment of the present invention is as follows. Figure 4 As shown, the device includes: a terminal model keyword and TAC extraction module 410, a first mapping relationship establishment module 420, a second mapping relationship establishment module 430 and a terminal model library construction module 440.

[0133] The terminal model keyword and TAC extraction module 410 is used to obtain each call bill data in the online call bill of the mobile network, and respectively extract the terminal model keyword and TAC corresponding to each call bill data;

[0134] A first mapping relationship establishing module 420, configured to establish at least one first mapping relationship consisting of a terminal model keyword and a TAC according to the extraction result;

[0135] The second mapping relationship establishment module 430 is used to query the pre-built terminal model keyword interpretation library according to each first mapping relationship, and establish at least one second mapping relationship consisting of the terminal model keyword, TAC and terminal model;

[0136] The terminal model library construction module 440 is used to construct a terminal model library according to each second mapping relationship.

[0137] The technical solution of the embodiment of the present invention obtains each call bill data in the online call bill of the mobile network, and extracts the terminal model keyword and TAC corresponding to each call bill data; according to the extraction result, at least one first mapping relationship consisting of the terminal model keyword and TAC is established; according to each first mapping relationship, a pre-constructed terminal model keyword interpretation library is queried to establish at least one second mapping relationship consisting of the terminal model keyword, TAC and terminal model; according to each second mapping relationship, a terminal model library is constructed. The relationship between the terminal model keyword, TAC and the terminal model is established through the terminal model keyword interpretation library, and the terminal model library is constructed, so as to associate the online behavior of the mobile terminal with the label information of the physical world, thereby improving the accuracy and efficiency of the cluster analysis of the call bill data information.

[0138] Based on the above embodiments, the terminal model keyword and TAC extraction module 410 is specifically used for:

[0139] Extracting user agent information from the current call log data, and detecting whether the user agent information contains a preset mobile terminal identification name;

[0140] If yes, extract TAC from the IMEI information in the current call log data, and perform regular matching between the user agent information and the feature rules in the terminal feature library;

[0141] If the match is successful, the matched content is obtained as the terminal model keyword.

[0142] Based on the above embodiments, the first mapping relationship establishing module 420 is specifically used for:

[0143] According to the extraction results, all terminal model keywords corresponding to each TAC are obtained;

[0144] If the first TAC corresponds to only a single first terminal model keyword, directly establishing a first mapping relationship between the first TAC and the first terminal model keyword;

[0145] If the second TAC corresponds to multiple terminal model keywords, the second terminal model keyword is determined from the multiple terminal model keywords according to the occurrence frequencies of the multiple terminal model keywords for the second TAC, and a first mapping relationship between the second TAC and the second terminal model keyword is established.

[0146] Optionally, the first mapping relationship establishing module 420 includes: a second terminal model keyword acquiring unit.

[0147] The second terminal model keyword acquiring unit is configured to acquire, from among a plurality of terminal model keywords, a terminal model keyword with the highest occurrence frequency for the second TAC as the second terminal model keyword.

[0148] Based on the above embodiments, the second mapping relationship establishing module 430 is specifically used for:

[0149] Using the terminal model keyword in each first mapping relationship, query the terminal model keyword interpretation library respectively;

[0150] If a matching target terminal model is found in the terminal model keyword interpretation library for the target terminal model keyword in the target first mapping relationship, a second mapping relationship is formed according to the target first mapping relationship and the target terminal model.

[0151] Further, based on the above embodiments, the second mapping relationship establishing module 430 may also be specifically used for:

[0152] If the target terminal model keyword in the target first mapping relationship is not found in the terminal model keyword interpretation library, an operation of automatically obtaining the target terminal model matching the target terminal model keyword is performed by using a crawler or calling an artificial intelligence AI interface;

[0153] When the target terminal model matching the target terminal model keyword is successfully obtained, the corresponding relationship between the target terminal model keyword and the target terminal model is additionally stored in the terminal model keyword interpretation library.

[0154] Further, based on the above embodiments, the second mapping relationship establishing module 430 may also be specifically used for:

[0155] Whenever it is detected that the terminal model keyword interpretation library is updated, the pre-built terminal model keyword interpretation library is re-queried according to each first mapping relationship for which the second mapping relationship is not successfully established, so as to try to establish a new second mapping relationship.

[0156] The device for constructing a mobile network call bill terminal model library provided in an embodiment of the present invention can execute the method for constructing a mobile network call bill terminal model library provided in any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.

[0157] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0158] Embodiment 4

[0159] Figure 5 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0160] like Figure 5 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0161] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0162] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the method for constructing a mobile network call terminal model library, that is:

[0163] Obtain each call sheet data in the online call sheet of the mobile network, and respectively extract the terminal model keyword and type allocation code TAC corresponding to each call sheet data;

[0164] According to the extraction result, establishing at least one first mapping relationship consisting of a terminal model keyword and a TAC;

[0165] According to each first mapping relationship, query a pre-built terminal model keyword interpretation library to establish at least one second mapping relationship consisting of a terminal model keyword, a TAC, and a terminal model;

[0166] According to each second mapping relationship, a terminal model library is constructed.

[0167] In some embodiments, the method for constructing a mobile network call bill terminal model library can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the method for constructing a mobile network call bill terminal model library described above can be executed. Alternatively, in other embodiments, the processor 11 can be configured to execute the method for constructing a mobile network call bill terminal model library in any other appropriate manner (for example, by means of firmware).

[0168] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0169] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0170] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0171] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0172] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0173] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0174] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0175] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for constructing a mobile network call terminal model library, characterized in that: include: Obtain each call sheet data in the online call sheet of the mobile network, and respectively extract the terminal model keyword and type allocation code TAC corresponding to each call sheet data; According to the extraction result, establishing at least one first mapping relationship consisting of a terminal model keyword and a TAC; According to each first mapping relationship, query a pre-built terminal model keyword interpretation library to establish at least one second mapping relationship consisting of a terminal model keyword, a TAC, and a terminal model; According to each second mapping relationship, a terminal model library is constructed.

2. The method according to claim 1, characterized in that Extract the terminal model keyword and TAC corresponding to each call record data, including: Extracting user agent information from the current call log data, and detecting whether the user agent information contains a preset mobile terminal identification name; If yes, extract TAC from the IMEI information in the current call log data, and perform regular matching between the user agent information and the feature rules in the terminal feature library; If the match is successful, the matched content is obtained as the terminal model keyword.

3. The method according to claim 1, characterized in that According to the extraction result, at least one first mapping relationship consisting of a terminal model keyword and a TAC is established, including: According to the extraction results, all terminal model keywords corresponding to each TAC are obtained; If the first TAC corresponds to only a single first terminal model keyword, directly establishing a first mapping relationship between the first TAC and the first terminal model keyword; If the second TAC corresponds to multiple terminal model keywords, the second terminal model keyword is determined from the multiple terminal model keywords according to the occurrence frequencies of the multiple terminal model keywords for the second TAC, and a first mapping relationship between the second TAC and the second terminal model keyword is established.

4. The method according to claim 3, characterized in that Determining a second terminal model keyword from among the plurality of terminal model keywords according to the occurrence frequencies of the plurality of terminal model keywords for the second TAC includes: Among the plurality of terminal model keywords, a terminal model keyword with the highest occurrence frequency for the second TAC is obtained as the second terminal model keyword.

5. The method according to any one of claims 1 to 4, characterized in that: According to each first mapping relationship, a pre-built terminal model keyword interpretation library is queried to establish at least one second mapping relationship consisting of a terminal model keyword, a TAC, and a terminal model, including: Using the terminal model keyword in each first mapping relationship, querying the terminal model keyword interpretation library respectively, wherein the terminal model keyword interpretation library stores the correspondence between the terminal model keyword and the terminal model; If a matching target terminal model is found in the terminal model keyword interpretation library for the target terminal model keyword in the target first mapping relationship, a second mapping relationship is formed according to the target first mapping relationship and the target terminal model.

6. The method according to claim 5, characterized in that After using the terminal model keyword in each first mapping relationship to query the terminal model keyword interpretation library respectively, the method further includes: If the target terminal model keyword in the target first mapping relationship is not found in the terminal model keyword interpretation library, an operation of automatically obtaining the target terminal model matching the target terminal model keyword is performed by using a crawler or calling an artificial intelligence AI interface; When the target terminal model matching the target terminal model keyword is successfully obtained, the corresponding relationship between the target terminal model keyword and the target terminal model is additionally stored in the terminal model keyword interpretation library.

7. The method according to claim 6, characterized in that The method further comprises: Whenever it is detected that the terminal model keyword interpretation library is updated, the pre-built terminal model keyword interpretation library is re-queried according to each first mapping relationship for which the second mapping relationship is not successfully established, so as to try to establish a new second mapping relationship.

8. A device for constructing a mobile network call terminal model library, characterized in that: include: The terminal model keyword and TAC extraction module is used to obtain each call bill data in the online call bill of the mobile network, and respectively extract the terminal model keyword and TAC corresponding to each call bill data; A first mapping relationship establishing module, used to establish at least one first mapping relationship consisting of a terminal model keyword and a TAC according to the extraction result; A second mapping relationship establishment module, used to query a pre-built terminal model keyword interpretation library according to each first mapping relationship, and establish at least one second mapping relationship consisting of a terminal model keyword, a TAC, and a terminal model; The terminal model library construction module is used to construct a terminal model library according to each second mapping relationship.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for constructing a mobile network call terminal model library as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for constructing a mobile network call terminal model library according to any one of claims 1 to 7 when executed.

Images