User portraying method and device, equipment, medium and product

Abstract

The invention provides a user portraying method and device, equipment, a medium and a product, and relates to the technical field of communication. The method comprises: acquiring attribute information of a user and a plurality of service messages, the service messages being messages sent by a terminal used by the user when executing a service, the service messages comprising a service identifier representing a service type; counting the service identifiers in the plurality of service messages to obtain a service type counting result; and carrying out user portraying according to the business type statistical result and the attribute information of the user. According to the embodiment of the invention, the accuracy of the user portrait information can be improved while the portrait efficiency of the user is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of communication technology, and in particular to a user profiling method, a user profiling device, an electronic device, a computer-readable storage medium, and a computer program product. Background Art

[0002] Usually, when profiling a user, it is necessary to conduct a comprehensive analysis of all collected business messages to obtain user profile information.

[0003] However, due to the huge amount of data in business messages, the server's computing power is increased, which reduces the efficiency of user profiling. At the same time, there is also the problem of inaccurate analysis caused by the huge amount of data, which reduces the accuracy of user profiling. Summary of the invention

[0004] To this end, the present disclosure provides a user profiling method, a user profiling device, an electronic device, a computer-readable storage medium, and a computer program product to solve the problem of how to improve the efficiency of user profiling and improve the accuracy of user profiling.

[0005] In a first aspect, an embodiment of the present disclosure provides a user profiling method, the method comprising: obtaining attribute information of the user and multiple business messages, the business message being a message sent by a terminal used by the user when executing a business, the business message including a business identifier representing the business type; performing statistics on the business identifiers in the multiple business messages to obtain business type statistics; and performing user profiling based on the business type statistics and the user's attribute information.

[0006] In a second aspect, an embodiment of the present disclosure provides a user portrait device, which includes: an acquisition module, used to obtain user attribute information and multiple business messages, the business message is a message sent by a terminal used by the user when executing a business, and the business message includes a business identifier representing the business type; a statistical module, used to count the business identifiers in the multiple business messages to obtain business type statistical results; a portrait module, used to create a user portrait based on the business type statistical results and the user's attribute information.

[0007] In a third aspect, an embodiment of the present disclosure provides an electronic device, comprising: one or more processors; and a memory on which one or more programs are stored. When the one or more programs are executed by one or more processors, the one or more processors implement any one of the user profiling methods in the embodiments of the present disclosure.

[0008] In a fourth aspect, an embodiment of the present disclosure provides a readable storage medium, which stores a computer program. When the computer program is executed by a processor, any one of the user portrait methods in the embodiments of the present disclosure is implemented.

[0009] In a fifth aspect, an embodiment of the present disclosure provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, any one of the user profiling methods in the embodiments of the present disclosure is implemented.

[0010] The user profiling method disclosed in the present invention improves the speed of statistical analysis of business messages by counting the business identifiers in multiple business messages without the need to conduct a comprehensive analysis of each business message. Furthermore, user profiling is performed based on the statistical results of business type and the attribute information of the user, so that the obtained user portrait information can reflect not only the business attributes but also the attribute information of the user, thereby improving the accuracy of the user portrait information while improving the efficiency of user profiling. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The accompanying drawings are used to provide a further understanding of the embodiments of the present disclosure and constitute a part of the specification. Together with the embodiments of the present disclosure, they are used to explain the present disclosure and do not constitute a limitation of the present disclosure. The above and other features and advantages will become more apparent to those skilled in the art by describing detailed example embodiments with reference to the accompanying drawings, in which:

[0012] Figure 1 A schematic diagram showing a flow chart of a user profiling method provided by an embodiment of the present disclosure;

[0013] Figure 2 A block diagram showing a user portrait device provided by an embodiment of the present disclosure is shown;

[0014] Figure 3 A block diagram showing a user portrait system provided by an embodiment of the present disclosure;

[0015] Figure 4 A schematic diagram showing a flow chart of another user profiling method provided by an embodiment of the present disclosure;

[0016] Figure 5 A block diagram of a composition of an electronic device provided by an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0017] The specific embodiments of the present disclosure are described in detail below in conjunction with the accompanying drawings. It should be understood that the specific embodiments described herein are only used to illustrate and explain the present disclosure and are not intended to limit the present disclosure. For those skilled in the art, the present disclosure can be implemented without the need for some of these specific details. The following description of the embodiments is only intended to provide a better understanding of the present disclosure by illustrating examples of the present disclosure.

[0018] In order to make the objectives, technical solutions and advantages of the present disclosure more clear, the embodiments of the present disclosure will be further described in detail below with reference to the accompanying drawings.

[0019] With the development of the Internet and big data technology, in order to achieve better analysis of user behavior and characteristics, user profiling is usually used to obtain profile information of different users. When profiling users, it is usually necessary to conduct a comprehensive analysis of all collected business messages to obtain user profile information.

[0020] However, in order to analyze and process business messages with huge amounts of data, the server's computing power needs to be increased. In addition, there is also the problem of inaccurate analysis due to the large amount of data, which not only reduces the efficiency of user profiling, but also fails to guarantee the accuracy of user profiling.

[0021] In order to solve the above problems, the embodiments of the present disclosure provide a user profiling method, a user profiling device, an electronic device, a computer-readable storage medium and a computer program product to improve the efficiency and accuracy of user profiling.

[0022] In a first aspect, an embodiment of the present disclosure provides a user profiling method.

[0023] Figure 1 A schematic diagram of a user portrait method provided by an embodiment of the present disclosure is shown. The user portrait method can be applied to a user portrait device. Figure 1 As shown, the user profiling method includes but is not limited to the following steps.

[0024] Step S101, obtaining user attribute information and multiple business messages.

[0025] The service message is a message sent by a terminal used by a user when executing a service, and the service message includes a service identifier indicating a service type.

[0026] The services performed by the user using the terminal may include a variety of different service types, such as video services, voice services, SMS services, etc. Correspondingly, the service identifier matches the service type. That is, when the service performed by the user using the terminal is a voice service, the service identifier in the corresponding service message represents the identifier of the voice type; when the service performed by the user using the terminal is a video service, the service identifier in the corresponding service message represents the identifier of the video type; and so on.

[0027] The user's attribute information includes at least one of the following: the mobile phone number corresponding to the terminal, the user's age, the user level, the subscribed data package information, the terminal type, and the monthly communication fee. The above-mentioned user attribute information is only an example, and can be specifically set according to actual needs. Other unspecified user attribute information is also within the scope of protection of this disclosure and will not be repeated here.

[0028] Among them, the user level is the level at which the operator provides communication services to the user. For example, a user level of 1 indicates that the user is an ordinary user; a user level of 2 indicates that the user is an intermediate user, and when handling communication services, the user can have priority over a user with a user level of 1; and so on, multiple different levels can be set according to actual needs.

[0029] The terminal type is information such as the model and brand of the terminal used by the user, so as to analyze the characteristics of the user's use of communication services based on different terminal types.

[0030] Step S102, counting the service identifiers in multiple service messages to obtain service type statistics.

[0031] When counting multiple service messages, only the service identifiers in the service messages need to be counted, without detailed parsing and analysis of each service message, so that the service type statistics can be obtained quickly and accurately.

[0032] For example, when statistics determine that there are 5 voice-type service identifiers, 3 SMS service identifiers, and 2 video-type service identifiers among 10 service messages, the service type statistics result can be determined as follows: the levels of service types executed by users from high to low are: voice service, SMS service, and video service.

[0033] Step S103: Create a user profile based on the business type statistics and the user's attribute information.

[0034] By combining the service type statistics with the user's attribute information, it is possible to comprehensively measure the user's usage characteristics when conducting communication services, and thus accurately profile the user based on the usage characteristics to obtain user profile information that can reflect the user's communication characteristics.

[0035] Furthermore, operators can provide users with more accurate communication services based on the obtained user profile information. For example, if the user profile information indicates that the user tends to use voice services, the corresponding voice package service can be pushed to the user; if the user profile information indicates that the user tends to use data transmission services (such as video download services, etc.), the corresponding data flow package service can be pushed to the user to meet the user's usage needs.

[0036] In this embodiment, by counting the business identifiers in multiple business messages without the need to conduct a comprehensive analysis of each business message, the speed of counting business messages is improved; further, user profiling is performed based on the business type statistical results and the user's attribute information, so that the obtained user portrait information can not only reflect the business attributes, but also reflect the user's attribute information, thereby improving the accuracy of user portrait information while improving the efficiency of user profiling.

[0037] In some exemplary embodiments, the service identifier includes: a main identifier, or a main identifier and a sub-identifier.

[0038] Among them, the main identifier represents the type of the main business, and the sub-identifier represents the type of the sub-business under the main business; the type of the main business includes any one of the following: video business type, text business type, live broadcast business type and audio business type.

[0039] Each main business has multiple sub-businesses. For example, when the main business is a live broadcast business type, the corresponding sub-businesses include: shopping live broadcast type, music live broadcast type, news live broadcast type, game live broadcast type, etc.

[0040] When the main business is a video business type, the corresponding sub-businesses include: film and television drama video business type, science video business type, news video business type, etc.

[0041] Therefore, when counting the service messages executed by the user, the service type executed by the user can be preliminarily determined based on the main identifier, and then the specific service type executed by the user can be further determined through the sub-identifier, thereby accurately locating the service type executed by the user.

[0042] In some exemplary embodiments, the service type statistics result includes the service differentiation corresponding to each service identifier.

[0043] In step S102, the service identifiers in the plurality of service messages are counted to obtain the service type statistics result, which can be implemented in the following manner:

[0044] The number of times each business identifier appears in multiple business messages is counted; the frequency of occurrence of each business identifier is determined according to the number of occurrences corresponding to each business identifier and the total number of all business messages; the frequency of occurrence of each business identifier is smoothed to obtain the business differentiation corresponding to each business identifier.

[0045] The number of occurrences corresponding to each service identifier is the number of times the service identifier appears in multiple service messages collected within the preset time. For example, if the preset time is set to 10 minutes, 20 service messages can be collected per minute, and the service identifier to be counted is the voice service identifier, then the number of times the voice service identifier appears in 200 service messages collected within 10 minutes can be counted.

[0046] Since each service message carries a service identifier, but different service messages carry different service identifiers, the total number of all service messages may also be represented by the total number of all service identifiers appearing in multiple service messages.

[0047] For example, if 100 service messages are collected within a preset time period, it can be determined that the total number of all service messages is 100. Correspondingly, the total number of all service identifiers appearing in the 100 service messages collected within the preset time period is 100.

[0048] The frequency of occurrence of each service identifier may be represented by the quotient of the number of occurrences corresponding to each service identifier and the total number of all service messages.

[0049] For example, if statistics determine that the number of occurrences of a certain service identifier within a preset time length is k, and the total number of all service messages collected within the preset time length is m, then the occurrence frequency of the service identifier is f = k / m, where k is a positive integer and m is an integer greater than or equal to k.

[0050] By smoothing the occurrence frequency of each business identifier, the business differentiation corresponding to each business identifier is obtained to make the statistical data smoother and reduce the occurrence of extreme values.

[0051] The smoothing process can be achieved by removing the maximum and minimum values ​​of the frequency of occurrence of each business identifier, or by averaging the frequency of occurrence of multiple business identifiers. The present disclosure does not impose any restrictions on this. As long as the frequency of occurrence of each business identifier can be smoothed, it can be applied to the present disclosure and will not be repeated here.

[0052] In some exemplary embodiments, the occurrence frequency of each service identifier is smoothed to obtain the service differentiation corresponding to each service identifier, including: taking the reciprocal of the occurrence frequency of each service identifier, and performing a logarithmic operation on the reciprocal of the occurrence frequency to determine the service differentiation corresponding to the service identifier.

[0053] The service differentiation corresponding to the service identifier is used to characterize the degree to which the target service corresponding to the service identifier is distinguished from other services.

[0054] The service differentiation p corresponding to the service identifier is calculated using the formula: p = log (1 / f) = log (m / k). Among them, log () represents logarithmic operation, f represents the frequency of occurrence of any service identifier; m represents the total number of all service identifiers appearing in multiple service messages; k represents the number of times the service identifier appears in multiple service messages.

[0055] When performing logarithmic operations, the base of the logarithm may be set according to actual needs to adapt to the number of service messages obtained, so that the service distinction corresponding to the service identifier finally obtained is more accurate.

[0056] For example, if m is set to 100, k is set to 10, and 10 is determined to be the base of the logarithmic operation, then p=log(100 / 10)=lg10=1.

[0057] By adopting the above processing, the statistical results of the service identification can be smoothed and the occurrence of extreme values ​​can be reduced.

[0058] In some exemplary embodiments, user profiling is performed based on business type statistics and user attribute information, including: marking the terminal used by the user according to the business differentiation corresponding to each business identifier to obtain a business tag of the terminal; and performing user profiling based on the business tag of the terminal and the user's attribute information.

[0059] Among them, through the service differentiation corresponding to each service identifier, the type of service specifically executed by the terminal can be clarified, so that the terminal can be marked, so that the service label of the terminal can reflect the type of the most core service executed by the terminal.

[0060] For example, if the terminal used by the user performs multiple different types of services within a preset time period, the service differentiation corresponding to multiple service identifiers can be obtained, and the service differentiation corresponding to each service identifier can reflect the degree to which the target service corresponding to the service identifier is different from other services. Therefore, by comparing and analyzing the service differentiations corresponding to multiple service identifiers, the service label of the terminal can be determined.

[0061] Furthermore, creating a user profile based on the terminal's service tag and the user's attribute information can more accurately reflect the characteristics of the services performed by the user and the user's general attribute characteristics, making the obtained user profile information more accurate.

[0062] In some exemplary embodiments, the terminal used by the user is marked according to the service differentiation corresponding to each service identifier to obtain a service tag of the terminal, including: sorting the service differentiation corresponding to each service identifier to determine the maximum service differentiation; marking the terminal according to the service identifier corresponding to the maximum service differentiation to obtain the service tag of the terminal.

[0063] Among them, sorting the service differentiation corresponding to each service identifier can reflect the importance of the target service corresponding to each service identifier relative to other services. It can be arranged in descending order or ascending order. It is only necessary to finally obtain the maximum service differentiation value. The maximum service differentiation value can represent the service that is executed the most times (or the highest execution frequency) by the terminal used by the user during the statistical period.

[0064] Then, the terminal is marked according to the service identifier corresponding to the maximum service differentiation value, and the service tag of the terminal is determined, so that the service tag can reflect the characteristics of the service executed by the terminal during the statistical period, which is convenient for subsequent more accurate user profiling.

[0065] In some exemplary embodiments, when the business type includes a shopping type, the method further includes: acquiring payment behavior data corresponding to the terminal; and verifying the user portrait information based on the payment behavior data.

[0066] Among them, the payment behavior data corresponding to the terminal is the behavior data of the terminal paying for the purchased items when performing shopping-type business, such as the fees paid for a merchant as prompted by a text message, and the payment success information fed back by the third-party payment platform (such as including the payment amount, recipient information, etc.).

[0067] Through the payment behavior data, the obtained user portrait information can be verified to determine whether the shopping type of business performed by the user using the terminal within a preset time period (or statistical period) represented by the user portrait information is correct; if the payment behavior data corresponding to the terminal represents that the user using the terminal did not complete the payment after placing an order, it is determined that the user portrait information is inaccurate, and it is necessary to further analyze the obtained business messages to prompt the accuracy of the user portrait.

[0068] In a second aspect, an embodiment of the present disclosure provides a user portrait device.

[0069] Figure 2 FIG. 1 is a block diagram showing a user portrait device provided by an embodiment of the present disclosure. Figure 2 As shown, the user portrait device 200 includes but is not limited to the following modules.

[0070] The acquisition module 201 is used to acquire the attribute information of the user and multiple service messages. The service message is a message sent by the terminal used by the user when executing a service. The service message includes a service identifier indicating the service type.

[0071] A statistics module 202 is used to count the service identifiers in multiple service messages to obtain service type statistics results;

[0072] The portrait module 203 is used to create a user portrait based on the business type statistics and the user's attribute information.

[0073] It should be noted that the user portrait device 200 can implement any user portrait method disclosed in the present invention.

[0074] In this embodiment, the business identifiers in multiple business messages are counted through the statistical module without the need to conduct a comprehensive analysis of each business message, thereby improving the statistical speed of the business messages; further, the portrait module is used to perform user portraits based on the business type statistical results and the user's attribute information, so that the obtained user portrait information can not only reflect the business attributes, but also reflect the user's attribute information, thereby improving the accuracy of the user portrait information while improving the efficiency of the user portrait.

[0075] It is worth mentioning that all modules involved in this embodiment are logic modules. In practical applications, a logic unit can be a physical unit, a part of a physical unit, or a combination of multiple physical units. In addition, in order to highlight the innovative part of the present disclosure, this embodiment does not introduce units that are not closely related to solving the technical problems proposed by the present disclosure, but this does not mean that there are no other units in this embodiment.

[0076] In a third aspect, an embodiment of the present disclosure provides a user portrait system.

[0077] Figure 3 FIG. 1 is a block diagram showing a user portrait system provided by an embodiment of the present disclosure. Figure 3 As shown, the user portrait system includes but is not limited to the following devices: terminal 301, base station 302, portrait server 303, business server 304 and business support server 305.

[0078] The terminal 301 and the base station 302 interact with each other via service messages to process the service.

[0079] The service message includes a service identifier indicating the service type.

[0080] In some embodiments, a service identifier is stored in a message header of each service message, and the service identifier includes a main identifier and a sub-identifier.

[0081] Among them, the main identifier represents the type of the main business, and the sub-identifier represents the type of the sub-business under the main business; the type of the main business includes any one of the following: video business type, text business type, live broadcast business type and audio business type.

[0082] For example, if the service identifier is set to include a main identifier (A1) and a sub-identifier (B1), when the type of the main service represented by A1 is a live broadcast service type, the sub-identifier (B1) may include any one of the following: shopping live broadcast type, music live broadcast type, news live broadcast type, and game live broadcast type.

[0083] In some embodiments, both the main identifier and the sub-identifier may occupy 2 bytes to represent, for example, the main identifier includes: 00: video service type; 01: text service type; 02: live service type; 03: audio service type; ...; etc. Correspondingly, the types of sub-services under the live service type include: 00: shopping type; 01: music type; 02: news type; 03: game type; ...; etc.

[0084] The main logo and sub-logo are combined to represent: 0200: shopping live broadcast type; 0201: music live broadcast type; 0202: news live broadcast type; 0203: game live broadcast type; ...; etc.

[0085] The portrait server 303 is used to count the service identifiers in the multiple service messages obtained, obtain service type statistics, and create a user portrait based on the service type statistics and the user's attribute information.

[0086] The service server 304 is used to provide service messages to the portrait server 303. The service messages are messages sent by the terminal 301 to the base station 302 when executing services.

[0087] The business support server 305 is used to provide the portrait server 303 with attribute information of the user using the terminal 301 .

[0088] The user's attribute information includes at least one of the following: the mobile phone number (PhoneNumber) corresponding to the terminal 301, the user level (User Priority), the subscribed data package information (Plan), the terminal type (Terminaltype) and the monthly communication fee (ARPU). The above-mentioned user attribute information is only an example, which can be specifically set according to actual needs. Other unspecified user attribute information is also within the scope of protection of this disclosure and will not be repeated here.

[0089] Figure 4 A flow chart of another user profiling method provided by an embodiment of the present disclosure is shown. Figure 4 As shown, the user portrait method includes but is not limited to the following steps:

[0090] Step S401 : the portrait server 303 sends a first acquisition request to the business support server 305 .

[0091] The first acquisition request includes the mobile phone number (eg, 186XXXXXXXX) corresponding to the terminal 301 , so as to request the business support server 305 to feed back the attribute information of the user corresponding to the mobile phone number to the portrait server 303 .

[0092] Step S402 : the business support server 305 feeds back a first acquisition response including attribute information of the user to the portrait server 303 .

[0093] The first acquisition response includes attribute information of the user, and the attribute information of the user corresponds to the mobile phone number corresponding to the terminal 301 .

[0094] Step S403: the portrait server 303 creates an initial portrait of the user based on the acquired attribute information of the user.

[0095] The initial portrait of the user may be embodied in the form of a user tag, and the user tag is used to represent information such as the user level of the user.

[0096] Step S404 : the portrait server 303 sends a second acquisition request to the business server 304 .

[0097] The second acquisition request is used to request to obtain the message header information of the service message sent by the terminal 301 within a preset time period.

[0098] Step S405 , the service server 304 feeds back a second acquisition response to the portrait server 303 , where the second acquisition response carries the message header information of the service message sent by the terminal 301 within a preset time period.

[0099] Step S406: the portrait server 303 collects statistics on the message header information of the service messages sent by the terminal 301 within a preset time period to obtain service type statistics results.

[0100] The service type statistics result includes the service differentiation corresponding to each of the service identifiers.

[0101] In the process of counting the message header information of the service message sent by the terminal 301 within a preset time period, it can be implemented in the following way: counting the number of times the service identifier appears in each message header information, and then determining the frequency of occurrence of each service identifier based on the number of occurrences corresponding to each service identifier and the total number of all service messages; smoothing the frequency of occurrence of each service identifier to obtain the service differentiation corresponding to each service identifier.

[0102] Since different service messages carry different service identifiers in their header information, the specific service type of the service performed by the terminal 301 within the preset time period can be determined by counting the number of service identifiers appearing in each header information.

[0103] For example, when "00" representing the video service type appears once, it is determined that the terminal 301 has performed a video service once within the preset duration, and the number of occurrences of the video service can be increased by 1; when "02" representing the live broadcast service type appears once, it is determined that the terminal 301 has performed a live broadcast service once within the preset duration, and the number of occurrences of the live broadcast service can be increased by 1; when "0200" representing the shopping live broadcast type appears once, it is determined that the terminal 301 has performed a live broadcast shopping service once within the preset duration, and the number of occurrences of the live broadcast shopping service can be increased by 1; and so on.

[0104] Furthermore, for each service identifier, the portrait server 303 calculates the ratio of the number of occurrences (k) corresponding to each service identifier and the total number (m) of all service identifiers appearing in multiple service messages, and determines the frequency of occurrence (f) of each service identifier within the pre-examination period. Wherein, f = k / m, k is a positive integer, and m is an integer greater than or equal to k.

[0105] Then, the reciprocal of the occurrence frequency of each service identifier is taken, and a logarithmic operation is performed on the reciprocal of the occurrence frequency to determine the service distinction corresponding to the service identifier.

[0106] For example, the service differentiation corresponding to each service identifier is calculated using the following formula: p=log(1 / f)=log(m / k).

[0107] In some embodiments, if n types of service identifiers appear within a preset time period, and the number of occurrences of each service identifier is kn, then m=k1+k2+…+kn; n is an integer greater than or equal to 1.

[0108] By calculating the service differentiation corresponding to each service identifier, the data can be made smoother, the occurrence of extreme values ​​can be reduced, and the service differentiation corresponding to the service identifier obtained statistically can be made more accurate, which is conducive to distinguishing different service types according to the service differentiation corresponding to the service identifier.

[0109] Furthermore, the service differentiation corresponding to the service identifier can reflect the degree to which the service corresponding to the service identifier is distinguished from other services within a preset time period.

[0110] Step S407, the portrait server 303 sorts the service distinctions corresponding to the service identifiers to determine the maximum service distinction; and labels the terminal according to the service identifier corresponding to the maximum service distinction to obtain the service tag of the terminal.

[0111] Among them, since the service identifier includes the main identifier and the sub-identifier, the service messages can be classified more finely, and the maximum service differentiation value obtained by statistics can characterize the type of the most important service performed by the terminal within the preset time period, so that the terminal is marked according to the service identifier corresponding to the maximum service differentiation value. The type of service performed by the terminal can be more accurately characterized by the obtained service identifier of the terminal, which is conducive to the subsequent accurate profiling of the user according to the service tag of the terminal.

[0112] For example, if statistics determine that the service differentiation corresponding to the shopping live broadcast type (ie, the corresponding service identifier is "0200") is the greatest, it can be determined that the terminal mainly performed the shopping live broadcast service within the preset duration.

[0113] Step S408: the portrait server 303 re-profiles the user according to the user's attribute information and the terminal's service tag to obtain user portrait information.

[0114] Among them, the user portrait information obtained from the user portrait can reflect the type of business performed by the user, as well as the user's attribute information (such as the user's level information, consumption capacity, etc.), which is more convenient for providing users with marketing of different communication products, so that users can obtain communication products that match their usage needs and enhance the user's usage experience.

[0115] In some instances, the portrait server 303 may also verify the user portrait information based on the user's subsequent behavior data. For example, when the business type includes a shopping type, the portrait server 303 obtains the payment behavior data corresponding to the terminal and verifies the user portrait information based on the payment behavior data.

[0116] For example, the portrait server 303 may also verify the user portrait information by interacting with the SMS service center server (not shown) to verify whether the user has received payment behavior data (such as a SMS message carrying payment amount, etc.).

[0117] If the payment behavior data corresponding to the terminal indicates that the terminal has completed the shopping payment, it is determined that the shopping transaction conducted by the user is real and the user portrait information obtained by the user portrait is accurate; otherwise, it is determined that the user portrait information is inaccurate and further user portrait is required.

[0118] In some embodiments, since the user's attribute information changes dynamically, it is necessary to update the user's attribute information at certain intervals and to regularly update the user's portrait information to improve the accuracy of the user's portrait information, thereby more accurately recommending the business or communication services that the user needs.

[0119] In this embodiment, by counting the business identifiers in multiple business messages without conducting a comprehensive analysis of each business message, not only the statistical speed of the business messages is improved, but also the amount of calculation in the user profiling process can be greatly reduced, thereby improving the statistical efficiency of the data; further, user profiling is performed based on the business type statistical results and the user's attribute information, so that the obtained user portrait information can reflect not only the business attributes, but also the user's attribute information, thereby improving the accuracy of the user portrait information while improving the user profiling efficiency.

[0120] In a fourth aspect, the embodiments of the present disclosure provide an electronic device, a computer-readable storage medium, and a computer program product. All of the above can be used to implement any user profiling method in the embodiments of the present disclosure, and the corresponding technical solutions and descriptions are referred to the corresponding records in the method part, which will not be repeated here.

[0121] Figure 5 A block diagram of a composition of an electronic device provided by an embodiment of the present disclosure is shown.

[0122] like Figure 5 As shown, the electronic device includes: at least one processor 501, at least one memory 502, and one or more I / O interfaces 503. The processor 501, the memory 502, and the I / O interface 503 are interconnected via a bus 504. The memory 502 stores one or more computer programs, and the one or more computer programs are executed by at least one processor 501, so that the at least one processor 501 can implement any one of the user portrait methods described in the above embodiments.

[0123] Each module in the above electronic device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0124] The present disclosure also provides a computer-readable storage medium on which a computer program is stored, wherein the computer program implements the above-mentioned user profiling method when executed by a processor / processing core. The computer-readable storage medium may be a volatile or non-volatile computer-readable storage medium.

[0125] The embodiments of the present disclosure also provide a computer program product, including a computer-readable code, or a non-volatile computer-readable storage medium carrying the computer-readable code. When the computer-readable code runs in a processor of an electronic device, the processor in the electronic device executes the above-mentioned user portrait method.

[0126] It will be appreciated by those skilled in the art that all or some of the steps, systems, and functional modules / units in the methods disclosed above may be implemented as software, firmware, hardware, and appropriate combinations thereof. In a hardware implementation, the division between the functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed by several physical components in cooperation. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or may be implemented as hardware, or may be implemented as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on a computer-readable storage medium, which may include a computer storage medium (or a non-transitory medium) and a communication medium (or a temporary medium).

[0127] As is known to those of ordinary skill in the art, the term computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable program instructions, data structures, program modules or other data). Computer storage media include, but are not limited to, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), static random access memory (SRAM), flash memory or other memory technology, portable compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and can be accessed by a computer. In addition, it is known to those of ordinary skill in the art that communication media typically contain computer-readable program instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transmission mechanism, and may include any information delivery medium.

[0128] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0129] The computer program instructions for performing the operation of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. Computer-readable program instructions may be executed completely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may be customized by utilizing the state information of the computer-readable program instructions, and the electronic circuit may execute the computer-readable program instructions, thereby realizing various aspects of the present disclosure.

[0130] The computer program product described herein may be implemented in hardware, software, or a combination thereof. In one optional embodiment, the computer program product is embodied as a computer storage medium, and in another optional embodiment, the computer program product is embodied as a software product, such as a software development kit (SDK), etc.

[0131] Various aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0132] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0133] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0134] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of the module, program segment or instruction includes one or more executable instructions for realizing the specified logical function. In some alternative implementations, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or action, or can be implemented with a combination of special hardware and computer instructions.

[0135] Example embodiments have been disclosed herein, and although specific terms are employed, they are used and should be interpreted only in a general illustrative sense and not for limiting purposes. In some instances, it will be apparent to those skilled in the art that, unless otherwise expressly noted, features, characteristics, and / or elements described in conjunction with a particular embodiment may be used alone or in combination with features, characteristics, and / or elements described in conjunction with other embodiments. Therefore, those skilled in the art will appreciate that various changes in form and detail may be made without departing from the scope of the present disclosure.

Claims

1. A user profiling method, characterized in that: The method comprises: Acquire attribute information of the user and a plurality of service messages, wherein the service message is a message sent by a terminal used by the user when executing a service, and the service message includes a service identifier indicating a service type; Counting the service identifiers in the plurality of service messages to obtain service type statistics; Create a user profile based on the business type statistics and the user's attribute information.

2. The method according to claim 1, characterized in that The service identifier includes: a primary identifier, or a primary identifier and a sub-identifier; Among them, the main identifier represents the type of the main business, and the sub-identifier represents the type of the sub-business under the main business; the type of the main business includes any one of the following: video business type, text business type, live broadcast business type and audio business type.

3. The method according to claim 1, characterized in that The service type statistical result includes the service differentiation corresponding to each of the service identifiers; The process of performing statistics on the service identifiers in the plurality of service messages to obtain service type statistics results includes: Counting the number of times each of the service identifiers appears in the plurality of service messages; Determine the frequency of occurrence of each service identifier according to the number of occurrences corresponding to each service identifier and the total number of all service messages; The occurrence frequency of each of the service identifiers is smoothed to obtain the service distinction corresponding to each of the service identifiers.

4. The method according to claim 3, characterized in that The smoothing process of the occurrence frequency of each of the service identifiers to obtain the service distinction corresponding to each of the service identifiers includes: Taking the reciprocal of the occurrence frequency of each of the service identifiers, and performing a logarithmic operation on the reciprocal of the occurrence frequency to determine the service differentiation corresponding to the service identifier; The service differentiation corresponding to the service identifier is used to characterize the degree to which the target service corresponding to the service identifier is distinguished from other services.

5. The method according to claim 3, characterized in that: The generating a user profile according to the business type statistics and the user's attribute information includes: According to the service distinctions corresponding to the service identifiers, marking the terminal used by the user to obtain a service tag of the terminal; Create a user profile based on the service tag of the terminal and the attribute information of the user.

6. The method according to claim 5, characterized in that The step of marking the terminal used by the user according to the service distinction corresponding to each service identifier to obtain the service label of the terminal includes: Sorting the service differentiations corresponding to the service identifiers to determine the maximum service differentiation; The terminal is marked according to the service identifier corresponding to the maximum service differentiation value to obtain the service tag of the terminal.

7. The method according to any one of claims 1 to 6, characterized in that: In the case where the business type includes a shopping type, the method further includes: Obtaining payment behavior data corresponding to the terminal; The user portrait information is verified based on the payment behavior data.

8. A user portrait device, characterized in that: include: An acquisition module, used to acquire attribute information of a user and a plurality of service messages, wherein the service message is a message sent by a terminal used by the user when executing a service, and the service message includes a service identifier indicating a service type; A statistical module, used to count the service identifiers in the plurality of service messages to obtain service type statistical results; The portrait module is used to create a user portrait based on the business type statistics and the user's attribute information.

9. An electronic device comprising a memory and a processor; the memory stores a computer program that can be executed by the processor, and when the computer program is executed by the processor, it implements the user profiling method as described in any one of claims 1 to 7.

10. A computer-readable medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the user profiling method according to any one of claims 1 to 7.

11. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the user profiling method according to any one of claims 1 to 7 is implemented.

Images