Method, device and electronic device for constructing user portrait of Internet of Things

By obtaining and analyzing the behavioral operation logs and industry characteristic information of IoT devices, calculating the total characteristic value and aggregation calculation, combined with the time attenuation mechanism, the problem of equipment behavior analysis in different industries is solved, and the accurate construction and commercial value of IoT user portraits is realized. Identify.

CN115658632BActive Publication Date: 2024-11-15CHINA MOBILE M2M +1
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202110766250.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-07-07
Publication Date
2024-11-15
Estimated Expiration
2041-07-07

AI Technical Summary

Technical Problem

The existing technology is difficult to effectively analyze the behavior of IoT devices in different industries, resulting in inaccurate user portrait construction.

Method used

By obtaining the behavioral operation log information and industry characteristic information of the target device, calculate the total characteristic value of the target business operation type, combine the aggregation calculation and time attenuation mechanism of user portrait information, determine the portrait value of the target user, and judge the user's effectiveness based on the portrait value and the distribution of equipment.

Benefits of technology

It has realized targeted analysis of the behavior of IoT devices in different industries, accurately constructed user portraits, identified commercial value, and supported traffic monetization and marketing strategy formulation.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115658632B_ABST
    Figure CN115658632B_ABST
Patent Text Reader

Abstract

The present invention provides a method, device and electronic device for constructing a user portrait of the Internet of Things, and relates to the technical field of the Internet of Things, wherein the method comprises: obtaining the behavior operation log information of a target device, wherein the behavior operation log information comprises the industry to which the target device belongs, the user to which the target device belongs and the target business operation type corresponding to the behavior operation of the target device; obtaining the industry characteristic information corresponding to the industry to which the target device belongs, and obtaining the total characteristic value corresponding to the target business operation type based on the industry characteristic information, wherein the industry characteristic information comprises characteristic values ​​corresponding to multiple business operation types; and determining the target user portrait value of the user to which the target device belongs based on the total characteristic value corresponding to the target business operation type. The embodiment of the present invention can better construct a user portrait of the Internet of Things.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of Internet of Things, and in particular to a method, device and electronic equipment for constructing a user portrait of the Internet of Things. Background Art

[0002] In recent years, the Internet of Things (IoT) technology has developed rapidly, bringing a revolution to the production and lifestyle of human society. There are a large number of intelligent terminal devices in the IoT, and the amount of data generated is also huge. The popularization of cloud computing technology and the construction of cloud infrastructure and platforms have made it possible to manage and analyze these massive devices in real time. With the development of artificial intelligence technology, especially user profiling technology, the potential commercial value behind the data can be mined by analyzing the data of massive devices. As IoT devices have developed into all walks of life, there are large differences in the behavior of IoT devices in different industries. How to effectively analyze the behavior of IoT devices in different industries and build user profiles has become an urgent problem to be solved. Summary of the invention

[0003] The embodiments of the present invention provide a method, device and electronic device for constructing a user portrait of the Internet of Things to solve the problem of how to effectively analyze the behaviors of Internet of Things devices in different industries to construct user portraits.

[0004] To solve the above technical problems, the present invention is achieved as follows:

[0005] In a first aspect, an embodiment of the present invention provides a method for constructing an IoT user portrait, the method comprising:

[0006] Acquire behavior operation log information of a target device, wherein the behavior operation log information includes the industry to which the target device belongs, the user to which the target device belongs, and the target business operation type corresponding to the behavior operation of the target device;

[0007] Acquire industry characteristic information corresponding to the industry to which the target device belongs, and acquire a total characteristic value corresponding to the target business operation type based on the industry characteristic information, wherein the industry characteristic information includes characteristic values ​​corresponding to multiple business operation types;

[0008] A target user portrait value of the user to which the target device belongs is determined based on the total feature value corresponding to the target business operation type.

[0009] Optionally, determining a target user portrait value of a user to which the target device belongs based on the total feature value corresponding to the target business operation type includes:

[0010] Adding the total feature value corresponding to the target business operation type to the user portrait information of the user to which the target device belongs;

[0011] An aggregate calculation is performed based on the total feature value included in the user portrait information and the generation time corresponding to each of the total feature values ​​to obtain a target user portrait value of the user to which the target device belongs.

[0012] Optionally, performing aggregate calculation according to the total feature value included in the user portrait information and the generation time corresponding to each of the total feature values ​​to obtain the target user portrait value of the user to which the target device belongs includes:

[0013] According to the generation time corresponding to each of the total feature values ​​included in the total feature values ​​included in the user portrait information, obtain a first generation time whose time interval with the current moment is greater than a first preset time length and less than a second preset time length;

[0014] determining a first total eigenvalue corresponding to the first generation time;

[0015] determining an attenuation total eigenvalue according to the first total eigenvalue and an attenuation coefficient, wherein the attenuation coefficient is determined based on the time interval;

[0016] According to the generation time corresponding to each of the total characteristic values, a second generation time whose time interval with the current moment is less than or equal to the first preset time length is obtained;

[0017] determining a second total eigenvalue corresponding to the second generation time;

[0018] Among them, the target user portrait value of the user to which the target device belongs is the sum of the attenuation total eigenvalue and the second total eigenvalue.

[0019] Optionally, after determining the target user portrait value of the user to which the target device belongs based on the total feature value corresponding to the target business operation type, the method further includes:

[0020] When the target user portrait value of the user to which the target device belongs is greater than a preset user portrait threshold, determining the user to which the target device belongs as a valid user;

[0021] The target user portrait value of the valid user is stored.

[0022] Optionally, the behavior operation log information also includes an address identifier of the target device;

[0023] After determining the user to which the target device belongs as a valid user, the method further includes:

[0024] A device distribution heat map is generated, wherein the device distribution heat map displays the target user portrait value of the effective user and the address identifier of the target device corresponding to the effective user.

[0025] Optionally, before acquiring the industry characteristic information corresponding to the industry to which the target device belongs, the method further includes:

[0026] receiving a modification input of industry characteristic information corresponding to the industry to which the target device belongs;

[0027] In response to the modification input, updating the industry characteristic information;

[0028] The obtaining of industry characteristic information corresponding to the industry to which the target device belongs includes:

[0029] Get updated industry characteristic information.

[0030] In a second aspect, an embodiment of the present invention provides a device for constructing a user portrait of an Internet of Things, the device comprising:

[0031] A first acquisition module is used to acquire behavior operation log information of a target device, wherein the behavior operation log information includes the industry to which the target device belongs, the user to which the target device belongs, and the target business operation type corresponding to the behavior operation of the target device;

[0032] A second acquisition module is used to acquire industry characteristic information corresponding to the industry to which the target device belongs, and acquire a total characteristic value corresponding to the target business operation type based on the industry characteristic information, wherein the industry characteristic information includes characteristic values ​​corresponding to multiple business operation types;

[0033] The first determination module is used to determine a target user portrait value of a user to which the target device belongs based on a total feature value corresponding to the target business operation type.

[0034] Optionally, the first determining module is specifically configured to:

[0035] An adding unit, configured to add the total feature value corresponding to the target business operation type to the user portrait information of the user to which the target device belongs;

[0036] The calculation unit is used to perform aggregation calculation based on the total feature value included in the user portrait information and the generation time corresponding to each total feature value to obtain the target user portrait value of the user to which the target device belongs.

[0037] Optionally, the computing unit is specifically used for:

[0038] According to the generation time corresponding to each of the total feature values ​​included in the total feature values ​​included in the user portrait information, obtain a first generation time whose time interval with the current moment is greater than a first preset time length and less than a second preset time length;

[0039] determining a first total eigenvalue corresponding to the first generation time;

[0040] determining an attenuation total eigenvalue according to the first total eigenvalue and an attenuation coefficient, wherein the attenuation coefficient is determined based on the time interval;

[0041] According to the generation time corresponding to each of the total characteristic values, a second generation time whose time interval with the current moment is less than or equal to the first preset time length is obtained;

[0042] determining a second total eigenvalue corresponding to the second generation time;

[0043] Among them, the target user portrait value of the user to which the target device belongs is the sum of the attenuation total eigenvalue and the second total eigenvalue.

[0044] Optionally, the device further comprises:

[0045] A second determination module is used to determine the user to which the target device belongs as a valid user when the target user portrait value of the user to which the target device belongs is greater than a preset user portrait threshold;

[0046] A storage module is used to store the target user portrait value of the effective user.

[0047] Optionally, the behavior operation log information also includes an address identifier of the target device;

[0048] The device also includes:

[0049] A generation module is used to generate a device distribution heat map, wherein the device distribution heat map displays the target user portrait value of the effective user and the address identifier of the target device corresponding to the effective user.

[0050] Optionally, the device further comprises:

[0051] A receiving module, used for receiving a modification input of the industry characteristic information corresponding to the industry to which the target device belongs;

[0052] An updating module, for updating the industry characteristic information in response to the modification input;

[0053] The second acquisition module is specifically used for:

[0054] The updated industry characteristic information is obtained, and based on the industry characteristic information, a total characteristic value corresponding to the target business operation type is obtained.

[0055] In a third aspect, an embodiment of the present invention provides an electronic device, comprising: a processor, a memory, and a program stored in the memory and executable on the processor, wherein when the program is executed by the processor, the steps of the method for constructing an IoT user profile as described in the first aspect are implemented.

[0056] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method for constructing an IoT user profile described in the first aspect are implemented.

[0057] In an embodiment of the present invention, behavioral operation log information of a target device is obtained, the behavioral operation log information includes the industry to which the target device belongs, the user to which the target device belongs, and the target business operation type corresponding to the behavioral operation of the target device; industry characteristic information corresponding to the industry to which the target device belongs is obtained, and a total characteristic value corresponding to the target business operation type is obtained based on the industry characteristic information, the industry characteristic information includes total characteristic values ​​corresponding to multiple business operation types; a target user portrait value of the user to which the target device belongs is determined based on the total characteristic value corresponding to the target business operation type. In this way, the behavior of IoT devices in different industries can be analyzed in a targeted manner through the industry characteristic information, so that a better IoT user portrait can be constructed. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0059] Figure 1 It is a flow chart of a method for constructing a user portrait of the Internet of Things provided by an embodiment of the present invention;

[0060] Figure 2 It is a structural schematic diagram of a device for constructing a user portrait of the Internet of Things provided by an embodiment of the present invention;

[0061] Figure 3 It is a structural schematic diagram of another device for constructing a user portrait of the Internet of Things provided by an embodiment of the present invention;

[0062] Figure 4 It is a structural schematic diagram of another device for constructing a user portrait of the Internet of Things provided by an embodiment of the present invention;

[0063] Figure 5 It is a structural schematic diagram of another device for constructing a user portrait of the Internet of Things provided by an embodiment of the present invention;

[0064] Figure 6 It is a structural schematic diagram of another device for constructing a user portrait of the Internet of Things provided by an embodiment of the present invention;

[0065] Figure 7 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0066] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are 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 are within the scope of protection of the present invention.

[0067] In the embodiments of the present invention, a method, device and electronic device for constructing a user portrait of the Internet of Things are proposed to solve the problem of how to effectively analyze the behavior of Internet of Things devices in different industries to construct user portraits.

[0068] See also Figure 1 , Figure 1 is a flow chart of a method for constructing a user portrait of the Internet of Things provided by an embodiment of the present invention, such as Figure 1 As shown, the method comprises the following steps:

[0069] Step 101: Obtain behavior operation log information of a target device, wherein the behavior operation log information includes the industry to which the target device belongs, the user to which the target device belongs, and the target business operation type corresponding to the behavior operation of the target device.

[0070] The target device may be an IoT device, for example, an IoT device managed by an IoT cloud platform. The industry to which the target device belongs may be represented by industry information, and the user to which the target device belongs may be represented by a user ID. The target business operation type may be one or more of a plurality of business operation types, and the plurality of business operation types may include: device login, device subscription to a topic, device upload data, device acquisition of topic data, device reply to topic data, device downlink command, business alarm notification, and device logout, etc. The business operation type may indicate the business functions provided by the IoT cloud platform.

[0071] In addition, the behavior operation log information may also include a device identifier, which is the unique identifier of the target device on the IoT cloud platform. The behavior operation log information may also include a product identifier, which is the product identifier of the target device. The behavior operation log information may also include the IP address of the target device when it logs in. The behavior operation log information may also include the time of the behavior operation of the target device.

[0072] Step 102: Obtain industry characteristic information corresponding to the industry to which the target device belongs, and obtain a total characteristic value corresponding to the target business operation type based on the industry characteristic information, wherein the industry characteristic information includes characteristic values ​​corresponding to multiple business operation types.

[0073] In addition, industry characteristic information of different industries can be stored, and the industry characteristic information can be pre-set. The industry characteristic information corresponding to the industry to which the target device belongs can include characteristic values ​​corresponding to multiple business operation types under the industry to which the target device belongs, and the characteristic value can represent the value occupied by the business operation type. The principle of setting the characteristic value corresponding to the business operation type can be: the higher the frequency of the business function used by the device in the industry, the larger the characteristic value corresponding to the business operation type corresponding to the business function, and the characteristic value corresponding to the business operation type of the device downlink acquisition message can be higher than the characteristic value corresponding to the business operation type of uplink upload data.

[0074] Taking the smart home industry as an example, the services of the devices in the smart home industry are mainly reporting of device monitoring data, issuing control commands, business alarm notifications, etc., and the devices need to be online for a long time. The characteristic values ​​corresponding to the multiple business operation types of the devices in the smart home industry can be defined as follows: the characteristic value corresponding to the device online time is: 1 / hour, the characteristic value corresponding to the device subscription topic is: 3 / item, the characteristic value corresponding to the device upload data is: 0.5 / item, the characteristic value corresponding to the device acquisition topic data is: 0.8 / item, the characteristic value corresponding to the device reply topic data is: 0.5 / item, the characteristic value corresponding to the device downlink command is: 0.8 / item, and the characteristic value corresponding to the trigger alarm is: 0.8 / time. Among them, the device online time can be calculated based on the device login and logout time, and the device online time can be the time difference between the device logout time and the device login time.

[0075] In addition, the total characteristic value corresponding to the target business operation type can be calculated based on the characteristic values ​​corresponding to multiple business operation types. For example, the target business operation type may include 10 hours of device online time, 100 pieces of device uploaded data, 50 device downlink commands, and 10 triggered alarms. The total characteristic value corresponding to the target business operation type can be: 10*1+100*0.5+50*0.8+10*0.8=108. If the number of target devices is 20, and the target business operation types of the 20 devices are the same, the total characteristic value of the target business operation type of the 20 devices is: 20*108=2160.

[0076] Step 103: Determine a target user portrait value of the user to which the target device belongs based on the total feature value corresponding to the target business operation type.

[0077] Among them, the total feature value corresponding to the target business operation type can be added to the user portrait information of the user to which the target device belongs, and aggregation calculation is performed based on the total feature values ​​included in the user portrait information and the generation time corresponding to each total feature value to obtain the target user portrait value of the user to which the target device belongs; or, the total feature value corresponding to the target business operation type can be added to the user portrait information of the user to which the target device belongs, and the total feature values ​​included in the user portrait information are added to obtain the target user portrait value of the user to which the target device belongs.

[0078] It should be noted that the Internet of Things user portrait construction method in the embodiment of the present invention can be applied to the Internet of Things user portrait construction system, which may include Filebeat software for pulling device behavior operation log information from the Internet of Things cloud platform, message queue middleware kafka for caching device behavior operation log information, an industry characteristic management module for configuring and managing industry characteristic information, a user portrait module for determining the target user portrait value of the user to which the target device belongs based on the total characteristic value corresponding to the target business operation type to construct a user portrait, and a portrait result display module for displaying user portrait results.

[0079] In addition, the behavior operation log information of the target device can be obtained through the Filebeat software. The Filebeat software is an open source third-party software and is a lightweight application. It can filter the behavior log of the device from the IoT cloud platform with very little overhead, and has almost no impact on the services of the IoT cloud platform. After the Filebeat software obtains the behavior operation log information of the target device, it can send the behavior operation log information of the target device to the message queue middleware kafka. Kafka is a high-concurrency, low-latency distributed middleware that can cache the behavior operation log information of the target device. The user portrait module can pull the behavior operation log information of the target device from kafka, and can obtain industry feature information from the industry feature management module according to the industry to which the target device belongs, obtain the total feature value corresponding to the target business operation type based on the industry feature information, and determine the target user portrait value of the user to which the target device belongs based on the total feature value corresponding to the target business operation type, thereby profiling the user to which the target device belongs, and can send the target user portrait value and the address identifier of the target device to the portrait result display module. The portrait result display module can store the target user portrait value and the address identifier of the target device, and can provide a query interface for the target user portrait value and an acquisition interface for the address identifier for page display. For example, the portrait result display module can store the target user portrait value and the address identifier of the target device in the database, and provide a corresponding API interface for query and display.

[0080] Furthermore, if the industry characteristic information is stored in the local cache, the industry characteristic information can be directly obtained from the local cache; if the industry characteristic information is not stored in the local cache, the industry characteristic information can be obtained from the industry characteristic management module.

[0081] It should be noted that, at present, when constructing user portraits, only users with a certain obvious feature are identified and profiled. However, at this stage, the application of the Internet of Things has developed to all walks of life, such as the smart home industry, the remote meter reading industry, the industrial Internet of Things industry, etc. The behavior of users under the device in each industry is not exactly the same. For example, the smart home industry focuses on the reporting and early warning of home environment data and the application of issuing device control commands; the remote meter reading industry focuses on the reporting of meter reading data, and the industrial Internet of Things industry focuses on the reporting of device status data and abnormal monitoring. The existing technology only identifies and profiles users with a certain obvious feature and cannot accurately identify valuable users. In an embodiment of the present invention, the total feature value corresponding to the target business operation type is obtained based on the industry feature information, and the target user portrait value of the user to which the target device belongs is determined based on the total feature value corresponding to the target business operation type, so that the target users of different industries in the Internet of Things platform can be identified, the commercial value in the massive data of the Internet of Things can be explored, and data support can be provided for the flow realization, commercial promotion and marketing strategy formulation in the Internet of Things application.

[0082] In an embodiment of the present invention, behavioral operation log information of a target device is obtained, the behavioral operation log information includes the industry to which the target device belongs, the user to which the target device belongs, and the target business operation type corresponding to the behavioral operation of the target device; industry characteristic information corresponding to the industry to which the target device belongs is obtained, and a total characteristic value corresponding to the target business operation type is obtained based on the industry characteristic information, the industry characteristic information includes total characteristic values ​​corresponding to multiple business operation types; a target user portrait value of the user to which the target device belongs is determined based on the total characteristic value corresponding to the target business operation type. In this way, the behavior of IoT devices in different industries can be analyzed in a targeted manner through the industry characteristic information, so that a better IoT user portrait can be constructed.

[0083] Optionally, determining a target user portrait value of a user to which the target device belongs based on the total feature value corresponding to the target business operation type includes:

[0084] Adding the total feature value corresponding to the target business operation type to the user portrait information of the user to which the target device belongs;

[0085] An aggregate calculation is performed based on the total feature value included in the user portrait information and the generation time corresponding to each of the total feature values ​​to obtain a target user portrait value of the user to which the target device belongs.

[0086] Among them, the user portrait information may include multiple total feature values, and the multiple total feature values ​​may include a total feature value determined based on a business operation type corresponding to a historical behavior operation of the target device.

[0087] In addition, the aggregation calculation based on the total feature value included in the user portrait information and the generation time corresponding to each total feature value to obtain the target user portrait value of the user to which the target device belongs may include: according to the generation time corresponding to each total feature value, obtaining a second generation time whose time interval with the current moment is less than or equal to a first preset time length; determining a second total feature value corresponding to the second generation time; wherein the target user portrait value of the user to which the target device belongs is the second total feature value. Alternatively, performing aggregate calculation based on the total feature value included in the user portrait information and the generation time corresponding to each of the total feature values ​​to obtain the target user portrait value of the user to which the target device belongs may include: obtaining a first generation time whose time interval with the current moment is greater than a first preset time length and less than a second preset time length based on the generation time corresponding to each of the total feature values ​​in the total feature value included in the user portrait information; determining a first total feature value corresponding to the first generation time; determining an attenuated total feature value based on the first total feature value and an attenuation coefficient, wherein the attenuation coefficient is determined based on the time interval; obtaining a second generation time whose time interval with the current moment is less than or equal to the first preset time length based on the generation time corresponding to each of the total feature values; determining a second total feature value corresponding to the second generation time; wherein the target user portrait value of the user to which the target device belongs is the sum of the attenuated total feature value and the second total feature value. This embodiment does not limit this.

[0088] In addition, an aggregate calculation may be performed based on the total feature value included in the user portrait information and the generation time corresponding to each of the total feature value to obtain the target user portrait value of the user to which the target device belongs, so that the target user portrait value of the user to which the target device belongs may be updated regularly. For example, an aggregate calculation may be performed based on the total feature value included in the user portrait information and the generation time corresponding to each of the total feature value to obtain the target user portrait value of the user to which the target device belongs once every other day.

[0089] In this implementation, an aggregation calculation is performed based on the total feature value included in the user portrait information and the generation time corresponding to each total feature value to obtain the target user portrait value of the user to which the target device belongs, thereby being able to construct a user portrait based on industry characteristics while also taking into account the impact of time, which is more accurate.

[0090] Optionally, performing aggregate calculation according to the total feature value included in the user portrait information and the generation time corresponding to each of the total feature values ​​to obtain the target user portrait value of the user to which the target device belongs includes:

[0091] According to the generation time corresponding to each of the total feature values ​​included in the total feature values ​​included in the user portrait information, obtain a first generation time whose time interval with the current moment is greater than a first preset time length and less than a second preset time length;

[0092] determining a first total eigenvalue corresponding to the first generation time;

[0093] determining an attenuation total eigenvalue according to the first total eigenvalue and an attenuation coefficient, wherein the attenuation coefficient is determined based on the time interval;

[0094] According to the generation time corresponding to each of the total characteristic values, a second generation time whose time interval with the current moment is less than or equal to the first preset time length is obtained;

[0095] determining a second total eigenvalue corresponding to the second generation time;

[0096] Among them, the target user portrait value of the user to which the target device belongs is the sum of the attenuation total eigenvalue and the second total eigenvalue.

[0097] In addition, the user portrait information may include multiple total feature values, each of which may correspond to a generation time. The first preset duration may be less than the second preset duration. For example, the first preset duration may be 48 hours, 24 hours, or 12 hours, etc. The second preset duration may be 48 hours, or 3*24 hours, or 7*24 hours, etc. For the third total feature value whose time interval between the generation time and the current time is greater than or equal to the second preset duration, it may not be included in the target user portrait value of the user.

[0098] Taking the first preset time length as 24 hours and the second preset time length as 7*24 hours as an example, for the total feature value within the time interval of 24 hours, the total feature value is fully included in the target user portrait value; for the total feature value with a time interval greater than 7*24 hours, it is not included in the target user portrait value; for the total feature value with a time interval greater than 24 hours and less than 7*24 hours, the attenuated total feature value obtained by attenuation according to the attenuation coefficient is included in the target user portrait value. The attenuated total feature value can be the product of the first total feature value and the attenuation coefficient.

[0099] It should be noted that the attenuation coefficient r can be:

[0100]

[0101] Wherein, T is the time interval in hours.

[0102] In this implementation, the sum of the attenuated total eigenvalue and the second total eigenvalue is determined as the target user portrait value of the user to which the target device belongs, so that the target user portrait value can be calculated according to the principle that the longer the generation time is, the lower the value of the total eigenvalue is. Based on timeliness considerations, the target user portrait value can be determined more accurately.

[0103] Optionally, after determining the target user portrait value of the user to which the target device belongs based on the total feature value corresponding to the target business operation type, the method further includes:

[0104] When the target user portrait value of the user to which the target device belongs is greater than a preset user portrait threshold, determining the user to which the target device belongs as a valid user;

[0105] The target user portrait value of the valid user is stored.

[0106] The preset user portrait threshold may be 500, 2000, 3000, etc., which is not limited in this embodiment. Different industries may have different preset user portrait thresholds.

[0107] In this implementation, when the target user portrait value of the user to which the target device belongs is greater than a preset user portrait threshold, the user to which the target device belongs is determined as a valid user; and the target user portrait value of the valid user is stored. In this way, the target user portrait value of the valid user can be retained to provide a reference for formulating marketing strategies and promotions.

[0108] Optionally, the behavior operation log information also includes an address identifier of the target device;

[0109] After determining the user to which the target device belongs as a valid user, the method further includes:

[0110] A device distribution heat map is generated, wherein the device distribution heat map displays the target user portrait value of the effective user and the address identifier of the target device corresponding to the effective user.

[0111] The address identifier may be used to represent a geographical location, or may be used to represent a network address, such as an IP address.

[0112] In this implementation, by generating a device distribution heat map, it is possible to provide a device distribution heat map for different industries, thereby providing a reference for formulating marketing strategies and promotions.

[0113] Optionally, before acquiring the industry characteristic information corresponding to the industry to which the target device belongs, the method further includes:

[0114] receiving a modification input of industry characteristic information corresponding to the industry to which the target device belongs;

[0115] In response to the modification input, updating the industry characteristic information;

[0116] The obtaining of industry characteristic information corresponding to the industry to which the target device belongs includes:

[0117] Get updated industry characteristic information.

[0118] Among them, the industry characteristic information can be stored in the industry characteristic management module. The industry characteristic management module can provide a corresponding remote procedure call (RPC) interface for the user portrait module to query the industry characteristic information, and can also provide a corresponding application programming interface (API) interface for dynamically modifying the industry characteristic information.

[0119] In this implementation, the industry characteristic information can be modified dynamically, so that the industry characteristic information can be modified to fit the actual characteristics of the industry in different periods and stages.

[0120] See also Figure 2 , Figure 2 is a schematic diagram of the structure of a device for constructing a user portrait of an Internet of Things provided by an embodiment of the present invention, such as Figure 2 As shown, the IoT user portrait building device 200 includes:

[0121] The first acquisition module 201 is used to acquire the behavior operation log information of the target device, wherein the behavior operation log information includes the industry to which the target device belongs, the user to which the target device belongs, and the target business operation type corresponding to the behavior operation of the target device;

[0122] A second acquisition module 202 is used to acquire industry characteristic information corresponding to the industry to which the target device belongs, and acquire a total characteristic value corresponding to the target business operation type based on the industry characteristic information, wherein the industry characteristic information includes characteristic values ​​corresponding to multiple business operation types;

[0123] The first determination module 203 is used to determine the target user portrait value of the user to which the target device belongs based on the total feature value corresponding to the target business operation type.

[0124] Optional, such as Figure 3 As shown, the first determining module 203 is specifically used for:

[0125] An adding unit 2031 is used to add the total feature value corresponding to the target business operation type to the user portrait information of the user to which the target device belongs;

[0126] The calculation unit 2032 is used to perform aggregation calculation based on the total feature value included in the user portrait information and the generation time corresponding to each of the total feature values ​​to obtain the target user portrait value of the user to which the target device belongs.

[0127] Optionally, the calculation unit 2032 is specifically used for:

[0128] According to the generation time corresponding to each of the total feature values ​​included in the total feature values ​​included in the user portrait information, obtain a first generation time whose time interval with the current moment is greater than a first preset time length and less than a second preset time length;

[0129] determining a first total eigenvalue corresponding to the first generation time;

[0130] determining an attenuation total eigenvalue according to the first total eigenvalue and an attenuation coefficient, wherein the attenuation coefficient is determined based on the time interval;

[0131] According to the generation time corresponding to each of the total characteristic values, a second generation time whose time interval with the current moment is less than or equal to the first preset time length is obtained;

[0132] determining a second total eigenvalue corresponding to the second generation time;

[0133] Among them, the target user portrait value of the user to which the target device belongs is the sum of the attenuation total eigenvalue and the second total eigenvalue.

[0134] Optional, such as Figure 4 As shown, the device 200 also includes:

[0135] The second determination module 204 is used to determine the user to which the target device belongs as a valid user when the target user portrait value of the user to which the target device belongs is greater than a preset user portrait threshold;

[0136] The storage module 205 is used to store the target user portrait value of the valid user.

[0137] Optionally, the behavior operation log information also includes an address identifier of the target device;

[0138] like Figure 5 As shown, the device 200 also includes:

[0139] The generating module 206 is used to generate a device distribution heat map, wherein the device distribution heat map displays the target user portrait value of the valid user and the address identifier of the target device corresponding to the valid user.

[0140] Optional, such as Figure 6 As shown, the device 200 also includes:

[0141] The receiving module 207 is used to receive a modification input of the industry characteristic information corresponding to the industry to which the target device belongs;

[0142] An updating module 208, for updating the industry characteristic information in response to the modification input;

[0143] The second acquisition module 202 is specifically used for:

[0144] The updated industry characteristic information is obtained, and based on the industry characteristic information, a total characteristic value corresponding to the target business operation type is obtained.

[0145] The IoT user portrait construction device can achieve Figure 1 The various processes implemented in the method embodiment can achieve the same technical effect, and to avoid repetition, they will not be described again here.

[0146] like Figure 7 As shown, an embodiment of the present invention further provides an electronic device 300, including: a processor 301, a memory 302, and a program stored in the memory 302 and executable on the processor 301. When the program is executed by the processor 301, each process of the above-mentioned Internet of Things user portrait construction method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0147] The embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, each process of the above-mentioned method for building a user profile of the Internet of Things is implemented, and the same technical effect can be achieved. To avoid repetition, it is not repeated here. The computer-readable storage medium is, for example, a ROM, RAM, a magnetic disk, or an optical disk.

[0148] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0149] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0150] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation modes, which are merely illustrative rather than restrictive. Under the guidance of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the present invention and the claims, all of which are within the protection of the present invention.

Claims

1. A method for constructing user portraits of the Internet of Things, It is characterized in that The method comprises: Acquire behavior operation log information of a target device, wherein the behavior operation log information includes the industry to which the target device belongs, the user to which the target device belongs, and the target business operation type corresponding to the behavior operation of the target device; Acquire industry characteristic information corresponding to the industry to which the target device belongs, and acquire a total characteristic value corresponding to the target business operation type based on the industry characteristic information, wherein the industry characteristic information includes characteristic values ​​corresponding to multiple business operation types; Determine a target user portrait value of the user to which the target device belongs based on the total feature value corresponding to the target business operation type; The determining, based on the total feature value corresponding to the target business operation type, a target user portrait value of a user to which the target device belongs includes: Adding the total feature value corresponding to the target business operation type to the user portrait information of the user to which the target device belongs; Performing aggregate calculation based on the total feature value included in the user portrait information and the generation time corresponding to each of the total feature values ​​to obtain a target user portrait value of the user to which the target device belongs; The aggregate calculation is performed based on the total feature value included in the user portrait information and the generation time corresponding to each of the total feature values ​​to obtain the target user portrait value of the user to which the target device belongs, including: According to the generation time corresponding to each of the total feature values ​​included in the total feature values ​​of the user portrait information, obtain a first generation time whose time interval with the current moment is greater than a first preset time length and less than a second preset time length; determining a first total eigenvalue corresponding to the first generation time; determining an attenuation total eigenvalue according to the first total eigenvalue and an attenuation coefficient, wherein the attenuation coefficient is determined based on the time interval; According to the generation time corresponding to each of the total characteristic values, a second generation time whose time interval with the current moment is less than or equal to the first preset time length is obtained; determining a second total eigenvalue corresponding to the second generation time; Among them, the target user portrait value of the user to which the target device belongs is the sum of the attenuation total eigenvalue and the second total eigenvalue.

2. The method according to claim 1, It is characterized in that After determining the target user portrait value of the user to which the target device belongs based on the total feature value corresponding to the target business operation type, the method further includes: When the target user portrait value of the user to which the target device belongs is greater than a preset user portrait threshold, determining the user to which the target device belongs as a valid user; The target user portrait value of the valid user is stored.

3. The method according to claim 2, It is characterized in that The behavior operation log information also includes the address identifier of the target device; After determining the user to which the target device belongs as a valid user, the method further includes: A device distribution heat map is generated, wherein the device distribution heat map displays the target user portrait value of the effective user and the address identifier of the target device corresponding to the effective user.

4. The method according to claim 1, It is characterized in that Before acquiring the industry characteristic information corresponding to the industry to which the target device belongs, the method further includes: receiving a modification input of industry characteristic information corresponding to the industry to which the target device belongs; In response to the modification input, updating the industry characteristic information; The obtaining of industry characteristic information corresponding to the industry to which the target device belongs includes: Get updated industry characteristic information.

5. A device for constructing user portraits of the Internet of Things, It is characterized in that The device comprises: A first acquisition module is used to acquire behavior operation log information of a target device, wherein the behavior operation log information includes the industry to which the target device belongs, the user to which the target device belongs, and the target business operation type corresponding to the behavior operation of the target device; A second acquisition module is used to acquire industry characteristic information corresponding to the industry to which the target device belongs, and acquire a total characteristic value corresponding to the target business operation type based on the industry characteristic information, wherein the industry characteristic information includes characteristic values ​​corresponding to multiple business operation types; A first determination module, configured to determine a target user portrait value of a user to which the target device belongs based on a total feature value corresponding to the target business operation type; The first determining module is specifically used for: An adding unit, configured to add the total feature value corresponding to the target business operation type to the user portrait information of the user to which the target device belongs; A calculation unit, configured to perform aggregate calculation according to the total feature value included in the user portrait information and the generation time corresponding to each of the total feature values, to obtain a target user portrait value of the user to which the target device belongs; The computing unit is specifically used for: According to the generation time corresponding to each of the total feature values ​​included in the total feature values ​​of the user portrait information, obtain a first generation time whose time interval with the current moment is greater than a first preset time length and less than a second preset time length; determining a first total eigenvalue corresponding to the first generation time; determining an attenuation total eigenvalue according to the first total eigenvalue and an attenuation coefficient, wherein the attenuation coefficient is determined based on the time interval; According to the generation time corresponding to each of the total characteristic values, a second generation time whose time interval with the current moment is less than or equal to the first preset time length is obtained; determining a second total eigenvalue corresponding to the second generation time; Among them, the target user portrait value of the user to which the target device belongs is the sum of the attenuation total eigenvalue and the second total eigenvalue.

6. An electronic device, It is characterized in that include: A processor, a memory, and a program stored in the memory and executable on the processor, wherein when the program is executed by the processor, the steps of the method for constructing a user portrait of the Internet of Things as described in any one of claims 1 to 4 are implemented.

7. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for constructing an Internet of Things user portrait as described in any one of claims 1 to 4 are implemented.

Citation Information

Patent Citations

  • System used for constructing user figure

    CN106504099A

  • Weight value determination method and device for user point-of-interest and electronic equipment

    CN108133036A

  • User portrait drawing method and device, computer readable storage medium and terminal equipment

    CN112035519A

  • User portrait generation method, device and equipment and computer storage medium

    CN112465598A

  • System and Method for Creating a Virtual Backdrop

    US20150029216A1