Home portrait construction method and device, equipment, medium and program product
Through the neural network model, we can identify the operating duration and Internet access information of home network equipment, build a family portrait, solve the problems of insufficient comprehensiveness and error in the construction of home portraits in the existing technology, realize low-cost and accurate home portraits, and improve the network The accuracy of marketing and maintenance services.
Patent Information
- Application Number
- CN202410963545.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-18
- Publication Date
- 2024-11-22
Smart Images

Figure CN119011999A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of network communication technology, and in particular to a family portrait construction method, device, equipment, medium and program product. Background Art
[0002] The existing technical solutions for constructing family portraits include a solution for determining the identity of family users based on specific home router identification screening and constructing a family portrait by extracting user features. However, this solution has the problem that the constructed family portrait is not comprehensive enough; it also includes a solution for generating a family portrait based on collecting all the fixed networked device information and mobile networked device information of the entire family. However, this solution will have errors when judging whether a network device is a home router by using methods such as longitude and latitude, overlap of mobile networked devices, and physical distance, and when judging whether a network device and a home router belong to the same family, thereby causing errors in the generated family portrait; and it also includes a solution for generating family portraits based on dedicated hardware, such as cameras, human body sensing modules, Internet behavior management devices, etc., but this solution has the problem of high cost. Summary of the invention
[0003] The purpose of the technical solution of the present invention is to provide a family portrait construction method, device, equipment, medium and program product, which are used to solve the problems of insufficient comprehensiveness, errors and high cost in constructing family portraits in the prior art.
[0004] To achieve the above object, the present invention is achieved by:
[0005] In a first aspect, an embodiment of the present invention provides a family portrait construction method, comprising:
[0006] Identify the home network perception data of each home network device of the user through the first neural network model to obtain the manual operation time of each home network device;
[0007] Creating a profile of each of the home network devices based on device information, Internet access information, and manual operation duration of each of the home network devices;
[0008] A family portrait of the user is established according to the portrait of each of the home network devices and the weight corresponding to each of the home network devices.
[0009] Optionally, the family portrait building method, wherein building the family portrait of the user according to the portrait of each of the home network devices and the weight corresponding to each of the home network devices, comprises:
[0010] Identify the home network perception data of the plurality of home network devices of the user by using a second neural network model to obtain the home time of the user;
[0011] A home portrait of the user is established according to the time the user spends at home, the portrait of each of the home network devices, and the weight corresponding to each of the home network devices.
[0012] Optionally, in the family portrait construction method, the weight corresponding to each of the home network devices is determined based on the manual operation duration, manual operation frequency and Internet traffic in the Internet access information of each of the home network devices.
[0013] Optionally, the family portrait construction method further comprises:
[0014] The home network perception data is obtained based on at least one of the following:
[0015] Changes in network topology;
[0016] Changes in device connection status;
[0017] Condition of the room where the equipment is located;
[0018] User online behavior information;
[0019] Internet access quality data;
[0020] Device dialing test status.
[0021] Optionally, the family portrait construction method further comprises:
[0022] At intervals of a preset time, obtaining a network topology of the user according to device information of each of the plurality of home network devices;
[0023] According to the network topology of the user at different times, the change of the network topology is obtained.
[0024] Optionally, the method for constructing a family portrait, wherein the network topology of the user is obtained according to the device information of each of the plurality of home network devices, comprises:
[0025] Matching device information between the plurality of home network devices to obtain a device association analysis result, wherein the device association analysis result is used to indicate a second home network device associated with a first home network device, wherein the first home network device is one of the plurality of home network devices, and the second home network device is a home network device other than the first home network device among the plurality of home network devices;
[0026] According to the device association analysis result, the network topology of the user is obtained.
[0027] In a second aspect, an embodiment of the present invention further provides a family portrait construction device, including:
[0028] A first acquisition module is used to identify the home network perception data of each home network device of the user through a first neural network model, and obtain the manual operation time of each home network device;
[0029] A first establishing module is used to establish a portrait of each of the home network devices according to device information, Internet access information and manual operation duration of each of the home network devices;
[0030] The second establishing module is used to establish the family portrait of the user according to the portrait of each of the home network devices and the weight corresponding to each of the home network devices.
[0031] In a third aspect, an embodiment of the present invention further provides a family portrait construction 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 family portrait construction method as described in the first aspect is implemented.
[0032] In a fourth aspect, an embodiment of the present invention further provides a readable storage medium having a program stored thereon, and when the program is executed by a processor, the family portrait construction method as described in the first aspect is implemented.
[0033] In a fifth aspect, an embodiment of the present invention further provides a computer program product, comprising computer instructions, which, when executed by a processor, implement the family portrait construction method as described in the first aspect.
[0034] The beneficial effects of the above technical solution of the present invention are as follows:
[0035] The family portrait construction method described in the embodiment of the present invention is adopted to identify the home network perception data of each home network device of the user through the first neural network model, and obtain the manual operation time of each home network device; according to the device information, Internet access information and manual operation time of each home network device, a portrait of each home network device is established; according to the portrait of each home network device and the weight corresponding to each home network device, a family portrait of the user is established. In this way, a comprehensive and accurate family portrait can be constructed at a relatively low cost, so that the constructed family portrait can improve the efficiency and effect of network marketing, realize precision marketing, and provide accurate installation and maintenance recommendation information to installation and maintenance personnel to realize precision service. BRIEF DESCRIPTION OF THE DRAWINGS
[0036] Figure 1 A schematic diagram of the process of constructing a family portrait according to an embodiment of the present invention;
[0037] Figure 2 This is a schematic diagram of the structure of the first neural network model according to an embodiment of the present invention;
[0038] Figure 3 A schematic diagram of a process of one implementation of the method for constructing a family portrait according to an embodiment of the present invention;
[0039] Figure 4 This is a schematic diagram of the structure of the second neural network model according to an embodiment of the present invention;
[0040] Figure 5 A schematic diagram of a process of another implementation of the method for constructing a family portrait according to an embodiment of the present invention;
[0041] Figure 6 This is a structural block diagram of a family portrait building device according to an embodiment of the present invention;
[0042] Figure 7 A schematic diagram of the hardware structure of the family portrait building device described in an embodiment of the present invention. DETAILED DESCRIPTION
[0043] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.
[0044] The embodiment of the present invention, as Figure 1 As shown, a family portrait construction method is provided, comprising:
[0045] Step 101: Identify the home network perception data of each home network device of the user through a first neural network model to obtain the manual operation time of each of the home network devices.
[0046] Home network perception data includes multiple feature data, which come from device feature data and Internet access feature data. The Internet access feature data includes Internet access behavior feature data and Internet access quality feature data. Among them, device feature data includes device type, device manufacturer, device model, device status change, device network connection signal strength change, device dialing status, device network topology change, device connection frequency of home network, etc. Internet access behavior feature data includes Internet access time, Internet access traffic and access URL (Uniform Resource Location). Internet access quality feature data includes website first byte response delay and website first screen buffering time, etc.
[0047] Before obtaining the human operation duration of each home network device, the family portrait construction method described in the embodiment of the present invention needs to first obtain the human operation behavior of each home network device, and then obtain the duration of the human operation behavior, that is, the human operation duration.
[0048] Specifically, the home network perception data of each home network device of the user (for example, feature data 1, feature data 2, ..., feature data n of home network device 1) is input into the Figure 2 The input layer of the first neural network model shown in the figure extracts deep features in the hidden layer of the first neural network model to identify whether the operation behavior corresponding to the home network perception data is a human operation behavior or a non-human operation behavior (i.e., obtaining the human operation behavior of each home network device), thereby outputting the human operation duration in the output layer of the first neural network model. Of course, the non-human operation duration can also be output in the output layer of the first neural network model.
[0049] In an embodiment of the present invention, the family portrait construction method can be applied to a cloud data analysis system. By identifying the family network perception data through the first neural network model, the recognition accuracy and generalization ability of human operation behavior can be improved.
[0050] Step 102: Create a profile of each home network device based on the device information, Internet access information, and manual operation duration of each home network device.
[0051] The device information and Internet access information described in the embodiment of the present invention can be collected through a home data collection module, such as a gateway, a set-top box, and a soft probe in the user's home network, without the need to purchase additional equipment, and the cost is low.
[0052] The device information includes: device name, device MAC (Media Access Control) address, uplink device MAC address, device type, device model, device manufacturer, and device connection status, etc. The device MAC address and uplink device MAC address are obtained from the cloud database.
[0053] Internet access information includes: Internet access preferences, Internet access quality data, Internet access traffic, and visited URLs, etc.
[0054] The portrait of each home network device can include multiple first-level tags, such as family member structure, Internet preferences, and device network quality.
[0055] The family member structure includes two secondary labels: age range of family members (for example, if the device type is a children's smart watch, smart learning machine, etc., then the family members include children; for example, if the device type is a smart blood pressure meter, smart blood glucose meter, and smart bracelet, etc., then the family members include the elderly; for example, if the device type is a projector, gaming device, etc., then the family members include teenagers); whether it is a temporary visitor (by identifying the number of times the home network device appears in the home network, determine whether the home network device is a temporary visitor).
[0056] Internet access preferences include five secondary tags: content preference (by comparing the URL feature library, identifying the type of access URL of the home network device, and obtaining the content preference of the home network device. The URL feature library can be obtained from the cloud database); device usage preference (by identifying the preference of the home network device used by the user when surfing the Internet through device type, device model and device manufacturer, for example, identifying whether the user prefers to watch live videos on a mobile phone or on a TV); Internet location preference (by analyzing the network topology, access URL and Internet traffic, etc., identifying the Internet location preference of the home network device, for example, in which room the user prefers to watch videos online); active time (by analyzing the active time of the home network device through the manual operation time of the home network device); Internet duration (by analyzing the Internet duration of the home network device through the manual operation time of the home network device).
[0057] Device network quality, obtained through Internet quality data in Internet access information.
[0058] Step 103: Establish a family portrait of the user according to the portrait of each of the home network devices and the weight corresponding to each of the home network devices.
[0059] Each home network device corresponds to a weight, such as Figure 3 FIG. 1 is a flow chart of one implementation of the method for constructing a family portrait according to an embodiment of the present invention. Figure 3 As shown, the users include home network device 1, home network device 2, home network device 3...home network device n, home network device 1 corresponds to weight 1, home network device 2 corresponds to weight 2, home network device 3 corresponds to weight 3...home network device n corresponds to weight n.
[0060] It should be noted that the user's family portrait includes multiple first-level tags, such as family attributes, family member structure, Internet preferences, consumption preferences, income level and home network quality.
[0061] Furthermore, each primary tag includes multiple secondary tags. Here, an example is given for the secondary tags included in each primary tag:
[0062] Home attributes include two secondary tags: home address (obtained through the installation and maintenance information database, which can be obtained from the cloud database and stores the mapping relationship between the home installation and maintenance address and the equipment serial number); home network bandwidth (obtained through the home bandwidth network registration address mapping library, which can be obtained from the cloud database).
[0063] The family member structure includes three secondary tags: the number of family members (obtained through the number of devices, device types, Internet preferences and active time. For example, a children's smart watch means that there is a child in the family); the age range of family members (obtained through the age range of family members in the portrait of each home network device and the corresponding weight of each home network device); whether the family member is a temporary visitor (obtained through whether the family member is a temporary visitor in the portrait of each home network device and the corresponding weight of each home network device).
[0064] Internet access preferences include five secondary tags: content preference (obtained by comparing the URL feature library and identifying the type of accessed URL); device usage preference (obtained through the device usage preference in the portrait of each home network device and the weight corresponding to each home network device); Internet access location preference (obtained through the Internet access location preference in the portrait of each home network device and the weight corresponding to each home network device); active time (obtained through the active time in the portrait of each home network device and the weight corresponding to each home network device); Internet access duration (obtained through the Internet access duration in the portrait of each home network device and the weight corresponding to each home network device).
[0065] Consumption preferences include two secondary labels: device manufacturer preference (identifying the user's consumption level and brand preference through device type, device model and device manufacturer, for example, judging the user's preferred brand through correlation analysis of mobile phone, computer and smart watch brands); consumption level (identifying the user's consumption level through the frequency of device upgrades).
[0066] Income level includes a secondary label: the income level of the household’s community (identifying the income level by identifying the number of networking routers, determining the number and type of rooms, and thus estimating the household area and the household’s community).
[0067] The home network quality is obtained through the device network quality in the portrait of each home network device and the corresponding weight of each home network device.
[0068] In one implementation mode, optionally, establishing a family portrait of the user according to the portrait of each home network device and the weight corresponding to each home network device includes:
[0069] Identify the home network perception data of the plurality of home network devices of the user by using a second neural network model to obtain the home time of the user;
[0070] A home portrait of the user is established according to the time the user spends at home, the portrait of each of the home network devices, and the weight corresponding to each of the home network devices.
[0071] Specifically, the home network perception data of the user's n home network devices (e.g., feature data 1, feature data 2 ... feature data d of home network device 1, feature data 1 ... feature data d of home network device 2, ..., feature data 1 ... feature data d of home network device n) are input as follows: Figure 4 The input layer of the second neural network model shown in the figure extracts deep features in the hidden layer of the second neural network model to identify whether someone is at home, so as to output the length of time spent at home in the output layer of the second neural network model. Of course, the number of people at home can also be output in the output layer of the second neural network model.
[0072] A more comprehensive family portrait is constructed by the second neural network model. The first-level label of family attributes of the family portrait can also include a second-level label: the length of time spent at home.
[0073] In an embodiment of the present invention, the first neural network model and the second neural network model may adopt the same neural network model, such as a feedforward neural network model. The neural network model includes an input layer, one or more hidden layers, and an output layer. Before the home network perception data is recognized by the neural network model, training may be performed by a back propagation algorithm, etc., and a gradient descent optimization algorithm may be used to speed up the training process.
[0074] Since users' online operation behaviors have certain regularity, the neural network model can be trained regularly.
[0075] In one implementation manner, optionally, the weight corresponding to each of the home network devices is determined according to the manual operation duration, manual operation frequency and Internet traffic in the Internet access information of each of the home network devices.
[0076] Since users' operational behaviors when using home network devices conform to the power-law distribution, and most of users' operational behaviors occur on some home network devices, these home network devices can better reflect users' Internet access preferences, consumption preferences, etc. Therefore, when establishing a user's family portrait, each home network device can be given a weight based on its device information, Internet access information, and manual operation time.
[0077] In the embodiment of the present invention, the calculation formula of the weight m of the home network device m among the n home network devices of the user is as follows:
[0078] Weight m = [human operation frequency, human operation duration, Internet traffic] of home network device m / [human operation frequency, human operation duration, Internet traffic] of n home network devices.
[0079] In one embodiment, optionally, the method further comprises:
[0080] The home network perception data is obtained based on at least one of the following:
[0081] Changes in network topology;
[0082] Changes in device connection status;
[0083] Condition of the room where the equipment is located;
[0084] User online behavior information;
[0085] Internet access quality data;
[0086] Device dialing test status.
[0087] In an embodiment of the present invention, a home network perception technology may be used to perceive at least one of the above items, and based on the perceived at least one of the above items, home network perception data may be acquired.
[0088] Among them, changes in network topology can be obtained by sensing device information; changes in device connection status can be obtained by sensing the status of home network devices or the network connection signal strength, such as sensing that the home network device switches from sleep state to wake-up state, sensing changes in the network connection signal strength of the home network device, etc.
[0089] The room where the device is located can be identified by connecting the terminal to the router of the FTTR (Fiber to The Room) network.
[0090] User online behavior information is collected through the home data collection module, such as changing TV program playback behavior, installing new application packages, voice remote control recognition behavior, and Internet traffic.
[0091] Internet access quality data is collected through the home data collection module, such as the buffering time of the first screen of video and the connection delay when accessing a web page.
[0092] Device dialing test status: Actively dial home network devices through home intranet IP, identify the status of home network devices on demand, and obtain the status start time and status end time.
[0093] In one embodiment, optionally, the method further comprises:
[0094] At intervals of a preset time, obtaining a network topology of the user according to device information of each of the plurality of home network devices;
[0095] According to the network topology of the user at different times, the change of the network topology is obtained.
[0096] It should be noted that the above-mentioned technology of obtaining the network topology of the user at each preset time interval to thereby obtain the network topology change situation is the home network perception technology for obtaining the network topology change situation.
[0097] In one implementation manner, optionally, acquiring the network topology of the user according to the device information of each of the plurality of home network devices includes:
[0098] Matching device information between the plurality of home network devices to obtain a device association analysis result, wherein the device association analysis result is used to indicate a second home network device associated with a first home network device, wherein the first home network device is one of the plurality of home network devices, and the second home network device is a home network device other than the first home network device among the plurality of home network devices;
[0099] According to the device association analysis result, the network topology of the user is obtained.
[0100] In an embodiment of the present invention, the device information includes an uplink device MAC address, a device MAC address, a device IP address, and a device name. Specifically, matching the device information between multiple home network settings includes one of the following methods:
[0101] The MAC address of the upstream device is accurately matched, and the MAC address of each home network device is matched with the MAC address of the LAN port of the gateway or router;
[0102] The device MAC address fuzzy matching method matches the sixth values of the device MAC addresses of any two home network devices among the multiple home network devices. If the difference between the device MAC addresses of the two home network devices is within a preset threshold range, the two home network devices are considered to be associated;
[0103] Device IP address matching method, matching the device IP address of each home network device with the IP address of the networking router;
[0104] The device name matching method matches the device names of multiple home network devices, the names of the devices connected to the gateway, and the device names of the networking routers.
[0105] It should be noted that when matching device information between multiple home network devices, the first step is to use the MAC address of the upstream device or the MAC address of the device. If these two matching methods fail, the device IP address matching method is used. If this matching method also fails, the device name matching method is used as the last step. Figure 5 This is a flow chart of another implementation of the method for constructing a family portrait according to an embodiment of the present invention. According to this embodiment, the method for constructing a family portrait includes the following steps:
[0106] Step 501: collect device information and Internet access information of each home network device of the user through a home data collection module.
[0107] Step 502: The home data analysis module performs association analysis between the multiple home network devices based on the device information of the multiple home network devices to obtain the network topology of the user.
[0108] Step 503, the cloud data identification module obtains the home network perception data based on the user's network topology, and uses the neural network model to identify the home network perception data of each home network device to obtain the manual operation time of each home network device.
[0109] Step 504: Use the pre-processed data to regularly train the neural network model, and use the trained neural network model for recognition.
[0110] Step 505, obtain the mapping library of the device MAC address, the home bandwidth network registration address, the URL feature library, the home installation address and the device serial number.
[0111] Step 506, the cloud data analysis module creates a portrait of each home network device based on the device information, Internet access information and manual operation time of each home network device, as well as the device MAC address, home bandwidth network registration address mapping library, URL feature library, home installation and maintenance address and device serial number mapping library, and creates a user's home portrait based on the portrait of each home network device and the corresponding weight of each home network device.
[0112] Step 507, using family portraits to achieve precision marketing and provide training data for the neural network model.
[0113] In summary, the family portrait construction method described in the embodiment of the present invention is adopted, the home network perception technology is used to obtain home network perception data, and the first neural network model is used for identification to obtain the manual operation time, so as to establish the user's family portrait based on the manual operation time, device information and Internet access information. The constructed family portrait is comprehensive and accurate, and the cost is low, which provides support for the operator's precision marketing and personalized recommendations.
[0114] like Figure 6 As shown, the embodiment of the present invention further provides a family portrait construction device, including:
[0115] A first acquisition module 601 is used to identify the home network perception data of each home network device of the user through a first neural network model, and obtain the manual operation time of each home network device;
[0116] A first establishing module 602 is used to establish a portrait of each of the home network devices according to the device information, Internet access information and manual operation duration of each of the home network devices;
[0117] The second establishing module 603 is used to establish the family portrait of the user according to the portrait of each of the home network devices and the weight corresponding to each of the home network devices.
[0118] Optionally, in the family portrait building device, the second building module 603 is specifically used to:
[0119] Identify the home network perception data of the plurality of home network devices of the user by using a second neural network model to obtain the home time of the user;
[0120] A home portrait of the user is established according to the time the user spends at home, the portrait of each of the home network devices, and the weight corresponding to each of the home network devices.
[0121] Optionally, in the family portrait constructing device, the weight corresponding to each of the home network devices is determined based on the manual operation duration, manual operation frequency and Internet traffic in the Internet access information of each of the home network devices.
[0122] Optionally, the family portrait construction device further comprises:
[0123] A second acquisition module is configured to acquire the home network perception data based on at least one of the following:
[0124] Changes in network topology;
[0125] Changes in device connection status;
[0126] Condition of the room where the equipment is located;
[0127] User online behavior information;
[0128] Internet access quality data;
[0129] Device dialing test status.
[0130] Optionally, the family portrait construction device further comprises:
[0131] A third acquisition module is used to acquire the network topology of the user according to the device information of each of the plurality of home network devices at intervals of a preset duration;
[0132] The fourth acquisition module is used to acquire the network topology change according to the network topology of the user at different times.
[0133] Optionally, in the family portrait building device, the third acquisition module is specifically used to:
[0134] Matching device information between the plurality of home network devices to obtain a device association analysis result, wherein the device association analysis result is used to indicate a second home network device associated with a first home network device, wherein the first home network device is one of the plurality of home network devices, and the second home network device is a home network device other than the first home network device among the plurality of home network devices;
[0135] According to the device association analysis result, the network topology of the user is obtained.
[0136] The family portrait construction device provided in the embodiment of the present invention can execute the above-mentioned family portrait construction method embodiment, and its implementation principle and technical effect are similar, which will not be repeated in this embodiment.
[0137] like Figure 7 As shown, the family portrait construction device of an embodiment of the present invention includes: a processor 701; and a memory 702 connected to the processor 701 through a bus interface, the memory 702 is used to store programs and data used by the processor 701 when performing operations, and the processor 701 calls and executes the programs and data stored in the memory 702.
[0138] The processor 701 is used to read the program in the memory 702 and execute the following process:
[0139] Identify the home network perception data of each home network device of the user through the first neural network model to obtain the manual operation time of each home network device;
[0140] Creating a profile of each of the home network devices based on device information, Internet access information, and manual operation duration of each of the home network devices;
[0141] A family portrait of the user is established according to the portrait of each of the home network devices and the weight corresponding to each of the home network devices.
[0142] The transceiver 703 is used to receive and send data in the controller of the processor 701.
[0143] Among them, Figure 7 In the embodiment, the bus architecture may include any number of interconnected buses and bridges, specifically one or more processors represented by processor 701 and various circuits of memory represented by memory 702 are linked together. The bus architecture may also link together various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface. The transceiver 703 may be a plurality of components, namely, a transmitter and a transceiver, providing a unit for communicating with various other devices on a transmission medium. For different user devices, the user interface 704 may also be an interface capable of externally and internally connecting required devices, and the connected devices include but are not limited to a keypad, a display, a speaker, a microphone, a joystick, and the like.
[0144] The processor 701 is responsible for managing the bus architecture and general processing, and the memory 702 can store data used by the processor 701 when performing operations.
[0145] Optionally, the processor 701 is specifically configured to read the computer program and execute the following steps:
[0146] Identify the home network perception data of the plurality of home network devices of the user by using a second neural network model to obtain the home time of the user;
[0147] A home portrait of the user is established according to the time the user spends at home, the portrait of each of the home network devices, and the weight corresponding to each of the home network devices.
[0148] Optionally, the weight corresponding to each of the home network devices is determined according to the manual operation duration, manual operation frequency and Internet traffic in the Internet access information of each of the home network devices.
[0149] Optionally, the processor 701 is further configured to read the computer program and execute the following steps:
[0150] The home network perception data is obtained based on at least one of the following:
[0151] Changes in network topology;
[0152] Changes in device connection status;
[0153] Condition of the room where the equipment is located;
[0154] User online behavior information;
[0155] Internet access quality data;
[0156] Device dialing test status.
[0157] Optionally, the processor 701 is further configured to read the computer program and execute the following steps:
[0158] At intervals of a preset time, obtaining a network topology of the user according to device information of each of the plurality of home network devices;
[0159] According to the network topology of the user at different times, the change of the network topology is obtained.
[0160] Optionally, the processor 701 is specifically configured to read the computer program and execute the following steps:
[0161] Matching device information between the plurality of home network devices to obtain a device association analysis result, wherein the device association analysis result is used to indicate a second home network device associated with a first home network device, wherein the first home network device is one of the plurality of home network devices, and the second home network device is a home network device other than the first home network device among the plurality of home network devices;
[0162] According to the device association analysis result, the network topology of the user is obtained.
[0163] A specific embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps in the above-mentioned family portrait construction method are implemented and the same technical effect can be achieved. To avoid repetition, it will not be described here.
[0164] In addition, an embodiment of the present invention further provides a computer program product, including computer instructions, which, when executed by a processor, implement the above Figure 1 The various processes of the method embodiment shown can achieve the same technical effect, and will not be described again here to avoid repetition.
[0165] In the several embodiments provided in the present application, it should be understood that the disclosed methods and devices can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0166] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may be physically included separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional units.
[0167] The above-mentioned integrated unit implemented in the form of a software functional unit can be stored in a computer-readable storage medium. The above-mentioned software functional unit is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform some steps of the sending and receiving methods described in various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store program codes.
[0168] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.
Claims
1. A method for constructing a family portrait, characterized in that: include: Identify the home network perception data of each home network device of the user through the first neural network model to obtain the manual operation time of each home network device; Creating a profile of each of the home network devices based on device information, Internet access information, and manual operation duration of each of the home network devices; A family portrait of the user is established according to the portrait of each of the home network devices and the weight corresponding to each of the home network devices.
2. The family portrait construction method according to claim 1, characterized in that: Establishing a family portrait of the user according to the portrait of each of the home network devices and the weight corresponding to each of the home network devices includes: Identify the home network perception data of the plurality of home network devices of the user by using a second neural network model to obtain the home time of the user; A home portrait of the user is established according to the time the user spends at home, the portrait of each of the home network devices, and the weight corresponding to each of the home network devices.
3. The family portrait construction method according to claim 1 or 2, characterized in that: The weight corresponding to each of the home network devices is determined according to the manual operation duration, manual operation frequency and Internet traffic in the Internet access information of each of the home network devices.
4. The method for constructing a family portrait according to claim 1, characterized in that: The method further comprises: The home network perception data is obtained based on at least one of the following: Changes in network topology; Changes in device connection status; Condition of the room where the equipment is located; User online behavior information; Internet access quality data; Device dialing test status.
5. The family portrait construction method according to claim 4, characterized in that: The method further comprises: At intervals of a preset time, obtaining a network topology of the user according to device information of each of the plurality of home network devices; According to the network topology of the user at different times, the change of the network topology is obtained.
6. The method for constructing a family portrait according to claim 5, characterized in that: Acquiring the network topology of the user according to the device information of each of the plurality of home network devices, comprising: Matching device information between the plurality of home network devices to obtain a device association analysis result, wherein the device association analysis result is used to indicate a second home network device associated with a first home network device, wherein the first home network device is one of the plurality of home network devices, and the second home network device is a home network device other than the first home network device among the plurality of home network devices; According to the device association analysis result, the network topology of the user is obtained.
7. A family portrait construction device, characterized in that: include: A first acquisition module is used to identify the home network perception data of each home network device of the user through a first neural network model, and obtain the manual operation time of each home network device; A first establishing module, for establishing a portrait of each of the home network devices according to device information, Internet access information and manual operation duration of each of the home network devices; The second establishing module is used to establish the family portrait of the user according to the portrait of each of the home network devices and the weight corresponding to each of the home network devices.
8. A family portrait construction device, characterized in that: include: A processor, a memory, and a program stored in the memory and executable on the processor, wherein the program, when executed by the processor, implements the family portrait construction method as described in any one of claims 1 to 6.
9. A readable storage medium, characterized in that: The readable storage medium stores a program, and when the program is executed by the processor, the family portrait construction method according to any one of claims 1 to 6 is implemented.
10. A computer program product, characterized in that It comprises computer instructions, which, when executed by a processor, implement the family portrait construction method as described in any one of claims 1 to 6.
Citation Information
Cited By
A network topology awareness-based home broadband user portrait construction method and system, electronic equipment and storage medium
CN122802558A
