User portrait construction method and system, computer device and readable storage medium

Abstract

The present invention proposes a user portrait construction method and construction system, and the user portrait construction system includes a data acquisition module, a data processing module, a first model generation module, a data fusion module, a first model execution module and a portrait construction module. The data acquisition module collects user data, the data processing module performs feature processing on the user data, generates N feature data sets based on different dimensions, and then the first model generation module generates a first model using the N feature data sets; the data fusion module processes the N feature data sets respectively and then performs data fusion to obtain a fused feature data set, the first model execution module processes the fused feature data set using the first model to obtain evaluation data of different dimensions, and finally the portrait construction module constructs a user portrait according to the evaluation data of different dimensions, which can generate user portraits of different dimensions and meet the portrait requirements in a more refined manner.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a user portrait construction method and construction system, a computer device and a readable storage medium. Background Art

[0002] User portraits, also known as user roles, are an effective tool for outlining target users and linking user demands with design directions. For example, user portraits can be used as a set of labels to characterize user characteristics, including static attributes such as age and gender, as well as user interest characteristics such as travel and clothing. The construction and update of user portraits are of great significance for the subsequent targeted dissemination of information, such as targeted advertising. User portraits have been widely used in various fields. In the actual operation process, user attributes, behaviors and expectations can be linked. Summary of the invention

[0003] Based on the above problems, the present invention proposes a user portrait construction method and construction system, a computer device and a readable storage medium. By generating a feature data set from user data, inputting the feature data set into a first model to obtain evaluation data, and using the evaluation data to construct a user portrait, user portraits of different dimensions can be generated to meet portrait requirements in a more refined manner.

[0004] In view of this, a first aspect of the present invention proposes a method for constructing a user portrait, comprising:

[0005] Collect user data;

[0006] Performing feature processing on the user data to generate N feature data sets based on different dimensions;

[0007] Generate a first model using the N feature data sets;

[0008] After processing the N feature data sets, data fusion is performed to obtain a fused feature data set;

[0009] Using the first model to process the fused feature data set to obtain evaluation data of different dimensions;

[0010] A user profile is constructed based on the evaluation data of the different dimensions.

[0011] Optionally, the step of collecting user data specifically includes:

[0012] Build virtual scenes for users to interact with and collect user behavior data during the interaction process;

[0013] The physiological data of the user is collected using a physiological data collection sensor.

[0014] Optionally, the step of generating the first model using the N feature data sets is specifically:

[0015] Send the N feature data sets as input values ​​to the input layer respectively;

[0016] The input layer is connected to the initial layer through matrix operation;

[0017] The initial layer obtains a first output result, activates the first output result, and sends the activated first output result to the simulation output layer;

[0018] The simulation output layer obtains simulation output values ​​through matrix calculation, and inputs the simulation output values ​​into the secondary initial layer;

[0019] The secondary initial layer obtains the verification output result through matrix calculation;

[0020] Performing data connection between the input value of the input layer and the secondary initial layer;

[0021] The secondary initial layer obtains a secondary output result through matrix calculation, sends the secondary output result and the verification output result to the verification coefficient layer for verification, and obtains a normalization coefficient;

[0022] Sending the normalization coefficient and the simulated output value to the output layer, the output layer normalizes the simulated output value to obtain a mimicking result;

[0023] Collect positive and / or negative feedback information;

[0024] The mimicry result is learned and corrected according to the positive feedback and / or the negative feedback information to generate the first model.

[0025] Optionally, the step of using the first model to process the fused feature data set to obtain evaluation data of different dimensions is specifically:

[0026] Processing the user number, gender, age, personality traits, marital status, occupation and education level in the fused feature data set to obtain basic user evaluation data;

[0027] Processing the interactive product numbers and interactive behaviors in the fused feature data set to obtain user consumption evaluation data;

[0028] Processing the user number, gender, age, medical history and historical physical examination data in the fused feature data set to obtain user health assessment data;

[0029] The step of constructing a user portrait based on the evaluation data of different dimensions is specifically:

[0030] Constructing a first user portrait according to the basic evaluation data of the user;

[0031] Constructing a second user portrait based on the user health assessment data;

[0032] The third user portrait is constructed based on the consumption evaluation data.

[0033] A second aspect of the present invention provides a user portrait construction system, comprising: a data acquisition module, a data processing module, a first model generation module, a data fusion module, a first model execution module and a portrait construction module;

[0034] The data collection module is used to collect user data;

[0035] The data processing module is used to perform feature processing on the user data and generate N feature data sets based on different dimensions;

[0036] The first model generating module is used to generate a first model using the N feature data sets;

[0037] The data fusion module is used to process the N feature data sets respectively and then fuse the data to obtain a fused feature data set;

[0038] The first model execution module is used to process the fused feature data set using the first model to obtain evaluation data of different dimensions;

[0039] The portrait construction module is used to construct a user portrait based on the evaluation data of different dimensions.

[0040] Optionally, the data acquisition module includes a virtual reality unit and a physiological data acquisition unit;

[0041] The virtual reality unit is used to construct a virtual scene for user interaction and collect user behavior data during the interaction process;

[0042] The physiological data collection unit is used to collect the physiological data of the user.

[0043] Optionally, the first model generation module is used to generate a first model using the N feature data sets, specifically:

[0044] Send the N feature data sets as input values ​​to the input layer respectively;

[0045] The input layer is connected to the initial layer through matrix operation;

[0046] The initial layer obtains a first output result, activates the first output result, and sends the activated first output result to the simulation output layer;

[0047] The simulation output layer obtains simulation output values ​​through matrix calculation, and inputs the simulation output values ​​into the secondary initial layer;

[0048] The secondary initial layer obtains the verification output result through matrix calculation;

[0049] Performing data connection between the input value of the input layer and the secondary initial layer;

[0050] The secondary initial layer obtains a secondary output result through matrix calculation, sends the secondary output result and the verification output result to the verification coefficient layer for verification, and obtains a normalization coefficient;

[0051] Sending the normalization coefficient and the simulated output value to the output layer, the output layer normalizes the simulated output value to obtain a mimicking result;

[0052] Collect positive and / or negative feedback information;

[0053] The mimicry result is learned and corrected according to the positive feedback and / or the negative feedback information to generate the first model.

[0054] Optionally, the second model is used to process the fused feature data set using the first model to obtain evaluation data of different dimensions, specifically:

[0055] Processing the user number, gender, age, personality traits, marital status, occupation and education level in the fused feature data set to obtain basic user evaluation data;

[0056] Processing the interactive product numbers and interactive behaviors in the fused feature data set to obtain user consumption evaluation data;

[0057] Processing the user number, gender, age, medical history and historical physical examination data in the fused feature data set to obtain user health assessment data;

[0058] The portrait construction module is used to construct a user portrait according to the evaluation data of different dimensions, specifically:

[0059] Constructing a first user portrait according to the basic evaluation data of the user;

[0060] Constructing a second user portrait based on the user health assessment data;

[0061] The third user portrait is constructed based on the consumption evaluation data.

[0062] The third aspect of the present invention provides a computer device, comprising a processor and a memory, wherein the memory stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by the processor to implement the user portrait construction method as described in any one of claims 1 to 4.

[0063] The fourth aspect of the present invention provides a computer-readable storage medium, which stores at least one instruction, at least one program, a code set or an instruction set. The at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by a processor to implement the user portrait construction method as described in any one of claims 1 to 4.

[0064] According to the technical solution of the present invention, the user portrait construction system includes a data acquisition module, a data processing module, a first model generation module, a data fusion module, a first model execution module and a portrait construction module. The data acquisition module collects user data, the data processing module performs feature processing on the user data, generates N feature data sets based on different dimensions, and then the first model generation module generates a first model using the N feature data sets; the data fusion module processes the N feature data sets respectively and then performs data fusion to obtain a fused feature data set, the first model execution module processes the fused feature data set using the first model to obtain evaluation data of different dimensions, and finally the portrait construction module constructs a user portrait based on the evaluation data of different dimensions, which can generate user portraits of different dimensions and meet the portrait requirements in a more refined manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 is a flow chart of a method for constructing a user portrait provided by an embodiment of the present invention;

[0066] Figure 2 is a flowchart of specific steps for collecting user data in one embodiment of the present invention;

[0067] Figure 3 is a flowchart of specific steps of generating a first model in one embodiment of the present invention;

[0068] Figure 4 It is a flowchart of specific steps of processing the fused feature data set by the first model in one embodiment of the present invention to obtain evaluation data of different dimensions;

[0069] Figure 5 is a flowchart of specific steps for constructing a user portrait based on the evaluation data of different dimensions in one embodiment of the present invention.

[0070] Figure 6 It is a schematic block diagram of a user portrait construction system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0071] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0072] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0073] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0074] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0075] Refer to the following Figures 1 to 6 To describe a user portrait construction method and construction system provided according to some embodiments of the present invention.

[0076] like Figure 1 As shown, an embodiment of the present invention provides a method for constructing a user portrait, including:

[0077] Step S1, collecting user data;

[0078] In this step, user data can be collected through various channels, such as extracting from the terminal device used by the user or the log file of the network server; collecting physiological data in the user data through smart devices; and generating virtual scenes through virtual reality devices to immerse users in them, while identifying user behaviors and collecting user data through sensors, etc. The embodiments of the present invention are not limited to this.

[0079] Step S2: performing feature processing on the user data to generate N feature data sets based on different dimensions;

[0080] In this step, after the user data is preprocessed, feature processing is performed, and feature processing includes standardization, normalization, discretization, feature dimension increase / reduction, default value processing, etc., and the corresponding feature processing method can be selected according to the purpose of the data. After the user data is feature processed, N feature data sets are generated based on different dimensions using the processed user data, and the N feature data sets are used to represent multiple data types corresponding to the user data, where N is a positive integer.

[0081] Step S3, generating a first model using the N feature data sets;

[0082] Step S4, performing data fusion after processing the N feature data sets to obtain a fused feature data set;

[0083] Step S5: using the first model to process the fused feature data set to obtain evaluation data of different dimensions;

[0084] Step S6: construct a user portrait based on the evaluation data of different dimensions.

[0085] It is understandable that the user data includes but is not limited to user number, gender, age, personality traits, marital status, occupation, education level, medical history, historical physical examination data, historical insurance data, user shopping location, user shopping time, interactive product number and interactive behavior, and the interactive behavior includes clicking on products, browsing, visit frequency, favorites, adding to shopping cart, removing from shopping cart, favorites, purchasing, sharing, registering as a member, receiving shopping coupons, returns, exchanges, complaints, refunds, comments, card swiping, and recharging.

[0086] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. Based on big data and deep learning models, it is possible to build a user model based on the user's basic characteristics, browsing behavior, access frequency, purchase behavior and other information, understand the user's interests, hobbies, purchasing power, consumption habits, etc. in multiple dimensions, and achieve a clearer and more comprehensive understanding of the user.

[0087] The technical solution of this embodiment is adopted, and the user portrait construction system includes a data acquisition module, a data processing module, a first model generation module, a data fusion module, a first model execution module and a portrait construction module. The data acquisition module collects user data, the data processing module performs feature processing on the user data, generates N feature data sets based on different dimensions, and then the first model generation module generates the first model using the N feature data sets; the data fusion module processes the N feature data sets respectively and then performs data fusion to obtain a fused feature data set, the first model execution module processes the fused feature data set using the first model to obtain evaluation data of different dimensions, and finally the portrait construction module constructs a user portrait based on the evaluation data of different dimensions, which can generate user portraits of different dimensions and meet the portrait requirements in a more refined manner.

[0088] like Figure 2 As shown, in some possible implementations of the present invention, step S1, collecting user data, specifically includes:

[0089] Sub-step S11: constructing a virtual scene for user interaction and collecting user behavior data during the interaction process;

[0090] Sub-step S12: collecting the user's physiological data using a physiological data collection sensor.

[0091] In this embodiment, a virtual scene for user interaction can be constructed through a virtual reality terminal, and user behavior data of the user during the interaction process can be collected. The virtual reality terminal includes at least a visual presentation device, an interactive device and a sound device. The visual presentation device is used to present the constructed virtual scene to the user, and can be virtual reality glasses, virtual reality helmets, etc.; the sound device can be a three-dimensional sound system, and the interactive device includes a position tracker, a data glove, a three-dimensional mouse, a motion capture device, an eye tracker, a force feedback device and other interactive devices. For example, when the virtual reality terminal constructs a motion test scene, the presentation device presents the motion test virtual environment to the user and initiates interaction. The user's motion data and sound data and other user behavior data are collected through the motion capture device and the sound collection device. At the same time, the user's physiological data can also be collected through the physiological data collection sensor. By collecting these data, a data source can be provided for user portraits, especially for the health side of the user.

[0092] like Figure 3 As shown, in some possible implementations of the present invention, step S3, using the N feature data sets to generate a first model, specifically:

[0093] Sub-step S301, sending the N feature data sets as input values ​​to the input layer respectively;

[0094] Sub-step S302, the input layer is connected to the initial layer through matrix operation;

[0095] Sub-step S303, the initial layer obtains a first output result, activates the first output result, and sends the activated first output result to the simulation output layer;

[0096] Sub-step S304, the simulation output layer obtains a simulation output value through matrix calculation, and inputs the simulation output value into the secondary initial layer;

[0097] Sub-step S305, the secondary initial layer obtains a verification output result through matrix calculation;

[0098] Sub-step S306, performing data connection between the input value of the input layer and the secondary initial layer;

[0099] Sub-step S307, the secondary initial layer obtains a secondary output result through matrix calculation, sends the secondary output result and the verification output result to the verification coefficient layer for verification, and obtains a normalization coefficient;

[0100] Sub-step S308, sending the normalization coefficient and the simulation output value to the output layer, the output layer normalizes the simulation output value to obtain a mimicking result;

[0101] Sub-step S309: collecting positive feedback and / or negative feedback information;

[0102] Sub-step S310: performing learning and correction on the mimicry result according to the positive feedback and / or the negative feedback information to generate the first model.

[0103] In this embodiment, in order to generate an accurate and efficient first model, a feature data set is processed by a neural network to construct the first model, and the neural network includes an input layer, an initial layer, a simulated output layer, a secondary initial layer, a verification coefficient layer, and an output layer, and the first output result is activated using an activation function. An activation function is a function added to an artificial neural network to help the network learn complex patterns in data, similar to a neuron-based model in the human brain. The activation function ultimately determines the content to be emitted to the next neuron, including Sigmoid activation function, ReLU activation function, etc.

[0104] In some possible embodiments of the present invention, Figure 4 As shown, step S5, using the first model to process the fused feature data set to obtain evaluation data of different dimensions, specifically:

[0105] Sub-step S51, processing the user number, gender, age, personality characteristics, marital status, occupation and education level in the fused feature data set to obtain basic user evaluation data;

[0106] Sub-step S52: Processing the interactive product numbers and interactive behaviors in the fused feature data set to obtain user consumption evaluation data;

[0107] Sub-step S53, processing the user number, gender, age, medical history and historical physical examination data in the fused feature data set to obtain user health assessment data;

[0108] like Figure 5 As shown, step S6, constructing a user portrait according to the evaluation data of different dimensions, specifically:

[0109] Sub-step S61: constructing a first user portrait according to the basic evaluation data of the user;

[0110] Sub-step S62: constructing a second user portrait according to the user health assessment data;

[0111] Sub-step S63: construct the third user portrait based on the consumption evaluation data.

[0112] It can be understood that different user portraits can be obtained by inputting data feature vectors of different dimensions / types in the fused feature data set into the first model. For example, after processing the user number, gender, age, personality characteristics, marital status, occupation and education level in the fused feature data set, the basic evaluation data of the user is obtained and input into the first model, and then the first user portrait representing the basic attributes of the user can be obtained; after processing the user number, gender, age, medical history and historical physical examination data in the fused feature data set, the user health evaluation data is obtained and input into the first model, and then the second user portrait representing the health attributes of the user is obtained; after processing the interactive product number and interactive behavior in the fused feature data set, the user consumption evaluation data is obtained and input into the first model, and then the third user portrait representing the user consumption attributes is obtained; in the embodiment of the present invention, data of different dimensions can be selected and input according to the purpose of the user portrait, so as to obtain different user portraits, which is flexible and can better meet actual needs.

[0113] like Figure 6 As shown, another embodiment of the present invention provides a user portrait construction system, including: a data acquisition module, a data processing module, a first model generation module, a data fusion module, a first model execution module and a portrait construction module;

[0114] The data collection module is used to collect user data;

[0115] In this embodiment, user data can be collected through various channels, such as extracting from the terminal device used by the user or the log file of the network server; collecting physiological data in the user data through smart devices; and generating virtual scenes through virtual reality devices to immerse users in them, while identifying user behaviors and collecting user data through sensors, etc. The embodiments of the present invention are not limited to this.

[0116] The data processing module is used to perform feature processing on the user data and generate N feature data sets based on different dimensions, where N is a positive integer;

[0117] In this step, after the user data is preprocessed, feature processing is performed, and feature processing includes standardization, normalization, discretization, feature dimension increase / reduction, default value processing, etc., and the corresponding feature processing method can be selected according to the purpose of the data. After the user data is feature processed, N feature data sets are generated based on different dimensions using the processed user data, and the N feature data sets are used to represent multiple data types corresponding to the user data, where N is a positive integer.

[0118] The first model generating module is used to generate a first model using the N feature data sets;

[0119] The data fusion module is used to process the N feature data sets respectively and then fuse the data to obtain a fused feature data set;

[0120] The first model execution module is used to process the fused feature data set using the first model to obtain evaluation data of different dimensions;

[0121] The portrait construction module is used to construct a user portrait based on the evaluation data of different dimensions.

[0122] It is understandable that the user data includes but is not limited to user number, gender, age, personality traits, marital status, occupation, education level, medical history, historical physical examination data, historical insurance data, user shopping location, user shopping time, interactive product number and interactive behavior, and the interactive behavior includes clicking on products, browsing, visit frequency, favorites, adding to shopping cart, removing from shopping cart, favorites, purchasing, sharing, registering as a member, receiving shopping coupons, returns, exchanges, complaints, refunds, comments, card swiping, and recharging.

[0123] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. Based on big data and deep learning models, it is possible to build a user model based on the user's basic characteristics, browsing behavior, access frequency, purchase behavior and other information, understand the user's interests, hobbies, purchasing power, consumption habits, etc. in multiple dimensions, and achieve a clearer and more comprehensive understanding of the user.

[0124] The technical solution of this embodiment is adopted, and the user portrait construction system includes a data acquisition module, a data processing module, a first model generation module, a data fusion module, a first model execution module and a portrait construction module. The data acquisition module collects user data, the data processing module performs feature processing on the user data, generates N feature data sets based on different dimensions, and then the first model generation module generates the first model using the N feature data sets; the data fusion module processes the N feature data sets respectively and then performs data fusion to obtain a fused feature data set, the first model execution module processes the fused feature data set using the first model to obtain evaluation data of different dimensions, and finally the portrait construction module constructs a user portrait based on the evaluation data of different dimensions, which can generate user portraits of different dimensions and meet the portrait requirements in a more refined manner.

[0125] It should be known that Figure 6The block diagram of the user portrait construction system shown is for illustration only, and the number of modules shown therein does not limit the protection scope of the present invention.

[0126] In some possible implementations of the present invention, the data acquisition module includes a virtual reality unit (not shown in the figure) and a physiological data acquisition unit (not shown in the figure);

[0127] The virtual reality unit is used to construct a virtual scene for user interaction and collect user behavior data during the interaction process;

[0128] The physiological data collection unit is used to collect the physiological data of the user.

[0129] In this embodiment, a virtual scene for user interaction can be constructed through a virtual reality terminal, and user behavior data of the user during the interaction process can be collected. The virtual reality terminal includes at least a visual presentation device, an interactive device and a sound device. The visual presentation device is used to present the constructed virtual scene to the user, which can be virtual reality glasses, virtual reality helmets, etc.; the sound device can be a three-dimensional sound system, and the interactive device includes a position tracker, a data glove, a three-dimensional mouse, a motion capture device, an eye tracker, a force feedback device and other interactive devices. For example, when the virtual reality terminal constructs a motion test scene, the presentation device presents the motion test virtual environment to the user and initiates interaction, collects user behavior data such as user motion data and sound data through motion capture devices and sound collection devices, and can also collect user physiological data through physiological data collection sensors. By collecting these data, a data source can be provided for user portraits, especially for users on the health side. It can be understood that the virtual reality unit can be integrated into the virtual reality unit.

[0130] In some possible implementations of the present invention, the first model generation module is used to generate the first model using the N feature data sets, specifically:

[0131] Send the N feature data sets as input values ​​to the input layer respectively;

[0132] The input layer is connected to the initial layer through matrix operation;

[0133] The initial layer obtains a first output result, activates the first output result, and sends the activated first output result to the simulation output layer;

[0134] The simulation output layer obtains simulation output values ​​through matrix calculation, and inputs the simulation output values ​​into the secondary initial layer;

[0135] The secondary initial layer obtains the verification output result through matrix calculation;

[0136] Performing data connection between the input value of the input layer and the secondary initial layer;

[0137] The secondary initial layer obtains a secondary output result through matrix calculation, sends the secondary output result and the verification output result to the verification coefficient layer for verification, and obtains a normalization coefficient;

[0138] Sending the normalization coefficient and the simulated output value to the output layer, the output layer normalizes the simulated output value to obtain a mimicking result;

[0139] Collect positive and / or negative feedback information;

[0140] The mimicry result is learned and corrected according to the positive feedback and / or the negative feedback information to generate the first model.

[0141] In this embodiment, in order to generate an accurate and efficient first model, a feature data set is processed by a neural network to construct the first model, and the neural network includes an input layer, an initial layer, a simulated output layer, a secondary initial layer, a verification coefficient layer, and an output layer, and the first output result is activated using an activation function. An activation function is a function added to an artificial neural network to help the network learn complex patterns in data, similar to a neuron-based model in the human brain. The activation function ultimately determines the content to be emitted to the next neuron, including Sigmoid activation function, ReLU activation function, etc.

[0142] In some possible implementations of the present invention, the second model is used to process the fused feature data set using the first model to obtain evaluation data of different dimensions, specifically:

[0143] Processing the user number, gender, age, personality traits, marital status, occupation and education level in the fused feature data set to obtain basic user evaluation data;

[0144] Processing the interactive product numbers and interactive behaviors in the fused feature data set to obtain user consumption evaluation data;

[0145] Processing the user number, gender, age, medical history and historical physical examination data in the fused feature data set to obtain user health assessment data;

[0146] The portrait construction module is used to construct a user portrait according to the evaluation data of different dimensions, specifically:

[0147] Constructing a first user portrait according to the basic evaluation data of the user;

[0148] Constructing a second user portrait based on the user health assessment data;

[0149] The third user portrait is constructed based on the consumption evaluation data.

[0150] It can be understood that different user portraits can be obtained by inputting data feature vectors of different dimensions / types in the fused feature data set into the first model. For example, after processing the user number, gender, age, personality characteristics, marital status, occupation and education level in the fused feature data set, the basic evaluation data of the user is obtained and input into the first model, and then the first user portrait representing the basic attributes of the user can be obtained; after processing the user number, gender, age, medical history and historical physical examination data in the fused feature data set, the user health evaluation data is obtained and input into the first model, and then the second user portrait representing the health attributes of the user is obtained; after processing the interactive product number and interactive behavior in the fused feature data set, the user consumption evaluation data is obtained and input into the first model, and then the third user portrait representing the user consumption attributes is obtained; in the embodiment of the present invention, data of different dimensions can be selected and input according to the purpose of the user portrait, so as to obtain different user portraits, which is flexible and can better meet actual needs.

[0151] Another embodiment of the present invention provides a computer device, the computer device comprising a processor and a memory, the memory storing at least one instruction, at least one program, a code set or an instruction set, the at least one instruction, the at least one program, the code set or the instruction set being loaded and executed by the processor to implement the following method: collecting user data;

[0152] Performing feature processing on the user data to generate N feature data sets based on different dimensions;

[0153] Generate a first model using the N feature data sets;

[0154] After processing the N feature data sets, data fusion is performed to obtain a fused feature data set;

[0155] Using the first model to process the fused feature data set to obtain evaluation data of different dimensions;

[0156] Constructing a user profile based on the evaluation data of different dimensions;

[0157] Wherein, N is a positive integer.

[0158] Another embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores at least one instruction, at least one program, a code set, or an instruction set, and the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by a processor to implement the following method:

[0159] Collect user data;

[0160] Performing feature processing on the user data to generate N feature data sets based on different dimensions;

[0161] Generate a first model using the N feature data sets;

[0162] After processing the N feature data sets, data fusion is performed to obtain a fused feature data set;

[0163] Using the first model to process the fused feature data set to obtain evaluation data of different dimensions;

[0164] Constructing a user profile based on the evaluation data of different dimensions;

[0165] Wherein, N is a positive integer.

[0166] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0167] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0168] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the above-mentioned units, which 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, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0169] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0170] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically 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 software functional units.

[0171] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the above-mentioned methods of each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or CD-ROM and other media that can store program codes.

[0172] A person skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, and the memory can include: a flash drive, a read-only memory (English: Read-Only Memory, abbreviated as: ROM), a random access memory (English: Random Access Memory, abbreviated as: RAM), a magnetic disk or an optical disk, etc.

[0173] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

[0174] Although the present invention is disclosed as above, the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions without departing from the spirit and scope of the present invention, and can make various changes and modifications, including the combination of the above-mentioned different functions and implementation steps, including software and hardware implementation methods, all of which are within the scope of protection of the present invention.

Claims

1. A method for constructing a user portrait, characterized in that: include: Collect user data; Performing feature processing on the user data to generate N feature data sets based on different dimensions; Generate a first model using the N feature data sets; After processing the N feature data sets, data fusion is performed to obtain a fused feature data set; Using the first model to process the fused feature data set to obtain evaluation data of different dimensions; Constructing a user profile based on the evaluation data of different dimensions; Wherein, N is a positive integer; The step of collecting user data specifically includes: Build virtual scenes for users to interact with and collect user behavior data during the interaction process; Collecting the user's physiological data using a physiological data collection sensor; The step of generating the first model using the N feature data sets is specifically: Send the N feature data sets as input values ​​to the input layer respectively; The input layer is connected to the initial layer through matrix operation; The initial layer obtains a first output result, activates the first output result, and sends the activated first output result to the simulation output layer; The simulation output layer obtains simulation output values ​​through matrix calculation, and inputs the simulation output values ​​into the secondary initial layer; The secondary initial layer obtains the verification output result through matrix calculation; Performing data connection between the input value of the input layer and the secondary initial layer; The secondary initial layer obtains a secondary output result through matrix calculation, sends the secondary output result and the verification output result to the verification coefficient layer for verification, and obtains a normalization coefficient; Sending the normalization coefficient and the simulated output value to the output layer, the output layer normalizes the simulated output value to obtain a mimicking result; Collect positive and / or negative feedback information; The mimicry result is learned and corrected according to the positive feedback and / or the negative feedback information to generate the first model.

2. The user portrait construction method according to claim 1, characterized in that: The step of using the first model to process the fused feature data set to obtain evaluation data of different dimensions is specifically: Processing the user number, gender, age, personality traits, marital status, occupation and education level in the fused feature data set to obtain basic user evaluation data; Processing the interactive product numbers and interactive behaviors in the fused feature data set to obtain user consumption evaluation data; Processing the user number, gender, age, medical history and historical physical examination data in the fused feature data set to obtain user health assessment data; The step of constructing a user portrait based on the evaluation data of different dimensions is specifically: Constructing a first user portrait according to the basic evaluation data of the user; Constructing a second user portrait based on the user health assessment data; A third user portrait is constructed based on the consumption evaluation data.

3. A user portrait construction system, characterized in that: include: Data acquisition module, data processing module, first model generation module, data fusion module, first model execution module and portrait construction module; The data collection module is used to collect user data; The data processing module is used to perform feature processing on the user data and generate N feature data sets based on different dimensions; The first model generating module is used to generate a first model using the N feature data sets; The data fusion module is used to process the N feature data sets respectively and then fuse the data to obtain a fused feature data set; The first model execution module is used to process the fused feature data set using the first model to obtain evaluation data of different dimensions; The portrait building module is used to build a user portrait based on the evaluation data of different dimensions; Wherein, N is a positive integer; The data acquisition module includes a virtual reality unit and a physiological data acquisition unit; The virtual reality unit is used to construct a virtual scene for user interaction and collect user behavior data during the interaction process; The physiological data collection unit is used to collect the physiological data of the user; The first model generation module is used to generate a first model using the N feature data sets, specifically: Send the N feature data sets as input values ​​to the input layer respectively; The input layer is connected to the initial layer through matrix operation; The initial layer obtains a first output result, activates the first output result, and sends the activated first output result to the simulation output layer; The simulation output layer obtains simulation output values ​​through matrix calculation, and inputs the simulation output values ​​into the secondary initial layer; The secondary initial layer obtains the verification output result through matrix calculation; Performing data connection between the input value of the input layer and the secondary initial layer; The secondary initial layer obtains a secondary output result through matrix calculation, sends the secondary output result and the verification output result to the verification coefficient layer for verification, and obtains a normalization coefficient; Sending the normalization coefficient and the simulated output value to the output layer, the output layer normalizes the simulated output value to obtain a mimicking result; Collect positive and / or negative feedback information; The mimicry result is learned and corrected according to the positive feedback and / or the negative feedback information to generate the first model.

4. The user portrait construction system according to claim 3, characterized in that: The step of processing the fused feature data set using the first model to obtain evaluation data of different dimensions is specifically: Processing the user number, gender, age, personality traits, marital status, occupation and education level in the fused feature data set to obtain basic user evaluation data; Processing the interactive product numbers and interactive behaviors in the fused feature data set to obtain user consumption evaluation data; Processing the user number, gender, age, medical history and historical physical examination data in the fused feature data set to obtain user health assessment data; The portrait construction module is used to construct a user portrait according to the evaluation data of different dimensions, specifically: Constructing a first user portrait according to the basic evaluation data of the user; Constructing a second user portrait based on the user health assessment data; A third user portrait is constructed based on the consumption evaluation data.

5. A computer device, characterized in that: The computer device includes a processor and a memory, wherein the memory stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by the processor to implement the user portrait construction method as described in any one of claims 1 to 2.

6. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by the processor to implement the user portrait construction method as described in any one of claims 1 to 2.

Images