WO2020140911A1 - 数据处理方法及装置、数据节点及存储介质 - Google Patents

数据处理方法及装置、数据节点及存储介质 Download PDF

Info

Publication number
WO2020140911A1
WO2020140911A1 PCT/CN2019/130822 CN2019130822W WO2020140911A1 WO 2020140911 A1 WO2020140911 A1 WO 2020140911A1 CN 2019130822 W CN2019130822 W CN 2019130822W WO 2020140911 A1 WO2020140911 A1 WO 2020140911A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
portrait
type
situation
user
Prior art date
Application number
PCT/CN2019/130822
Other languages
English (en)
French (fr)
Inventor
周贤波
郑智民
Original Assignee
中国移动通信有限公司研究院
中国移动通信集团有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 中国移动通信有限公司研究院, 中国移动通信集团有限公司 filed Critical 中国移动通信有限公司研究院
Publication of WO2020140911A1 publication Critical patent/WO2020140911A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0269—Targeted advertisements based on user profile or attribute
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/01—Social networking

Definitions

  • the present disclosure relates to the field of information technology but is not limited to the field of information technology, and particularly relates to a data processing method and device, a data node, and a storage medium.
  • the process of generating a blockchain is generally based on a proof-of-work mechanism.
  • the proof-of-work mechanism based on the computing power of data nodes (referred to as computing power) competing to generate tokens for the blockchain record; if the token is successfully competed, the participation in the blockchain record or block generation At the same time, you will get tokens for establishment.
  • the generation of blockchain has become a computing power competition for mining machines.
  • the strongest computing power of competing computing nodes is generally a specific user node or a specific device.
  • the more computing nodes participate in the competition the more difficult the token competition is, and even Exponentially rising.
  • This kind of computing power competition also consumes energy, and although the fierce competition is more and more motivated, the more energy is consumed.
  • this competition based on the computing power of the mining machine will have a Jardin effect, that is, users with powerful mining machines can frequently seize tokens, while other users cannot participate in the generation of the blockchain , This will lead to a reduction in the number of participating users in the generation of blockchain, thereby reducing user activity.
  • embodiments of the present disclosure are expected to provide a data processing method and device, data node, and storage medium.
  • a first aspect of an embodiment of the present disclosure provides a data processing method, including:
  • tokens that participate in the generation of blockchain records are allocated to users in the same category according to the situation portraits.
  • the acquiring the situation portrait generated based on the second type of data includes:
  • the acquiring an individual portrait generated based on the first type of data includes: acquiring an individual portrait generated based on the user's long-term data in the first period of time; and acquiring the situation portrait generated based on the second type of data includes: Acquiring a situation portrait generated by real-time data in a second period of the user, wherein the first period is longer than the second period;
  • the acquiring an individual portrait generated based on the first type of data includes: acquiring an individual portrait generated based on network behavior data that the user actively participates in; acquiring the situation portrait generated based on the second type of data includes: acquiring the data collected by the Internet of Things device Situational portraits generated by user passive data.
  • the acquiring an individual portrait generated based on the first type of data includes:
  • the acquiring the situation portrait generated based on the second type of data includes:
  • the method further includes:
  • the method further includes:
  • the first model is a model that generates the individual portrait
  • the second The model is a model that generates the situation portrait.
  • the method further includes:
  • the collection parameters of the second type of data are determined according to the situation portrait, wherein the collection parameters include at least one of the following: collection frequency and collection target.
  • the method further includes:
  • the situation portrait is generated based on the preprocessed second type data.
  • the preprocessing of the second type of data includes at least one of the following:
  • noise data includes at least one of abnormal data and redundant data
  • the generating the situation portrait based on the preprocessed second-type data includes:
  • the situation portrait is generated based on the preprocessed feature data.
  • a second aspect of an embodiment of the present disclosure provides a data processing apparatus, including:
  • the first obtaining module is configured to obtain an individual portrait generated based on the first type of data
  • a second obtaining module configured to obtain a situation portrait generated based on the second type of data
  • the allocation module is configured to allocate tokens participating in the blockchain record generation according to the situation portraits among users of the same type based on the individual portraits.
  • a third aspect of an embodiment of the present disclosure provides a data node, including:
  • Memory configured for information storage
  • a processor connected to the memory, is configured to implement the data processing method provided by one or more of the foregoing technical solutions by executing computer-executable instructions stored in the memory.
  • a fourth aspect of an embodiment of the present disclosure provides a computer storage medium for storing computer-executable instructions; after being executed by a processor, the computer-executable instructions can implement the one or more technical solutions provided above Data processing methods.
  • the data processing method and device, data node, and storage medium provided by the embodiments of the present disclosure are no longer determined solely by the computing power of the mining machine when performing the token distribution recorded on the blockchain, but based on the user's individual portrait
  • the competition between the same type of users is achieved; on the one hand, the competition is purely relative to the computing power of the mining machine, which reduces the large amount of power consumption caused by the proof of work and saves the work. Consumption, achieving green environmental protection; on the other hand, competing in the same type of user to combine situational portraits, reducing the unfairness of competition between different types of users, and reducing the withdrawal of specific types of users due to unfairness , To ensure long-term user activity and participation.
  • FIG. 1 is a schematic flowchart of a first data processing method provided by an embodiment of the present disclosure
  • FIG. 2 is a schematic flowchart of a second data processing method provided by an embodiment of the present disclosure
  • FIG. 3 is a schematic structural diagram of a data processing device according to an embodiment of the present disclosure.
  • FIG. 4 is a schematic flowchart of a third data processing method provided by an embodiment of the present disclosure.
  • this embodiment provides a data processing method, including:
  • Step S110 Obtain an individual portrait generated based on the first type of data
  • Step S120 Acquire a situation portrait generated based on the second type of data, wherein the situation portrait is used to characterize the current state of the user;
  • Step S130 Based on the individual portraits, assign tokens that participate in the generation of blockchain records according to the situation portraits among users of the same category.
  • the data processing method provided in this embodiment can be applied to the generation of a blockchain, for example, to the generation of smart contracts in a blockchain.
  • blocks of the blockchain may be generated at predetermined time intervals, for example, one block is generated every 10 minutes, 5 minutes, 15 minutes, or 20 minutes. In some embodiments, the number of generated blockchain records is counted, and a block is generated when the predetermined number is reached.
  • an individual portrait generated based on the first type of data is first obtained; the individual portrait can be used to characterize the user's characteristics, and the user's characteristics can include: the user's age, gender, education, occupation, preferences, and so on.
  • Users can be classified based on individual portraits, for example, users with similar characteristics can be classified into one category. For example, through clustering algorithms, users with the same or similar characteristics are classified into the same category. In this way, athletes may fall into a category.
  • a context portrait is also generated based on the second type of data.
  • the context portrait is used to characterize the user's current state, for example, at least one of the user's current motion state, the user's current emotional state, and the user's current health state.
  • step S130 the individual portraits will be combined with the same type of users to allocate tokens for generating blockchain records according to the contextual portraits. Users who have obtained tokens will be able to obtain the accounting rights of at least one blockchain record, thus winning The right to obtain tokens, thus avoiding the large amount of power consumption caused by the pure use of the mining machine's computing power to fight for tokens.
  • the step S130 may include:
  • Polling for token allocation among multiple user categories if the nth type of user is currently polled, select a user among the nth type of user according to the situation profile to obtain the token for this poll.
  • the step S130 may include: selecting a user to obtain the token according to the situational characteristics of the user of the third type; thus, the next type of user polled is the user of the fourth type.
  • the step S130 may include:
  • the token allocation ratio and the user class allocated by the previous token determine the user class to be allocated to obtain the current token
  • Tokens are allocated according to contextual portraits in certain user classes.
  • each type of user has a chance to obtain a token, and the probability of a single user in each type of user getting a token is also equal, which reduces the amount of energy generated by the competition between users based on the computing power of the mining machine. It consumes and takes into account the fairness of token distribution.
  • the situation portrait characterizes the current state of the user. For example, if the current state is a sports state, in step S130, among all users of a class of users, the user with the largest amount of exercise in the current time period is selected to obtain the token. Because tokens are distributed among users of the same category, this can avoid or at least reduce the unfairness of athletes and office white-collar workers competing for a token based on the amount of exercise, improve the fairness of token competition, and thus reduce the competition for tokens. The unfairness of the user causes the user to lose interest, resulting in the problem of low user participation or low activity, thereby enhancing the user's enthusiasm for participation.
  • Step S130 may further include: among all users of a category of users, selecting the emotional characteristics of the users in the current time period, and selecting the users who are assigned tokens. For example, the user who selects the most emotional state obtains the token.
  • the evaluation index of emotional health may be composed of one or more.
  • emotional health may be generated based on multiple physiological signals, such as heartbeat signals and brain wave signals.
  • the user who assigns the token is selected according to the emotional characteristics of the user's current health status. For example, there are also multiple evaluation indicators for the health status, which can also be obtained by collecting physiological signals. As such, the health status of users of different ages, genders, and occupations may present certain group characteristics. For example, a healthy young person is obviously better than an elderly person in overall health status.
  • the first option is to distribute tokens among users of the same type based on individual portraits. In this way, it is possible to avoid indistinguishment between young people and old people. The characteristics of people come to allocate tokens, which leads to the unfairness of token distribution. In this way, if tokens are allocated according to the current health status, different types of users can also be distinguished to encourage healthy competition among users of the same type, which is beneficial to the improvement of user health.
  • the step S120 may include:
  • the step S130 may include: combining at least one of the sports portrait, the health portrait, and the emotional portrait, selecting a user among the same type of user to allocate the token.
  • allocating tokens based on motion portraits may include: selecting a user allocation token with the largest increase in the amount of exercise in the current period relative to the previous period; or selecting the amount of exercise in the current period relative to the user The increase in the amount of normal exercise is the largest with the distribution token, so as to achieve the purpose of encouraging exercise.
  • assigning a token based on an emotional portrait may include: selecting the user whose emotions are maintained in the happy state or the calm state for the longest time to allocate the token, or choosing to switch from pessimistic emotions to happy emotions Users with the largest emotional spans are allocated this token to encourage the maintenance of pleasant emotions, so as to enhance the user's emotional pleasure.
  • assigning tokens based on health portraits may include:
  • the step S110 may include: acquiring an individual portrait generated based on the user's long-term data in the first period;
  • the step S120 may include acquiring a situation portrait generated by the real-time data in the second period of the user, wherein the first period is longer than the second period.
  • the timing unit of the first period is at least days, even weeks, months or years.
  • the first type of data is long-term data, including but not limited to long-term network behavior data of users.
  • Long-term data reflects the long-term relatively static characteristics of users.
  • the second type of data may be dynamic data, which is data within a short time.
  • the timing unit of the second period may be hours, or even minutes.
  • the second type of data reflects the dynamic characteristics of the user in the current situation.
  • the token when token allocation is performed in step S130, the token can be allocated in combination with the user's long-term characteristics and current dynamic characteristics (or instantaneous characteristics), taking into account the fairness of the token distribution.
  • the step S110 may further include: obtaining an individual portrait generated based on network behavior data actively participated by the user; the step S120 may include: obtaining a situation portrait generated by the user's passive data collected by the Internet of Things device.
  • the user usually actively participates in some activities, thereby providing behavior data of the active participation, for example, the user's web browsing behavior, the user's online social behavior, and the user's online shopping behavior. These behaviors are behavior data generated by the user's conscious active participation.
  • the data collected by the IoT device may be data generated by the user's unconscious active control, for example, the user's breathing data, and for example, the user's heartbeat data, the user's pulse data, etc. These user data are collected actively by the physical network equipment, but are not provided by the user actively or consciously.
  • first-type data and the second-type data are different types of data.
  • the above is an example of the first-type data and the second-type data, and the specific implementation is not limited to this.
  • the Internet of Things devices may include, but are not limited to, wearable devices, such as smart watches, smart bracelets, smart foot rings, smart shoes or smart clothes, and so on.
  • the step S110 may include: obtaining an individual portrait generated based on at least one of the user's age information, gender information, occupational characteristic information, physical fitness information, reading behavior characteristic information, preference information, and aversion information .
  • the step S120 may include:
  • the user exercise data may include data such as the number of steps walked in the current time period, the current miles traveled, and so on.
  • the sign data may be data that characterizes the user's physical condition, for example, the number of breaths per minute or the number of pulse beats of the user are different in the exercise state and the rest state, so the situation portrait may also be generated according to the sign data At this time, the generated situation portrait may be at least one of the aforementioned sports portrait, emotional portrait or health portrait.
  • the method further includes:
  • Step S140 Based on the individual portrait and the situation portrait, perform service recommendation.
  • the service recommendations here include but are not limited to at least one of the following:
  • the content recommendation service may include: content recommendation of various multimedia information, for example, video, graphic information such as movies and TV series recommended by the user.
  • the content recommendation service may include: an advertisement distribution service. For example, combining an individual portrait and a context portrait of a user, an advertisement is distributed to a terminal device or a social account held by the user, and the advertisement may be content that is of interest to the user in the current context.
  • the shopping recommendation service can push items or services that the user is interested in in the shopping application.
  • the social recommendation service may include: recommending social friends that the user may be willing to make, and so on.
  • various service recommendations will be combined with individual portraits and contextual portraits, so that there are more recommended reference factors, thereby achieving more accurate service recommendation.
  • the method further includes:
  • Step S150 Obtain feedback information based on the service recommendation
  • Step S160 Update the model parameters of the first model based on the feedback information; and/or, update the model parameters of the second model based on the feedback information, wherein the first model is a model that generates the individual portrait;
  • the second model is a model for generating the situation portrait.
  • the model parameters of the first model and/or the second model will be modified according to the feedback information.
  • Both the first model and the second model here may be machine learning models, and the machine learning model may be a vector machine model or a deep learning model.
  • the method further includes:
  • the collection parameters of the second type of data are determined according to the situation portrait, wherein the collection parameters include at least one of the following: collection frequency and collection target.
  • the method also determines the collection parameters of the second type of data to be collected according to the situation portrait.
  • the user wears a variety of wearable devices. If these devices work at the same time, it is obviously also a consumption Yes, in this embodiment, it is possible to determine which sub-category of data of the second type of data needs to be collected according to the user’s current situation portrait, or, the frequency of collection; reduce unnecessary data collection, reduce the need for unnecessary data Data acquisition power consumption.
  • the collection frequency may be increased and/or the type of the second type of data collected may be increased according to the context portrait, so as to obtain a more comprehensive and accurate context portrait.
  • the collection parameters of the second type of data are reversely controlled according to the situation portrait, thereby achieving precise control of the second type of data collection.
  • the method further includes: pre-processing the second-type data; generating the situation portrait based on the pre-processed second-type data.
  • the second type of data after the second type of data is collected, there may be noise.
  • the second type of data will be preprocessed.
  • the preprocessing of the second type of data includes at least one of the following:
  • noise data includes at least one of abnormal data and redundant data
  • the generating the situation portrait based on the preprocessed second-type data includes:
  • the situation portrait is generated based on the preprocessed feature data.
  • high-dimensional data can be mapped to low-dimensional data, thereby reducing the amount of data when generating situation portraits.
  • non-linear mapping is used to map multiple dimensions of data in the second type of data to one-dimensional data. Due to this non-linear mapping, on the one hand, the characteristics of the second type of data are preserved, on the other hand, it is reduced The data dimension is reduced, which reduces the generation of subsequent situation portraits and improves the efficiency of situation portrait generation.
  • the denoising process here includes removing outliers and redundant data, for example, removing outliers according to the range of normal values, and for example, removing redundant redundant data, a On the one hand, it reduces the accuracy of the interference results of redundant data, on the other hand, it reduces the amount of data processing.
  • this embodiment provides a data processing apparatus, including:
  • the first obtaining module 110 is configured to obtain an individual portrait generated based on the first type of data
  • the second obtaining module 120 is configured to obtain a situation portrait generated based on the second type of data
  • the allocation module 130 is configured to allocate tokens generated by participating in the blockchain record according to the situation portraits among users of the same type based on the individual portraits.
  • the second acquisition module 120 is configured to acquire a situation portrait of the current period generated based on the second type of data of the user in the current period, wherein the situation portrait includes at least one of the following: characterizing the user A motion portrait of the user's movement state in the current period, a health portrait representing the user's health state in the current period, and an emotion portrait representing the user's emotional state in the current period.
  • the first acquisition module 110 is configured to acquire an individual portrait generated based on long-term data of the user in the first period; the second acquisition module 120 is specifically configured to acquire the user in the second period A portrait of the situation generated by real-time data of, where the first time period is longer than the second time period.
  • the first obtaining module 110 is configured to obtain an individual portrait generated based on network behavior data actively participated by the user; the second obtaining module 120 is specifically used to obtain user passive data collected by the Internet of Things device The generated portrait of the situation.
  • the first obtaining module 110 is configured to obtain at least one of user age information, gender information, occupational characteristic information, physical fitness information, reading behavior characteristic information, preference information, and aversion information.
  • the generated individual portrait; and/or, the second obtaining module 120 is specifically configured to obtain a situation portrait generated based on at least one of user motion data and sign data collected by the wearable device.
  • the device further includes:
  • the recommendation module is configured to perform service recommendation based on the individual portrait and the situation portrait.
  • the device further includes:
  • a third obtaining module configured to obtain feedback information based on the service recommendation
  • An update module configured to update the model parameters of the first model based on the feedback information; and/or, update the model parameters of the second model based on the feedback information, wherein the first model is a model that generates the individual portrait ;
  • the second model is a model that generates the situation portrait.
  • the device further includes:
  • the determination module is configured to determine a collection parameter of the second type of data according to the situation portrait, where the collection parameter includes at least one of the following: a collection frequency and a collection object.
  • the device further includes:
  • a preprocessing module configured to preprocess the second type of data
  • the generation module is configured to generate the situation portrait based on the preprocessed second type data.
  • the preprocessing module is specifically configured to perform at least one of the following: performing dimensionality reduction processing on the second type data to obtain feature data of a predetermined dimension; and removing the second type data Noise processing to obtain feature data from which noise data is removed, wherein the noise data includes at least one of abnormal data and redundant data; the generating module is specifically configured to generate the scenario based on the pre-processed feature data portrait.
  • this example proposes a data processing method based on a smart contract of a wearable device sports blockchain.
  • Long-term user-centric Internet data is combined with decentralized real-time data of the IoT wearable blockchain.
  • It is an Internet user portrait, now it is a combination of the Internet and Internet of Things user portraits, to judge real-time situations, that is, different ages, physical qualities, and occupational characteristics of people with time-based classification of separate computing power calculations, establishing a "thousands of people" consensus Mechanism to form a computing model of different user portraits in different situations that is most conducive to universal participation.
  • the data dimension is more abundant, the information source is true and reliable, and the user portrait is more three-dimensional, which helps advertisers improve the conversion rate of ad serving.
  • the sharing of data can be rewarded, and their own privacy can also be protected.
  • the method provided in this example can establish the most suitable marketing and situational service recommendation scheme for everyone based on the user's demographic attributes, historical personal preference setting data, combined with the sports context data collected by the Internet of Things signs, and time period feature information.
  • An evaluation system is established for each social quality.
  • the individual model is continuously revised and corrected.
  • the individual model is used as the input factor of the feature portrait crowd during the same perception, and the corresponding feature portrait model is continuously optimized.
  • the "individual portrait activity situation portrait model" suitable for individuals is formed, and the input contribution factor is provided for the establishment of the "overall crowd activity portrait model".
  • the user portraits in different periods based on individual and group characteristics can form the most "understand you” artificial intelligence user portrait method without the user's perception.
  • the user portrait of "knowing you” here is a user portrait that can accurately reflect user preferences and/or user habits.
  • This embodiment provides a data node, including:
  • Memory configured for information storage
  • a processor connected to the memory, is configured to implement the method provided by one or more of the foregoing technical solutions by executing computer-executable instructions stored in the memory, for example, the method shown in FIG. 1 and/or FIG. 2.
  • This embodiment provides a computer storage medium for storing computer-executable instructions; after the computer-executable instructions are executed by a processor, the method provided by one or more of the foregoing technical solutions can be implemented, for example, The method shown in FIG. 1 and/or FIG. 2.
  • the computer storage medium may be a non-transitory storage medium.
  • the disclosed device and method may be implemented in other ways.
  • the device embodiments described above are only schematic.
  • the division of the unit is only a logical function division, and in actual implementation, there may be another division manner, for example, multiple units or components may be combined, or Can be integrated into another system, or some features can be ignored, or not implemented.
  • the coupling or direct coupling or communication connection between the displayed or discussed components may be through some interfaces, and the indirect coupling or communication connection of the device or unit may be electrical, mechanical, or other forms of.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place or distributed to 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.
  • the functional units in the embodiments of the present disclosure may all be integrated into one processing module, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above integration
  • the unit can be implemented in the form of hardware, or in the form of hardware plus software functional units.
  • the foregoing program may be stored in a computer-readable storage medium, and when the program is executed, Including the steps of the above method embodiments; and the foregoing storage media include: mobile storage devices, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disks or optical disks, etc. A medium that can store program code.

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • Human Resources & Organizations (AREA)
  • Economics (AREA)
  • Development Economics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Accounting & Taxation (AREA)
  • Tourism & Hospitality (AREA)
  • Finance (AREA)
  • Game Theory and Decision Science (AREA)
  • Educational Administration (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Computing Systems (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

一种数据处理方法及装置、数据节点及存储介质，其中所述方法包括：获取基于第一类数据生成的个体画像（S110）；获取基于第二类数据生成的情境画像，其中，所述情境画像用于表征用户的当前状态（S120）；基于所述个体画像，在同一类用户中按照所述情境画像分配参与区块链记录生成的令牌（S130）。

Description

数据处理方法及装置、数据节点及存储介质 技术领域
本公开涉及信息技术领域但不限于信息技术领域，尤其涉及一种数据处理方法及装置、数据节点及存储介质。
背景技术
区块链生成的过程中，一般是基于工作量证明机制的。在工作量证明机制下，基于数据节点的计算能力(简称算力)竞争生成区块链记录的令牌(Token)；若成功竞争到了令牌，在参与区块链的记录或区块生成的同时，会获得代币作为建立。在这种机制下，区块链的生成，就成了矿机的算力竞争。如此，一方面，参与竞争的计算节点的算力最强一般都是特定用户节点，或者是特定的设备，如此，若参与竞争的计算节点越多，则令牌的竞争难度越大，甚至呈指数级上升。这种算力竞争也是消耗能量的，且虽则竞争的激烈程度的越来越激励，消耗的能量就越多。另一方面，这种基于矿机的计算能力的竞争，会产生马太效应，即具有强大的矿机的用户，就能够频繁抢占到令牌，而其他用户就无法参与到区块链的生成，如此会导致区块链生成中参与用户数量减少，从而使得用户活跃度降低。
发明内容
有鉴于此，本公开实施例期望提供一种数据处理方法及装置、数据节点及存储介质。
本公开的技术方案是这样实现的：
本公开实施例第一方面提供一种数据处理方法，包括：
获取基于第一类数据生成的个体画像；
获取基于第二类数据生成的情境画像，其中，所述情境画像用于表征用户 的当前状态；
基于所述个体画像，在同一类用户中按照所述情境画像分配参与区块链记录生成的令牌。
基于上述方案，所述获取基于第二类数据生成的情境画像，包括：
获取基于用户在当前时段内的第二类数据生成的当前时段的情境画像，其中，所述情境画像包括以下至少之一：表征用户当前时段内用户运动状态的运动画像、表征当前时段内用户健康状态的健康画像、表征当前时段内用户情绪状态的情绪画像。
基于上述方案，所述获取基于第一类数据生成的个体画像，包括：获取基于用户的第一时段内的长期数据生成的个体画像；所述获取基于第二类数据生成的情境画像，包括：获取用户的第二时段内的实时数据生成的情境画像，其中，所述第一时段长于所述第二时段；
或者，
所述获取基于第一类数据生成的个体画像，包括：获取基于用户主动参与的网络行为数据生成的个体画像；所述获取基于第二类数据生成的情境画像，包括：获取物联网设备采集的用户被动数据生成的情境画像。
基于上述方案，所述获取基于第一类数据生成的个体画像，包括：
获取基于用户年龄信息、性别信息、职业特点信息、身体素质信息、阅读行为特征信息、偏好信息及厌恶信息中的至少其中之一生成的个体画像；
和/或，
所述获取基于第二类数据生成的情境画像，包括：
获取基于可穿戴式设备采集的用户运动数据及体征数据的至少其中之一生成的情境画像。
基于上述方案，所述方法还包括：
基于所述个体画像及所述情境画像，进行服务推荐。
基于上述方案，所述方法还包括：
获取基于所述服务推荐的反馈信息；
基于所述反馈信息更新第一模型的模型参数；和/或，基于所述反馈信息更新第二模型的模型参数，其中，所述第一模型为生成所述个体画像的模型；所述第二模型为生成所述情境画像的模型。
基于上述方案，所述方法还包括：
根据所述情境画像，确定所述第二类数据的采集参数，其中，所述采集参数包括以下至少之一：采集频率及采集对象。
基于上述方案，所述方法还包括：
对所述第二类数据进行预处理；
基于预处理后的所述第二类数据生成所述情境画像。
基于上述方案，所述对所述第二类数据进行预处理，包括以下至少之一：
对所述第二类数据进行降维处理，获得预定维数的特征数据；
对所述第二类数据进行去噪处理，获得去除噪声数据的特征数据，其中，所述噪声数据包括：异常数据及冗余数据的至少其中之一；
所述基于预处理后的所述第二类数据生成所述情境画像，包括：
基于预处理后的特征数据生成所述情境画像。
本公开实施例第二方面提供一种数据处理装置，包括：
第一获取模块，配置为获取基于第一类数据生成的个体画像；
第二获取模块，配置为获取基于第二类数据生成的情境画像；
分配模块，配置为基于所述个体画像，在同一类用户中按照所述情境画像分配参与区块链记录生成的令牌。
本公开实施例第三方面提供一种数据节点，包括：
存储器，配置为信息存储；
处理器，与所述存储器连接，用于通过执行所述存储器存储的计算机可执行指令，实现前述一个或多个技术方案提供的数据处理方法。
本公开实施例第四方面提供一种计算机存储介质，所述计算机存储介质用于存储计算机可执行指令；所述计算机可执行指令被处理器执行后，能够实现前述一个或多个技术方案提供的数据处理方法。
本公开实施例提供的数据处理方法及装置、数据节点及存储介质，在进行区块链记录的令牌分配时，不再是单纯结合矿机的计算能力确定的，而是根据用户的个体画像在同一类用户的情境画像进行分配，实现的是同一类用户之间的竞争；一方面，单纯相对于矿机的计算能力进行竞争，减少了因为工作量证明产生大量的功耗，节省了功耗，实现了绿色环保；另一方面，在同一类用户之间结合情境画像进行竞争，减少了不同类用户之间竞争的不公平性，减少了因为不公平性导致的特定类型的用户退出竞争，确保了长期的用户活跃度和参与度。
附图说明
图1为本公开实施例提供的第一种数据处理方法的流程示意图；
图2为本公开实施例提供的第二种数据处理方法的流程示意图；
图3为本公开实施例提供的一种数据处理装置的结构示意图；
图4为本公开实施例提供的第三种数据处理方法的流程示意图。
具体实施方式
以下结合说明书附图及具体实施例对本公开的技术方案做进一步的详细阐述。
如图1所示，本实施例提供一种数据处理方法，包括：
步骤S110：获取基于第一类数据生成的个体画像；
步骤S120：获取基于第二类数据生成的情境画像，其中，所述情境画像用于表征用户的当前状态；
步骤S130：基于所述个体画像，在同一类用户中按照所述情境画像分配参与区块链记录生成的令牌。
本实施例提供的数据处理方法，可以应用于区块链的生成，例如，应用于区块链中智能合约的生成。
在一些实施例中，区块链的区块可以按照预定时间间隔生成，例如，每个 10分钟、5分钟、15分钟或者20分钟生成一个区块。在一些实施例中，统计产生的区块链记录的条数，当达到预定条数时就生成一个区块。
在本实施例中首先会获取基于第一类数据生成的个体画像；该个体画像可以用于表征用户的特征，该用户的特征可包括：用户的年纪、性别、学历、职业、喜好等。
基于个体画像可以进行用户的分类，例如，将特征相似的用户分为一个类。例如，通过聚类算法，将具有相同特点或相似特点的用户分为同一个类。如此，运动员可能就会分成一个类。
在步骤S120还会基于第二类数据生成情境画像，情境画像用于表征用户的当前状态，例如，用户的当前运动状态、用户当前的情绪状态及用户当前的健康状态的至少其中之一。
在步骤S130中，将结合个体画像，在同一类用户中按照情境画像分配生成区块链记录的令牌，获得令牌的用户就能够获得至少一条区块链记录的记账权利，从而争取到了获得代币的权利，从而避免了单纯利用矿机的计算能力来争取令牌导致的大量功耗。
例如，所述步骤S130可包括：
根据所述个体画像，对用户进行分类获得N个用户分类；
在多个用户分类之间进行令牌分配的轮询，若当前轮询到第n类用户，在在第n类用户中根据所述情境画像选择一个用户获得本次轮询的令牌。
例如，N等于5，若区块链的生成过程中产生了一个新的令牌，前一个令牌轮询到第3类用户，则当前令牌轮询到了第4类用户。此时，所述步骤S130可包括：根据第3类用户的情境特征，选择一个用户获得该令牌；如此，下一个获得令牌轮询的是第4类用户。
在还有一些实施例中，所述步骤S130可包括：
根据不同类用户的用户数在所有用户数中所占的比值，确定不同类用户之前的令牌分配比值；
根据令牌分配比值及前一个令牌所分配的用户类，确定获得当前令牌所要 分配的用户类；
在确定的用户类中按照情境画像分配令牌。
例如，假设有3类用户，这三类用户之间的用户数比值为：1：m：n；则3类用户获得令牌数的比值也等于1：m：n。如此，每一类别的用户都有获得令牌的几率，且每一类用户中单个用户获得令牌的几率也趋相等，则减少了用户之间基于矿机算力的竞争产生的大量的能量消耗，且兼顾了令牌分配的公平性。
所述情境画像表征了用户的当前状态，例如，所述当前状态为运动状态，则在步骤S130中，在一类用户的所有用户中，选择当前时段内运动量最大的用户获得所述令牌。由于是在同一个类用户中进行令牌分配，这就可以避免或至少减少运动员和办公室白领基于运动量竞争一个令牌的不公平现象，提升了令牌竞争的公平性，从而减少因为令牌竞争的不公平性导致用户丧失兴趣，导致用户参与量或活跃度低的问题，从而提升用户的参与积极性。
在步骤S130中还可包括：在一类用户的所有用户中，选择当前时间段内用户的情绪特征，选择分配令牌的用户。例如，选择情绪最健康的用户获得所述令牌。此处情绪健康的评价指标可以由一个或多个，例如、总之，情绪健康可以是基于多个生理信号产生的，例如，心跳信号及脑电波信号等。
在还有一些实施例中，在一类用户的所有用户中，根据用户的当前健康状态的情绪特征，选择分配令牌的用户。例如，所述健康状态的评价指标同样有多个，同样是可以采集生理信号来获得。如此，不同年龄段、不同性别、不同职业的用户的健康状态可能是呈现一定的群体特征。例如，健壮的青年显然比老年人的健康状态整体上更好，由于在本实施例中首先基于个体画像选择了是在同一类用户之间分配令牌，如此，可以避免不区分青年人和老年人的特点，来分配令牌，导致的令牌分配的不公平性。如此，若根据当前健康状态进行令牌的分配，还可以区分不同类用户以鼓励同类用户之间的健康竞争，有利于用户健康的提升。
故在一些实施例中，所述步骤S120可包括：
获取基于用户在当前时段内的第二类数据生成的当前时段的情境画像，其 中，所述情境画像包括以下至少之一：表征用户当前时段内用户运动状态的运动画像、表征当前时段内用户健康状态的健康画像、表征当前时段内用户情绪状态的情绪画像。此时，所述步骤S130可包括：结合所述运动画像、健康画像及情绪画像的至少其中之一，在同一类用户中选择用户分配所述令牌。
在一些实施例中，例如，基于运动画像分配令牌，可包括：选择当前时段内运动量相对于前一个时段内运动量增加量最大的用户分配令牌；或者，选择当前时段内运动量相对于该用户平常运动量增加量最大的用分配令牌，从而达到鼓励运动的目的。
在还有一些实施例中，例如，基于情绪画像分配令牌，可包括：选择情绪维持在愉悦状态或平静状态时间最长的用户分配该令牌，或者，选择从悲观情绪转换到愉悦情绪之间情绪跨度最大的用户分配该令牌，以鼓励维持愉悦情绪，以提升用户的情绪愉悦度。
在还有一些实施例中，例如，基于健康画像分配令牌，可包括：
选择当前时段内健康程度提升最快的用户分配令牌，或者，选择维持健康状态最长时间的用户分配令牌，以鼓励用户长期维持健康状态或尽快脱离非健康状态或亚健康状态。
在一些实施例中，所述步骤S110可包括：获取基于用户的第一时段内的长期数据生成的个体画像；
所述步骤S120可包括：获取用户的第二时段内的实时数据生成的情境画像，其中，所述第一时段长于所述第二时段。
所述第一时段的计时单元至少是天的，甚至是周、月或者年的。所述第一类数据为长期数据，包括但不限于用户长期的网络行为数据。长期数据反应的是用户长期的相对静止的特点。
所述第二类数据可为动态数据，是短时间内的数据。例如，所述第二时段的计时单元可为是小时、甚至是分钟等。
所述第二类数据是反应了当前情境下用户的动态特点。
如此，在步骤S130中进行令牌分配时，可以结合用户的长期特点和当前的 动态特点(或瞬间特点)来分配令牌，兼顾分配令牌的公平性。
在一些实施例中，所述步骤S110还可包括：获取基于用户主动参与的网络行为数据生成的个体画像；所述步骤S120可包括：获取物联网设备采集的用户被动数据生成的情境画像。
用户通常会主动参与一些活动，从而提供了主动参与的行为数据，例如，用户网页浏览行为、用户的网络社交行为、用户的网络购物行为等。这些行为都是用户有意识的主动参与的行为产生的行为数据。
物联网设备采集的数据，可能是用户无意识主动控制产生的数据，例如，用户的呼吸数据、再例如，用户的心跳数据、用户的脉搏数据等。这些用户数据都物理网设备主动采集，但是并非用户主动提供或主动有意识提供的。
总之，所述第一类数据和第二类数据为不同类型的数据，上述为第一类数据和第二类数据的举例，具体实现时不局限于此。
所述物联网设备可包括但不限于可穿戴式设备，例如，智能手表、智能手环、智能脚环或者智能鞋或智能衣等。
在一些实施例中，所述步骤S110可包括：获取基于用户年龄信息、性别信息、职业特点信息、身体素质信息、阅读行为特征信息、偏好信息及厌恶信息中的至少其中之一生成的个体画像。
由于，基于性别信息进行个体画像，如此，在后续进行用户分类时，可以考虑到性别分类，如此，若基于运动画像进行令牌分配时，可以考虑到男女体力差别，减少令牌在性别分配上的不公平性。
例如，有的用户喜好某一种动物或者某一种运动，但是有的用户却讨厌对应的动物或运动，这种喜好可以用偏好信息来表征，这种讨厌可以用厌恶信息来表征。
在一些实施例中，所述步骤S120可包括：
获取基于可穿戴式设备采集的用户运动数据及体征数据的至少其中之一生成的情境画像。
所述用户运动数据可包括：当前时段内的行走的步数、当前跑步的里数等 数据。
所述体征数据可为表征用户身体状况的数据，例如，运动状态下和静止状态下，用户的每分钟呼吸的次数或脉搏跳动次数是不同的，故还可以根据体征数据来生成所述情境画像，此时，生成的情境画像，可以是前述的运动画像、情绪画像或健康画像的至少其中之一。
在一些实施例中，如图2所示，所述方法还包括：
步骤S140：基于所述个体画像及所述情境画像，进行服务推荐。
此处的服务推荐，包括但不限于以下至少之一：
内容推荐服务；
购物推荐服务；
社交推荐服务。
所述内容推荐服务可包括：各种多媒体信息的内容推荐，例如，推荐用户观影的电影、电视剧等视频、图文信息。例如，所述内容推荐服务可包括：广告分发服务。例如，结合用户的个体画像和情境画像，向用户所持有的终端设备或者社交账号分发广告，该广告的广告物可能就是用户当前情境下感兴趣的内容。
例如，购物推荐服务可以在购物应用中推送用户感兴趣的物品或服务。
所述社交推荐服务可包括：向用户推荐其可能愿意结交的社交好友等等。
在本实施例中，将结合个体画像和情境画像进行各种服务的推荐，从而使得推荐的参考因素更多，从而实现更精准的服务推荐。
在一些实施例中，如图2所示，所述方法还包括：
步骤S150：获取基于所述服务推荐的反馈信息；
步骤S160：基于所述反馈信息更新第一模型的模型参数；和/或，基于所述反馈信息更新第二模型的模型参数，其中，所述第一模型为生成所述个体画像的模型；所述第二模型为生成所述情境画像的模型。
若结合个人画像和情境画像向用于推荐服务之后，还会监控服务推荐的反馈信息，例如，向用户推荐图文，将监控用户是否阅读了对应的图文信息，再 例如，向用户进行购物推荐，将根据用户是否流量了推荐的物品的展示页面、是否购买了同推荐的物品等反馈信息，来确定当前推荐是否精准。若不精准将根据反馈信息，修正第一模型和/或第二模型的模型参数。此处的第一模型和第二模型都可为机器学习模型，该机器学习模型可为向量机模型或深度学习模型等。
在一些实施例中，所述方法还包括：
根据所述情境画像，确定所述第二类数据的采集参数，其中，所述采集参数包括以下至少之一：采集频率及采集对象。
在本实施例中，所述方法还会根据情境画像，确定需要采集的第二类数据的采集参数，例如，用户身上佩戴有多种可穿戴式设备，若这些设备都同时工作，显然也是耗能的，在本实施例中，可以根据用户当前的情境画像，确定需要采集第二类数据的具体哪一子类的数据，或者，采集频率；减少不必要的数据的采集，降低因为不必要数据采集的功耗。在一些实施例中，还可以根据情境画像，提升采集频率和/或增加的采集的第二类数据的种类，从而获得更加全面和精准的情境画像。
总之，在本公开实施例中，会根据所述情境画像反向控制第二类数据的采集参数，从而实现第二类数据采集的精准控制。
在一些实施例中，所述方法还包括：对所述第二类数据进行预处理；基于预处理后的所述第二类数据生成所述情境画像。
在本实施例中，第二类数据采集之后，可能存在噪声，为了提升基于第二类数据产生的情境画像的精准度，将会进行第二类数据的预处理。
例如，所述对所述第二类数据进行预处理，包括以下至少之一：
对所述第二类数据进行降维处理，获得预定维数的特征数据；
对所述第二类数据进行去噪处理，获得去除噪声数据的特征数据，其中，所述噪声数据包括：异常数据及冗余数据的至少其中之一；
所述基于预处理后的所述第二类数据生成所述情境画像，包括：
基于预处理后的特征数据生成所述情境画像。
通过降维处理，可以使得高维数据映射为低维数据，从而使得在生成情境画像时，减少数据量。
例如，采用非线性映射，将第二类数据中的多个维度的数据映射为一个维度的数据，由于采用这种非线性映射，一方面保留第二类数据所要展示的特征，另一方面降低了数据维度，从而减化了后续情境画像的生成，提升了情境画像的生成效率。
在本实施例中还包括去噪处理，此处的去噪处理包括去除异常值及冗余数据，例如，根据正常值的区间范围去除异常值，再例如，将重复冗余数据的去除，一方面减少冗余数据的干扰结果的精确度，另一方面更，减少数据处理量。
如图3所示，本实施例提供一种数据处理装置，包括：
第一获取模块110，配置为获取基于第一类数据生成的个体画像；
第二获取模块120，配置为获取基于第二类数据生成的情境画像；
分配模块130，配置为基于所述个体画像，在同一类用户中按照所述情境画像分配参与区块链记录生成的令牌。
在一些实施例中，所述第二获取模块120，配置为获取基于用户在当前时段内的第二类数据生成的当前时段的情境画像，其中，所述情境画像包括以下至少之一：表征用户当前时段内用户运动状态的运动画像、表征当前时段内用户健康状态的健康画像、表征当前时段内用户情绪状态的情绪画像。
在一些实施例中，所述第一获取模块110，配置为获取基于用户的第一时段内的长期数据生成的个体画像；所述第二获取模块120，具体用于获取用户的第二时段内的实时数据生成的情境画像，其中，所述第一时段长于所述第二时段。
在一些实施例中，所述第一获取模块110，配置为获取基于用户主动参与的网络行为数据生成的个体画像；所述第二获取模块120，具体用于获取物联网设备采集的用户被动数据生成的情境画像。
在另一些实施例中，所述第一获取模块110，配置为获取基于用户年龄信息、性别信息、职业特点信息、身体素质信息、阅读行为特征信息、偏好信息 及厌恶信息中的至少其中之一生成的个体画像；和/或，所述第二获取模块120，具体用于获取基于可穿戴式设备采集的用户运动数据及体征数据的至少其中之一生成的情境画像。
在一些实施例中，所述装置还包括：
推荐模块，配置为基于所述个体画像及所述情境画像，进行服务推荐。
在一些实施例中，所述装置还包括：
第三获取模块，配置为获取基于所述服务推荐的反馈信息；
更新模块，配置为基于所述反馈信息更新第一模型的模型参数；和/或，基于所述反馈信息更新第二模型的模型参数，其中，所述第一模型为生成所述个体画像的模型；所述第二模型为生成所述情境画像的模型。
在一些实施例中，所述装置还包括：
确定模块，配置为根据所述情境画像，确定所述第二类数据的采集参数，其中，所述采集参数包括以下至少之一：采集频率及采集对象。
在一些实施例中，所述装置还包括：
预处理模块，配置为对所述第二类数据进行预处理；
生成模块，配置为基于预处理后的所述第二类数据生成所述情境画像。
在一些实施例中，所述预处理模块，具体用于执行以下至少之一：对所述第二类数据进行降维处理，获得预定维数的特征数据；对所述第二类数据进行去噪处理，获得去除噪声数据的特征数据，其中，所述噪声数据包括：异常数据及冗余数据的至少其中之一；所述生成模块，具体用于基于预处理后的特征数据生成所述情境画像。
以下结合上述任意实施例提供一个具体示例：
示例1：
参考图4所示，本示例提出一种基于穿戴设备运动区块链智能合约的数据处理方法，用户中心化的互联网长期数据与去中心化的物联网可穿戴区块链实时数据相结合，以往是互联网用户画像，现在是互联网和物联网用户画像相结合，判断实时情境，即不同年龄、身体素质、职业特点人群进行分时 分类的分别的算力计算，建立“千人千面”的共识机制，形成最有利于全民参与的普适性的不同用户画像在不同情境下的算力模型。同时数据维度更加丰富、信息来源真实可靠、用户画像更加立体，帮助广告主提高广告投放转化率。对于用户来说，分享数据的行为可以获得奖励，并且自身的隐私权也能得到保护。
本示例提供的方法，能够根据使用者人口特征属性、历史个人偏好设定数据、结合物联网体征采集的运动情境数据判断、时段特征信息，为每个人建立最适合的营销和情境服务推荐方案，并对每次社交质量建立评估体系，根据有监督的多层回馈模型，不断反馈修正个体模型，同感知时个体模型作为该特征画像人群的输入因子，不断优化其对应特征画像模型。从而一方面形成了最适合个人的“个体画像活动情境画像模型”，又为建立“整体人群活动画像模型”提供输入贡献因子。结合物联网丰富的线下数据来源，使得基于个体和群体特征不同时段的用户画像，在用户无感知的情况下，形成最“懂您”的人工智能用户画像方法。此处的“懂您”的用户画像，即为能够精确反映用户喜好和/或用户习惯的用户画像。
本实施例提供一种数据节点，包括：
存储器，配置为信息存储；
处理器，与所述存储器连接，用于通过执行所述存储器存储的计算机可执行指令，实现前述一个或多个技术方案提供的方法，例如，图1和/或图2所示的方法。
本实施例提供一种计算机存储介质，所述计算机存储介质用于存储计算机可执行指令；所述计算机可执行指令被处理器执行后，能够实现前述一个或多个技术方案提供的方法，例如，图1和/或图2所示的方法。该计算机存储介质可为非瞬间存储介质。
在本申请所提供的几个实施例中，应该理解到，所揭露的设备和方法，可以通过其它的方式实现。以上所描述的设备实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分 方式，如：多个单元或组件可以结合，或可以集成到另一个系统，或一些特征可以忽略，或不执行。另外，所显示或讨论的各组成部分相互之间的耦合、或直接耦合、或通信连接可以是通过一些接口，设备或单元的间接耦合或通信连接，可以是电性的、机械的或其它形式的。
上述作为分离部件说明的单元可以是、或也可以不是物理上分开的，作为单元显示的部件可以是、或也可以不是物理单元，即可以位于一个地方，也可以分布到多个网络单元上；可以根据实际的需要选择其中的部分或全部单元来实现本实施例方案的目的。
另外，在本公开各实施例中的各功能单元可以全部集成在一个处理模块中，也可以是各单元分别单独作为一个单元，也可以两个或两个以上单元集成在一个单元中；上述集成的单元既可以采用硬件的形式实现，也可以采用硬件加软件功能单元的形式实现。
本领域普通技术人员可以理解：实现上述方法实施例的全部或部分步骤可以通过程序指令相关的硬件来完成，前述的程序可以存储于一计算机可读取存储介质中，该程序在执行时，执行包括上述方法实施例的步骤；而前述的存储介质包括：移动存储设备、只读存储器(Read-Only Memory，ROM)、随机存取存储器(Random Access Memory，RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述，仅为本公开的具体实施方式，但本公开的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本公开揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本公开的保护范围之内。因此，本公开的保护范围应以所述权利要求的保护范围为准。

Claims (12)

  1. 一种数据处理方法，其中，包括：
    获取基于第一类数据生成的个体画像；
    获取基于第二类数据生成的情境画像，其中，所述情境画像用于表征用户的当前状态；
    基于所述个体画像，在同一类用户中按照所述情境画像分配参与区块链记录生成的令牌。
  2. 根据权利要求1所述的方法，其中，
    所述获取基于第二类数据生成的情境画像，包括：
    获取基于用户在当前时段内的第二类数据生成的当前时段的情境画像，其中，所述情境画像包括以下至少之一：表征用户当前时段内用户运动状态的运动画像、表征当前时段内用户健康状态的健康画像、表征当前时段内用户情绪状态的情绪画像。
  3. 根据权利要求1所述的方法，其中，
    所述获取基于第一类数据生成的个体画像，包括：获取基于用户的第一时段内的长期数据生成的个体画像；所述获取基于第二类数据生成的情境画像，包括：获取用户的第二时段内的实时数据生成的情境画像，其中，所述第一时段长于所述第二时段；
    或者，
    所述获取基于第一类数据生成的个体画像，包括：获取基于用户主动参与的网络行为数据生成的个体画像；所述获取基于第二类数据生成的情境画像，包括：获取物联网设备采集的用户被动数据生成的情境画像。
  4. 根据权利要求1所述的方法，其中，
    所述获取基于第一类数据生成的个体画像，包括：
    获取基于用户年龄信息、性别信息、职业特点信息、身体素质信息、阅读行为特征信息、偏好信息及厌恶信息中的至少其中之一生成的个体画像；
    和/或，
    所述获取基于第二类数据生成的情境画像，包括：
    获取基于可穿戴式设备采集的用户运动数据及体征数据的至少其中之一生成的情境画像。
  5. 根据权利要求1至4任一项所述的方法，其中，所述方法还包括：
    基于所述个体画像及所述情境画像，进行服务推荐。
  6. 根据权利要求5所述的方法，其中，所述方法还包括：
    获取基于所述服务推荐的反馈信息；
    基于所述反馈信息更新第一模型的模型参数；和/或，基于所述反馈信息更新第二模型的模型参数，其中，所述第一模型为生成所述个体画像的模型；所述第二模型为生成所述情境画像的模型。
  7. 根据权利要求1至4任一项所述的方法，其中，所述方法还包括：
    根据所述情境画像，确定所述第二类数据的采集参数，其中，所述采集参数包括以下至少之一：采集频率及采集对象。
  8. 根据权利要求1至4任一项所述的方法，其中，所述方法还包括：
    对所述第二类数据进行预处理；
    基于预处理后的所述第二类数据生成所述情境画像。
  9. 根据权利要求8所述的方法，其中，
    所述对所述第二类数据进行预处理，包括以下至少之一：
    对所述第二类数据进行降维处理，获得预定维数的特征数据；
    对所述第二类数据进行去噪处理，获得去除噪声数据的特征数据，其中，所述噪声数据包括：异常数据及冗余数据的至少其中之一；
    所述基于预处理后的所述第二类数据生成所述情境画像，包括：
    基于预处理后的特征数据生成所述情境画像。
  10. 一种数据处理装置，其中，包括：
    第一获取模块，配置为获取基于第一类数据生成的个体画像；
    第二获取模块，配置为获取基于第二类数据生成的情境画像；
    分配模块，配置为基于所述个体画像，在同一类用户中按照所述情境画像分配参与区块链记录生成的令牌。
  11. 一种数据节点，其中，包括：
    存储器，配置为信息存储；
    处理器，与所述存储器连接，用于通过执行所述存储器存储的计算机可执行指令，实现权利要求1至9任一项提供的方法。
  12. 一种计算机存储介质，所述计算机存储介质用于存储计算机可执行指令；所述计算机可执行指令被处理器执行后，能够实现权利要求1至9任一项提供的方法。
PCT/CN2019/130822 2019-01-02 2019-12-31 数据处理方法及装置、数据节点及存储介质 WO2020140911A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910002349.1 2019-01-02
CN201910002349.1A CN111461468B (zh) 2019-01-02 2019-01-02 数据处理方法及装置、数据节点及存储介质

Publications (1)

Publication Number Publication Date
WO2020140911A1 true WO2020140911A1 (zh) 2020-07-09

Family

ID=71407124

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/130822 WO2020140911A1 (zh) 2019-01-02 2019-12-31 数据处理方法及装置、数据节点及存储介质

Country Status (2)

Country Link
CN (1) CN111461468B (zh)
WO (1) WO2020140911A1 (zh)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150086949A1 (en) * 2013-09-20 2015-03-26 Hong Li Using user mood and context to advise user
CN105718579A (zh) * 2016-01-22 2016-06-29 浙江大学 一种基于上网日志挖掘和用户活动识别的信息推送方法
CN107391603A (zh) * 2017-06-30 2017-11-24 北京奇虎科技有限公司 用于移动终端的用户画像建立方法及装置
CN107679898A (zh) * 2017-09-26 2018-02-09 浪潮软件股份有限公司 一种商品推荐方法和装置
CN109003143A (zh) * 2018-08-03 2018-12-14 阿里巴巴集团控股有限公司 利用深度强化学习进行推荐营销的方法及装置

Family Cites Families (25)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10078691B2 (en) * 2013-12-27 2018-09-18 Futurewei Technologies, Inc. System and method for biometrics-based music recommendation
CN105574730A (zh) * 2014-10-10 2016-05-11 中兴通讯股份有限公司 基于物联网大数据平台的智能用户画像方法及装置
GB2539430A (en) * 2015-06-16 2016-12-21 The Provost Fellows Found Scholars & The Other Members Of Board Of The College Of The Holy & Unidv T Digital token exchange system
WO2017180382A1 (en) * 2016-04-12 2017-10-19 Pcms Holdings, Inc. System and method for data validation in a decentralized sensor network
CN105930425A (zh) * 2016-04-18 2016-09-07 乐视控股（北京）有限公司 个性化视频推荐方法及装置
KR101773073B1 (ko) * 2016-04-28 2017-08-31 주식회사 코인플러그 거래를 지원하기 위한 방법 및 이를 사용한 인증 지원 서버
WO2018069566A1 (en) * 2016-10-14 2018-04-19 Nokia Technologies Oy Method, device and system for validating sensitive user data transactions within trusted circle
CA2948230C (en) * 2016-11-10 2022-05-31 The Toronto-Dominion Bank Systems and method for tracking subdivided ownership of connected devices using block-chain ledgers
JP6775086B2 (ja) * 2016-12-16 2020-10-28 株式会社日立製作所 ブロックチェーン監視及び管理
KR101837169B1 (ko) * 2016-12-29 2018-03-09 주식회사 코인플러그 영지식 증명 알고리즘을 사용하여 머클 트리 구조의 블록체인 기반 비밀 전자 투표 서비스를 제공하기 위한 방법, 및 이를 이용한 투표 코인 발행 서버, 투표 토큰 분배 서버 및 투표 지원 서버
US11341488B2 (en) * 2017-02-06 2022-05-24 Northern Trust Corporation Systems and methods for issuing and tracking digital tokens within distributed network nodes
CN107360206B (zh) * 2017-03-29 2020-03-27 创新先进技术有限公司 一种区块链共识方法、设备及系统
JP7060221B2 (ja) * 2017-03-31 2022-04-26 Ｎｅｃソリューションイノベータ株式会社 物品情報管理装置、システム、方法およびプログラム
KR102382127B1 (ko) * 2017-04-05 2022-04-04 삼성에스디에스 주식회사 블록체인 기반의 데이터 처리 시스템 및 그 동작 방법
CN107018146A (zh) * 2017-05-09 2017-08-04 暨南大学 一种基于区块链技术的舆情检测平台建设方法
CN108470277A (zh) * 2018-02-28 2018-08-31 深圳市网心科技有限公司 区块链的奖励结算方法、系统、可读存储介质及计算设备
CN108632358B (zh) * 2018-04-11 2022-06-10 北京奇虎科技有限公司 基于wifi分享的代币管理方法及装置
CN108564469A (zh) * 2018-04-11 2018-09-21 北京奇虎科技有限公司 区块链节点的画像数据获取方法、装置及计算设备
CN108848063B (zh) * 2018-05-24 2021-05-07 苏州朗润创新知识产权运营有限公司 基于区块链的数据处理方法、系统和计算机可读存储介质
CN109117608A (zh) * 2018-06-30 2019-01-01 深圳市元征科技股份有限公司 一种数据处理方法、装置及相关设备
CN108846673B (zh) * 2018-07-02 2022-10-11 苏州我的打工人力资源有限公司 一种区块数据的处理方法、装置、设备和存储介质
KR102121930B1 (ko) * 2018-07-03 2020-06-11 네이버 주식회사 블록체인 기반의 개인 데이터 처리 방법 및 시스템
CN108920682B (zh) * 2018-07-11 2021-08-31 厦门盈趣科技股份有限公司 基于机器学习和用户画像技术的社交用户推荐方法及装置
CN108985774B (zh) * 2018-07-18 2022-05-31 百度在线网络技术（北京）有限公司 一种区块链网络的激励方法、装置、设备及存储介质
CN109118282B (zh) * 2018-08-08 2022-03-15 福建百悦信息科技有限公司 一种双模互感智能空间用户画像管理方法及终端

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150086949A1 (en) * 2013-09-20 2015-03-26 Hong Li Using user mood and context to advise user
CN105718579A (zh) * 2016-01-22 2016-06-29 浙江大学 一种基于上网日志挖掘和用户活动识别的信息推送方法
CN107391603A (zh) * 2017-06-30 2017-11-24 北京奇虎科技有限公司 用于移动终端的用户画像建立方法及装置
CN107679898A (zh) * 2017-09-26 2018-02-09 浪潮软件股份有限公司 一种商品推荐方法和装置
CN109003143A (zh) * 2018-08-03 2018-12-14 阿里巴巴集团控股有限公司 利用深度强化学习进行推荐营销的方法及装置

Also Published As

Publication number Publication date
CN111461468B (zh) 2023-10-31
CN111461468A (zh) 2020-07-28

Similar Documents

Publication Publication Date Title
US20220147535A1 (en) Software agents facilitating affective computing applications
US10387898B2 (en) Crowd-based personalized recommendations of food using measurements of affective response
US11200964B2 (en) Short imagery task (SIT) research method
US10198505B2 (en) Personalized experience scores based on measurements of affective response
US10111611B2 (en) Personal emotional profile generation
US11494390B2 (en) Crowd-based scores for hotels from measurements of affective response
US20190102706A1 (en) Affective response based recommendations
US20160300252A1 (en) Collection of Measurements of Affective Response for Generation of Crowd-Based Results
US20150058327A1 (en) Responding to apprehension towards an experience with an explanation indicative of similarity to a prior experience
US20170095192A1 (en) Mental state analysis using web servers
JP6692239B2 (ja) 情報処理装置、情報処理システム、端末装置、情報処理方法及び情報処理プログラム
US20190108191A1 (en) Affective response-based recommendation of a repeated experience
AU2010239526A1 (en) Method and system for measuring user experience for interactive activities
US11430561B2 (en) Remote computing analysis for cognitive state data metrics
Faust et al. Exploring compliance: Observations from a large scale Fitbit study
CN111465949A (zh) 信息处理设备、信息处理方法和程序
JP2019020882A (ja) ライフログ活用システム、方法及びプログラム
US20220375572A1 (en) Iterative generation of instructions for treating a sleep condition
WO2020140911A1 (zh) 数据处理方法及装置、数据节点及存储介质
CN111192348B (zh) 数据处理方法及装置、电子设备及存储介质
Hsieh et al. Users’ emotional attachments to internet celebrities: Based on the perspective of extended-self
WO2022138153A1 (ja) 情報処理装置および方法、並びにプログラム
US20240134868A1 (en) Software agents correcting bias in measurements of affective response
Clayton Psychophysiological responses to using digital media
JP2019012390A (ja) 肌状態、体状態又は心状態のケアに関する情報出力システム、情報出力プログラム及び情報出力方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19907254

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205 DATED 15/10/2021)

122 Ep: pct application non-entry in european phase

Ref document number: 19907254

Country of ref document: EP

Kind code of ref document: A1