WO2022156236A1 - 获取密接人员信息方法、装置、服务器和存储介质 - Google Patents

获取密接人员信息方法、装置、服务器和存储介质 Download PDF

Info

Publication number
WO2022156236A1
WO2022156236A1 PCT/CN2021/118087 CN2021118087W WO2022156236A1 WO 2022156236 A1 WO2022156236 A1 WO 2022156236A1 CN 2021118087 W CN2021118087 W CN 2021118087W WO 2022156236 A1 WO2022156236 A1 WO 2022156236A1
Authority
WO
WIPO (PCT)
Prior art keywords
bluetooth device
name
information
close contact
bluetooth
Prior art date
Application number
PCT/CN2021/118087
Other languages
English (en)
French (fr)
Inventor
宋轩
聂雨荷
张浩然
庄湛
Original Assignee
南方科技大学
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 南方科技大学 filed Critical 南方科技大学
Publication of WO2022156236A1 publication Critical patent/WO2022156236A1/zh

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W12/00—Security arrangements; Authentication; Protecting privacy or anonymity
    • H04W12/02—Protecting privacy or anonymity, e.g. protecting personally identifiable information [PII]
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/80—Services using short range communication, e.g. near-field communication [NFC], radio-frequency identification [RFID] or low energy communication
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D30/00—Reducing energy consumption in communication networks
    • Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks

Definitions

  • Embodiments of the present invention relate to the field of communications, and in particular, to a method, a device, a server, and a storage medium for acquiring information about a contact person.
  • Bluetooth network device Some manufacturers query personnel information through Bluetooth connection to mobile terminal information.
  • the information broadcast by a Bluetooth network device may indeed be exploited by a potentially malicious mobile phone program, resulting in unexpected location privacy violations, or even targeting invisible Bluetooth devices, infiltrating user equipment, leading to intrusions.
  • the data carrier of the user's device and steal the information.
  • the present invention provides a method for obtaining close contact personnel information.
  • the device close contact information can be obtained by obtaining the encoded bluetooth device name, and no Bluetooth pairing with unfamiliar devices is required, thereby avoiding leakage of user privacy.
  • the present invention provides a method for acquiring information about a contact person, which is executed by a device with a Bluetooth device name scanning function, including:
  • the decoded Bluetooth device name is used as the close contact information of the close contact device.
  • the method further includes:
  • the write operation signal is sent to the device, so that the device modifies the Bluetooth device name based on the write operation signal.
  • the creation process of the codec model also includes:
  • the historical contact data includes user name, personal contact risk factor, personal health status and/or activity area;
  • Neural network training is performed based on the input set and the test set to generate an encoding and decoding model.
  • the method further includes:
  • the Bluetooth device name of the device is not obtained.
  • the bluetooth device names of one or more devices are obtained, and after the bluetooth device names include the bluetooth device names, the bluetooth device names also include:
  • the bluetooth device name is stored in the database, and the number of searches is recorded as 1.
  • the bluetooth device name is sent every preset time interval.
  • the bluetooth device name is sent every preset time interval, it also includes:
  • the present invention provides a device for obtaining information of close contacts, including:
  • an acquisition module used to scan and acquire the Bluetooth device names of one or more close contact devices within a preset distance
  • a decoding module for decoding the Bluetooth device name using a preset codec model
  • a contact information generation module configured to use the decoded name of the Bluetooth device as the contact information of the contact device.
  • the present invention provides a server, including a memory, a processor, and a program stored in the memory and running on the processor, when the processor executes the program, the above-mentioned method of obtaining a contact person can be realized. information method.
  • the present invention provides a terminal-readable storage medium on which a program is stored, and when the program is executed by a processor, any one of the above-mentioned methods for obtaining close contact personnel information can be implemented.
  • the invention can know the device close connection information by acquiring the encoded bluetooth device name, and does not need to be paired with an unfamiliar device, thereby avoiding leakage of user privacy.
  • the model parameters are all obtained by training and kept closed to the outside world, that is, information security is achieved.
  • FIG. 1 is a flow chart of the method for acquiring the information of the close contact personnel in the first embodiment of the present invention.
  • FIG. 2 is a flowchart of an alternative embodiment of the first embodiment.
  • FIG. 3 is a flow chart of the method for obtaining the information of the close contact personnel according to the second embodiment of the present invention.
  • FIG. 4 is a flowchart of an alternative embodiment of the second embodiment.
  • FIG. 5 is a flow chart of the method for acquiring the information of the close contact person in the third embodiment of the present invention.
  • FIG. 6 is a flowchart of an alternative embodiment of the third embodiment.
  • FIG. 7 is a block diagram of a device for obtaining close contact personnel information according to the fourth embodiment.
  • FIG. 8 is a block diagram of an alternative embodiment of the fourth embodiment.
  • FIG. 9 shows the server structure diagram of the fifth embodiment.
  • first, second, etc. may be used herein to describe various directions, acts, steps or elements, etc., but are not limited by these terms. These terms are only used to distinguish a first direction, act, step or element from another direction, act, step or element.
  • the first feature information may be the second feature information or the third feature information, and similarly, the second feature information and the third feature information may be the first feature information.
  • the first feature information, the second feature information, and the third feature information are all feature information of the device for obtaining the contact person information, but they are not the same feature information.
  • the terms “first”, “second” and the like should not be understood as indicating or implying relative importance or implying the number of technical features indicated.
  • a feature defined as “first” or “second” may expressly or implicitly include one or more of that feature.
  • “plurality” and “batch” mean at least two, such as two, three, etc., unless otherwise expressly and specifically defined.
  • seq2seq refers to generating another output sequence y from an input sequence x.
  • seq2seq has many applications, such as translation, document extraction, question answering, etc.
  • the encoder-decoder model first inputs the input set, and the encoder trained by the neural network converts it into a semantic vector C of a specified length, and then the decoder trained by the neural network converts the semantic vector into the desired output set.
  • This embodiment provides a method for acquiring information of a contact person, which is executed by a device with a Bluetooth device name scanning function, and the device is installed with a contact APP for executing the solution. As shown in Figure 1, it includes:
  • S101 Scan and obtain the Bluetooth device names of one or more close contact devices
  • the device scans through Bluetooth for one or more other close contact devices within a distance.
  • the close contact device refers to a device whose distance from the device with the Bluetooth device name scanning function is less than a certain value.
  • the Bluetooth device name refers to the Bluetooth address.
  • the device with the Bluetooth device name scanning function is used as the master device, and other closely connected devices are described as slave devices.
  • the slave device broadcasts its own Bluetooth device name at a set frequency, and the master device obtains the slave device's Bluetooth device name based on the scanned broadcast information. In this process, no protocol will be established between devices to transmit information, and the master device will not save any information except the name of the other party's Bluetooth device, so as to avoid information leakage.
  • the trained neural network is pre-implanted into the close connection app to complete the construction of the codec, and the neural network model with the adjusted training parameters can be implanted in the close connection device app, so that the main device can execute this solution.
  • the function of this step is to decode the Bluetooth address state vector that satisfies the condition and restore it to the original semantics.
  • the creation process of the encoding and decoding model in this step includes: acquiring historical contact data, which includes user name, personal contact risk factor, personal health status and/or activity area; converting the historical contact data into preset sentences
  • the defined state vector, the state vector is used as an input set; the input set is converted into an n ⁇ 1-dimensional vector as a test set; a neural network is trained based on the input set and the test set, and an encoding and decoding model is generated.
  • the encoder-decoder model can choose the Attention model.
  • the model When the model generates output, it also generates an "attention range" to indicate which parts of the input sequence to focus on when outputting next, and then generate the next output according to the area of interest, and so on.
  • the Attention model does not require the encoder to encode all input information into a fixed-length vector. Instead, the encoder needs to encode the input into a sequence of vectors, and during decoding, each step selectively picks a subset of the vector sequence for further processing. The partition utilizes the information carried by the input sequence.
  • the seq2seq model can be selected as the encoding and decoding model, and only the input state vector needs to be encoded, and then decoded into the same state vector to complete the transmission, and the data details and size expressed by the state vector are all in advance. Processing is confirmed and simpler compared to other codecs.
  • the encoded data input by the Encoder is all kinds of raw data that have not yet been processed, mainly including various states of the current mobile phone, personal information of the user, and some dynamic information related to the app game.
  • the amount of information required for transmission needs to be determined in advance.
  • the personal information of the close contact user includes: contact time, Bluetooth device name strength, date, location, user status estimation; name, personal contact risk factor, and personal health status.
  • the codec model is installed in the close contact device APP, and the corresponding information corresponding to the close contact device APP can also be obtained, such as screen brightness, mobile phone motion acceleration, mobile phone angle, remaining power, whether to connect to Wifi/4G, The time when the app is activated.
  • the filtered raw data information, the relevant state vector is defined in a simplified sentence in the form of numbers, and the raw data corresponding to each digit is determined. Take it as the input set.
  • the filtered raw data information, the relevant state vector is defined in a simplified sentence in the form of numbers, and the raw data corresponding to each digit is determined. Take it as the input set.
  • X represents the compression semantic unit
  • T represents different data information
  • the state of the last time step of the Encoder is used as the intermediate semantic vector of the whole sentence (context vector).
  • the valid bluetooth name is a string with a maximum of 248 bytes encoded in UTF-8, so we try to compress the data in 124 bits to ensure that the valid bluetooth name is as much as possible
  • the saved feature information can be accurately decoded and restored to the original data.
  • RNN neural network model
  • the output set is restored to the result set and compared with the training variables, and the mean square error function (MSE) is used for evaluation.
  • MSE mean square error function
  • ⁇ is the parameter set of the model
  • each (x_n, y_n) corresponds to the training set and the output set
  • gradient descent can be used to solve the model.
  • Keras is used to build a neural network model, and the trained model is exported.
  • the model.save_weights("name") function can save the parameters and thresholds of the model.
  • the model.load_weights("name") function is used to import the entire model. When the Encoder-Decoder model is completely modified, the entire encoding can be saved. decoding model.
  • tensorflow Since the close-connected app is planned to be produced using Android Studio (using the java language), tensorflow also provides a mature deployment solution, TensorFlow Serving. To call the model in this way, it is necessary to convert the model exported by Keras into the model of the protobuf protocol of tensorflow. Use model.save(model.h5) in Keras to save the current model as a file in HDF5 format.
  • the back-end framework of Keras uses tensorflow, so first export the model as a pb model. In Java, only the model needs to be called for prediction, so all the variables in the current graph are changed into constants, and the weights after training are used.
  • the master device scans the updated slave device and obtains the bluetooth name, and uses the decoder code that has been defined in the close connection app to restore the encoded information to the original data and update various types of close connections of the master device user. data, complete the transmission of the entire information.
  • step S101 further includes:
  • the distance judgment can be as follows: the master device transmits a signal containing the specified information, and then the mobile device receives the signal, so as to realize near-field communication, which calculates the signal strength (rssi) transmitted by the Bluetooth beacon and the transceiver device.
  • the distance between the receiver and the receiving device can be reversed through the value of rssi, and the distance between the receiving device can be measured by reasonable calculation conversion in various countries.
  • the method can avoid the problems that the existing method of distinguishing distance according to the Bluetooth strength is greatly interfered by the environment and is easily interfered by various factors such as the human body, the wall and the emission direction, and improves the accuracy of the Bluetooth distance measurement.
  • the contact information by encoding the contact information into the name of the Bluetooth device, it is not necessary to connect the Bluetooth to obtain the contact device, but only need to scan the name.
  • the information is encoded into a number and then attached to the Bluetooth name, so that the mobile phone can be directly connected to the mobile phone without establishing a connection.
  • the mobile phone device in this embodiment can also perform a write operation on the name of the close contact device after scanning the surrounding close contact devices each time, and at the same time, after each time the close contact device sends the Bluetooth device name, it is modified and updated to realize the close contact information. change in time. As shown in Figure 3, it includes the following steps:
  • S201 Scan and obtain the Bluetooth device names of one or more close contact devices
  • the master device accesses the device name attribute under the service after connecting to the slave device, and then writes a new name through this attribute, and the slave device determines whether the write sent from the mobile phone is for the device name under the Generic Access service property write operation. If so, save the name to FLASH and update the slave device name.
  • the master device can scan again to see the new device name, and a label can be added to the address suffix to indicate that this address needs to be recorded.
  • step S201 it further includes:
  • a database table for storing and retrieving the Bluetooth address in the contact app of the master device.
  • the master device searches the surrounding devices every 30s, and the slave device simultaneously detects the surrounding devices every 30s, and does Modification of the number of retrievals to the database. If the same device is retrieved for more than 5 minutes in a row, both the master device and the slave device will re-encode the current data information, update the semantic vector, and update the updated semantic vector to the Bluetooth address. Since the instantaneous state of the mobile phone is constantly updated, others have obtained the state vector and tried to decode it. Since the information is constantly updated, the values in it are difficult to interpret correctly.
  • the method of this embodiment can realize the timely change of the contact information, reduce the possibility of the data information being cracked, and improve the security of the device.
  • the surrounding close contact devices may be scanned every preset time interval.
  • the device is a slave device, as shown in Figure 5, perform the following steps:
  • a new state vector is formed by dynamically encoding the close data data.
  • the device saves the close connection information in the flash, and reads the name from the flash.
  • the Nordic protocol stack will have a Generic Access service by default.
  • the service is a general attribute specification service, which provides a way for devices to determine information (including name changes of their own devices) that the phone accesses the service and saves the new name to flash. Save the address and length of the name stored in the flash, take it out from user_config.h, and put it in USER_DEVICE_NAME and USER_DEVICE_NAME_LEN.
  • This step is about to update the native Bluetooth name to broadcast.
  • the preset time interval is 30 seconds.
  • step S303 it further includes:
  • the present embodiment provides a device 4 for obtaining close contact personnel information, including the following modules:
  • an acquisition module 401 configured to scan and acquire the Bluetooth device names of one or more close contact devices within a preset distance
  • the decoding module 402 is configured to decode the Bluetooth device name using a preset codec model.
  • the creation process of the encoding and decoding model further includes: obtaining historical close contact data, the historical close contact data includes user name, personal contact risk factor, personal health status and/or activity area; converting the historical contact data into pre-defined contact data Assuming the state vector defined by the sentence, the state vector is used as an input set; the input set is converted into an n ⁇ 1-dimensional vector as a test set; a neural network is trained based on the input set and the test set, and an encoding and decoding model is generated.
  • the close contact information generation module 403 is configured to use the decoded Bluetooth device name as the close contact information of the close contact device.
  • a write operation module 404 configured to generate a write operation signal based on the decoded Bluetooth device name
  • the sending module 405 is configured to send the write operation signal to the device, so that the device modifies the Bluetooth device name based on the write operation signal.
  • the search module 407 is used to judge whether the bluetooth device name already exists in the preset database; if so, increase the number of searches for the bluetooth device name in the database by 1; if not, store the bluetooth device name in the database, and count the number of searches as 1.
  • the encoding module 408 is configured to encode the contact information using a preset codec model; use the encoded contact information as a Bluetooth device name; and send the Bluetooth device name every preset time interval.
  • the device name update module 409 is used to encode the Bluetooth device name based on the updated contact information using the preset codec model after sending the Bluetooth device name every preset time interval; the encoded contact information is used as the updated Bluetooth device. name.
  • the apparatus for obtaining the contact person information provided by the embodiment of the present invention can execute the method for obtaining the contact person information provided by any embodiment of the present invention, and has the corresponding execution method and beneficial effects of the functional modules.
  • the server includes a processor 501, a memory 502, an input device 503, and an output device 504; the number of processors 501 in the server may be one or more,
  • a processor 501 is taken as an example; the processor 501, memory 502, input device 503 and output device 504 in the device/terminal/server can be linked by a bus or in other ways.
  • the memory 502 can be used to store software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the method for obtaining contact information in the embodiment of the present invention.
  • the processor 501 executes various functional applications and data processing of the device/terminal/server by running the software programs, instructions and modules stored in the memory 502, that is, the above-mentioned method for obtaining the contact person information.
  • the memory 502 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal, and the like. Additionally, memory 502 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid-state storage device. In some instances, memory 502 may further include memory located remotely relative to processor 501, and these remote memories may be linked to the device/terminal/server through a network. Examples of such networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
  • the input device 503 can be used to receive input numerical or character information, and generate key signal input related to user setting and function control of the device/terminal/server.
  • the output device 504 may include a display device such as a display screen.
  • the fifth embodiment of the present invention provides a server that can execute the method for obtaining close contact personnel information provided by any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.
  • the sixth embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by the processor, the method for obtaining the information of the contact person provided by any embodiment of the present invention is realized:
  • the decoded Bluetooth device name is used as the close contact information of the close contact device.
  • the computer-readable storage medium of the embodiments of the present invention may adopt any combination of one or more computer-readable mediums.
  • the computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium.
  • the computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor device, apparatus or device, or a combination of any of the above.
  • a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution apparatus, apparatus, or device.
  • a computer-readable signal medium may include a propagated data signal in baseband or as part of a carrier wave, with computer-readable program code embodied thereon. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing.
  • a computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport the program for use by or in connection with the instruction execution apparatus, apparatus, or device .
  • Program code embodied on a storage medium may be transmitted using any suitable medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
  • Computer program code for carrying out operations of the present invention may be written in one or more programming languages, including object-oriented programming languages—such as Java, Smalltalk, C++, but also conventional procedural languages, or a combination thereof.
  • a programming language such as the "C" language or similar programming language.
  • the program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or terminal.
  • the remote computer may be linked to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or may be linked to an external computer (eg, using an Internet service provider through Internet link).
  • LAN local area network
  • WAN wide area network

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Computer Security & Cryptography (AREA)
  • Mobile Radio Communication Systems (AREA)
  • Telephone Function (AREA)

Abstract

本发明提供一种获取密接人员信息方法,由具有蓝牙设备名称扫描功能的设备执行，包括：扫描并获取一个或多个密接设备的蓝牙设备名称；将所述蓝牙设备名称使用预设的编解码模型进行解码；将解码后的所述蓝牙设备名称作为所述密接设备的密接信息。本发明通过将密接信息编码为蓝牙设备名称，使获取密接设备不需要连接蓝牙，只需要扫描名称即可，采用将信息编码成数字后附加在蓝牙名称上，从而可以不建立连接直接进行手机设备间有用信息的交换和获取。由于计算机网络中协议安全很难保障，蓝牙连接传输数据被盗取的安全隐患较大。采用不建立连接的方式，而仅仅识别并保存名称，可以直接规避协议窃取的问题提高了设备安全性。

Description

获取密接人员信息方法、装置、服务器和存储介质 技术领域
本发明实施例涉及通信领域，尤其涉及一种获取密接人员信息方法、装置、服务器和存储介质。
 背景技术
现有的新冠肺炎防疫政策中，通常需要获取与确诊、疑似病例相密接的密接人员的信息，通常采用的方法是根据确诊、疑似病例的线下行动轨迹，通过调查摄像头等影像进行人员流动调查，比较好费人力物力。
一些厂家通过蓝牙连接移动端的信息查询人员信息。一个蓝牙网装置所广播的信息确实可能被一个潜在的恶意手机只能程序利用，从而导致意外的位置隐私侵犯，更有甚者可以访将不可见的蓝牙设备作为目标，渗透用户设备，导致侵入用户设备的数据载体并窃取信息。
由于计算机网络中协议安全很难保障，蓝牙连接传输数据被盗取的安全隐患较大，可能会导致获取到被调查设备除了疫情防控以外的私人信息，造成信息泄露。
 技术问题
本发明提供一种获取密接人员信息的方法，通过获取编码后的蓝牙设备名称即可得知设备密接信息，不需要与陌生设备进行蓝牙配对，避免了用户隐私泄露。
 技术解决方案
第一方面，本发明提供一种获取密接人员信息的方法，由具有蓝牙设备名称扫描功能的设备执行，包括：
在预设距离内，扫描并获取一个或多个密接设备的蓝牙设备名称；
将所述蓝牙设备名称使用预设的编解码模型进行解码；
将解码后的所述蓝牙设备名称作为所述密接设备的密接信息。
进一步地，所述将解码后的所述蓝牙设备名称作为所述设备的密接信息之后，还包括：
基于解码后的蓝牙设备名称生成写操作信号；
将所述写操作信号发送至所述设备，以使所述设备基于所述写操作信号修改所述蓝牙设备名称。
进一步地，所述编解码模型的创建过程还包括：
获取历史密接数据，所述历史密接数据包括用户姓名、个人密接风险系数、个人健康状态和/或活动地区；
将所述历史密接数据转换为预设语句定义的状态向量，将所述状态向量作为输入集；
将所述输入集转换为n×1维向量作为测试集；
基于所述输入集和测试集进行神经网络训练，生成编解码模型。
进一步地，在所述在预设距离内，获取一个或多个设备的蓝牙设备名称之前，还包括：
基于所述蓝牙设备名称确定与一个或多个设备的距离；
判断所述距离是否小于或等于预设距离；
若小于或等于，则获取所述设备的蓝牙设备名称；
若大于，则不获取所述设备的蓝牙设备名称。
进一步地，在所述在预设距离内，获取一个或多个设备的蓝牙设备名称，所述蓝牙设备名称中包括蓝牙设备名称之后，还包括：
判断预设的数据库中是否已经存有所述蓝牙设备名称；
若有，则将数据库中蓝牙设备名称的搜索次数增加1；
若没有，则将所述蓝牙设备名称存入数据库，并将搜索次数记为1。
进一步地，还包括：
将密接信息使用预设的编解码模型进行编码；
将编码后的密接信息作为蓝牙设备名称；
每隔预设时间间隔发送一次蓝牙设备名称。
进一步地，在所述每隔预设时间间隔发送一次蓝牙设备名称之后，还包括：
基于更新后的密接信息使用预设的编解码模型进行编码；
将编码后的密接信息作为更新后的蓝牙设备名称。
第二方面，本发明提供一种获取密接人员信息的装置，包括：
获取模块，用于在预设距离内，扫描并获取一个或多个密接设备的蓝牙设备名称；
解码模块，用于将所述蓝牙设备名称使用预设的编解码模型进行解码；
密接信息生成模块，用于将解码后的所述蓝牙设备名称作为所述密接设备的密接信息。
第三方面本发明提供一种服务器，包括存储器、处理器及存储在存储器上并可在处理器上运行的程序，所述处理器执行所述程序时实现如上述任一所述的获取密接人员信息方法。
第四方面本发明提供一种终端可读存储介质，其上存储有程序，所述程序被处理器执行时能够实现如上述任一所述的获取密接人员信息方法。
 有益效果
本发明通过获取编码后的蓝牙设备名称即可得知设备密接信息，不需要与陌生设备进行配对，避免了用户隐私泄露。同时通过使用预先训练的编解码模型进行解码，模型参数全部由训练得到，对外保持封闭，即实现了信息安全。
 附图说明
如图1所示为本实施例一的获取密接人员信息方法流程图。
如图2所示为本实施例一的替代实施例流程图。
如图3所示为本实施例二的获取密接人员信息方法流程图。
如图4所示为本实施例二的替代实施例流程图。
如图5所示为本实施例三的获取密接人员信息方法流程图。
如图6所示为本实施例三的替代实施例流程图。
如图7所示为本实施例四的获取密接人员信息装置模块图。
如图8所示为本实施例四的替代实施例模块图。
如图9所示本实施例五的服务器结构图。
 本发明的实施方式
下面结合附图和实施例对本发明作进一步的详细说明。可以理解的是，此处所描述的具体实施例仅仅用于解释本发明，而非对本发明的限定。另外还需要说明的是，为了便于描述，附图中仅示出了与本发明相关的部分而非全部结构。
在更加详细地讨论示例性实施例之前应当提到的是，一些示例性实施例被描述成作为流程图描绘的处理或方法。虽然流程图将各步骤描述成顺序的处理，但是其中的许多步骤可以被并行地、并发地或者同时实施。此外，各步骤的顺序可以被重新安排。当其操作完成时处理可以被终止，但是还可以具有未包括在附图中的附加步骤。处理可以对应于方法、函数、规程、子例程、子程序等等。
此外，术语“第一”、“第二”等可在本文中用于描述各种方向、动作、步骤或元件等，但这些方向、动作、步骤或元件不受这些术语限制。这些术语仅用于将第一个方向、动作、步骤或元件与另一个方向、动作、步骤或元件区分。举例来说，在不脱离本申请的范围的情况下，第一特征信息可以为第二特征信息或第三特征信息，类似地，第二特征信息、第三特征信息可以为第一特征信息。第一特征信息和第二特征信息、第三特征信息都是获取密接人员信息装置的特征信息，但其不是同一特征信息。术语“第一”、“第二”等而不能理解为指示或暗示相对重要性或者隐含指明所指示的技术特征的数量。由此，限定有“第一”、“第二”的特征可以明示或者隐含地包括一个或者更多个该特征。在本发明的描述中，“多个”、“批量”的含义是至少两个，例如两个，三个等，除非另有明确具体的限定。
本实施例及下述实施例中提及的英文缩写及专有名词含义如下：
seq2seq：是指根据一个输入序列x，来生成另一个输出序列y。seq2seq有很多的应用，例如翻译，文档摘取，问答系统等等。编解码模型首先输入输入集，通过神经网络训练的编码器将其转换为一段规定好长度的语义向量C，再通过神经网络训练的解码器将该语义向量转化为所需的输出集。
实施例一
本实施例提供了一种获取密接人员信息的方法，由具有蓝牙设备名称扫描功能的设备执行，该设备安装有用于执行方案的密接APP。如图1，包括：
S101、扫描并获取一个或多个密接设备的蓝牙设备名称；
该步骤及下述步骤所述设备通过蓝牙扫描距离内的一个或多个其他密接设备。其中，密接设备指与具有蓝牙设备名称扫描功能的设备的距离小于一定值的设备。蓝牙设备名称指蓝牙地址。该过程中，将具有蓝牙设备名称扫描功能的设备作为主设备，其他密接设备作为从设备进行描述。在扫描中，从设备以设定的频率广播自己的蓝牙设备名称，主设备基于扫描到的广播信息获取从设备的蓝牙设备名称。该过程设备之间不会建立协议传输信息，主设备不保存除对方蓝牙设备名称外的任何信息，以避免了信息泄露。
S102、将所述蓝牙设备名称使用预设的编解码模型进行解码。
该步骤中，训练好的神经网络预先植入到密接app中，完成编解码器的搭建，调整好训练参数的神经网络模型可植入密接设备的app中，以使主设备能够执行本方案。该步骤的作用是解码满足条件的蓝牙地址状态向量，还原成原语意。
该步骤中编解码模型的创建过程包括：获取历史密接数据，所述历史密接数据包括用户姓名、个人密接风险系数、个人健康状态和/或活动地区；将所述历史密接数据转换为预设语句定义的状态向量，将所述状态向量作为输入集；将所述输入集转换为n×1维向量作为测试集；基于所述输入集和测试集进行神经网络训练，生成编解码模型。
在一种实施方式中，编解码模型可以选择Attention注意力模型。该模型在产生输出的时候，还会产生一个“注意力范围”表示接下来输出的时候要重点关注输入序列中的哪些部分，然后根据关注的区域来产生下一个输出，如此往复。Attention模型不要求编码器将所有输入信息都编码进一个固定长度的向量之中。相反，此时编码器需要将输入编码成一个向量的序列，而在解码的时候，每一步都会选择性的从向量序列中挑选一个子集进行进一步处理。分利用输入序列携带的信息。
在另一种实施方式中，编解码模型可以选用seq2seq模型，只需要将输入的状态向量编码，再解码成同样的状态向量完成传输即可，且状态向量的表达的数据细节和大小都在预处理中得到确认，相比于其他编解码器方式更简单。
具体地，该方案的模型建构过程如下：
1、选取需要编解码的信息作为整个输入序列，将其编码为一种上下文向量的状态向量。
a、密接信息选择
Encoder输入编码的数据为尚未处理的各类原始数据，主要有当前手机的各类状态，密接用户的个人信息，和一些与密接app游戏相关的动态信息。需要提前确定好传输所需要的信息量。例如，密接用户个人信息包括：接触时间、蓝牙设备名称强度、日期、地点、用户状态推测；姓名、个人密接风险系数、个人健康状态。在一种示例中，该编解码模型安装于密接设备APP中，对应的还可获取密接设备APP所对应的信息，如屏幕亮度、手机运动加速度、手机转角、剩余电量、是否连接Wifi/4G、密接app启用时间。
筛选好的原始数据信息，以数字的形式精简的语句定义相关的状态向量，确定每位数字所对应的原始数据。将其作为输入集。
b.状态向量定义
筛选好的原始数据信息，以数字的形式精简的语句定义相关的状态向量，确定每位数字所对应的原始数据。将其作为输入集。
c.生成训练变量
根据神经网络需要的传入训练变量集，首先随机生成测试集，将其整合成n×1维向量：
Figure dest_path_image001
其中X表示压缩语义单元，T表示不同的数据信息。
至此完成了Encoder模型前的输入训练变量的处理。
2、读取该状态向量为输入序列，在解码器中生成输出序列，完成Seq2Seq。
将Encoder最后一个时间步的状态作为整个句子的中间语义向量(context vector)。
a、语义向量长度确定
由于我们将使用语义向量C作为蓝牙名称，有效蓝牙名称是使用UTF-8编码最大的248个字节的字符串，故我们尽可能将数据压缩在124位内，保证在有效的蓝牙名称内尽量保存特征信息能够准确解码还原成原始数据。
3、选取适当的神经网络模型（RNN或LSTM）训练编解码器，并通过计算实际输入和重构输入之间的差异评估损失函数。
4、使用大量的训练集，测试集训练神经网络，优化编解码器神经网络参数。
将输出集还原回成的结果集与训练变量进行对比，使用均方差函数(MSE)进行评估。评估目标是最大化如下概率
Figure dest_path_image002
这里的θ就是模型的参数集合，每一个(x_n,y_n)对应训练集和输出集，模型求解可以使用梯度下降。
对于一些精度要求不大的参数，比如地理位置数据的末5位，如果损失函数效果过大/直接比对两文本差错信息过多，则考虑使用Attention模型或不同神经网络层来训练Encoder-Decoder模型（即编解码模型）。
该步骤中，当编解码模型植入密集APP并安装至主设备和从设备中。
在一种实施例中，使用Keras来搭建神经网络模型，并且把训练好的模型导出。model.save_weights("name")函数，可以将模型的参数和阈值保存下来，model.load_weights("name")函数用于将整个模型导入，当Encoder-Decoder模型完全修改好后，可以保存整个编解码模型。
由于密接app计划使用Android Studio制作(使用java语言)，tensorflow也提供了成熟的部署方案TensorFlow Serving，采用这种方式调用模型需要先将Keras导出的模型转成tensorflow的protobuf协议的模型。在Keras中使用model.save(model.h5)保存当前模型为HDF5格式的文件中。Keras的后端框架使用的是tensorflow，所以先把模型导出为pb模型。在Java中只需要调用模型进行预测，所以将当前的graph中的变量全部变成常数，并且使用训练后的权重。
S103、将解码后的所述蓝牙设备名称作为所述密接设备的密接信息。
在该步骤中，主设备扫描到已经更新的从设备并且将获取蓝牙名称，并使用密接app中已经定义好的decoder编码，将编码后的信息还原成原始数据并更新主设备用户的各类密接数据，完成整个信息的传输。
如图2，在替代实施例中，步骤S101还包括：
S1011、基于所述蓝牙设备名称确定与一个或多个设备的距离；
该步骤中，距离判断可以是：由主设备发射包含指定信息的信号，再由移动设备接收信号，从而实现近场通信，它通过计算蓝牙信标发射的信号强度(rssi)与收发设备之间的距离，同各国合理的运算转换，可以通过rssi的值反推出与接收设备间的距离，实现距离测量。
该方法可以避免现有根据蓝牙强度辨别距离的方法受环境干扰较大，容易受到人体，墙体以及发射方向等各种因素所干扰的问题，提高了蓝牙测距的准确度。
S1012、判断所述距离是否小于或等于预设距离；
S1013、若小于或等于，则获取所述设备的蓝牙设备名称；
S1014、若大于，则不获取所述设备的蓝牙设备名称。
本实施例通过将密接信息编码为蓝牙设备名称，使获取密接设备不需要连接蓝牙，只需要扫描名称即可，采用将信息编码成数字后附加在蓝牙名称上，从而可以不建立连接直接进行手机设备间有用信息的交换和获取。由于计算机网络中协议安全很难保障，蓝牙连接传输数据被盗取的安全隐患较大。采用不建立连接的方式，而仅仅识别并保存名称，可以直接规避协议窃取的问题提高了设备安全性。
实施例二
本实施例中的手机设备在每次扫描到周围密接设备之后，还可以执行对密接设备名称的写操作，同时密接设备每次发送一次蓝牙设备名称之后，都进行修改更新，以实现密接信息的及时变化。如图3，包括如下步骤：
S201、扫描并获取一个或多个密接设备的蓝牙设备名称；
S202、将所述蓝牙设备名称使用预设的编解码模型进行解码；
S203、将解码后的所述蓝牙设备名称作为所述密接设备的密接信息。
S204、基于解码后的蓝牙设备名称生成写操作信号；
S205、将所述写操作信号发送至所述设备，以使所述设备基于所述写操作信号修改所述蓝牙设备名称。
该步骤S204-S205中，主设备连接上从设备后访问这个服务下的设备名属性，然后通过这个属性写新的名字，从设备判断手机发送过来的写是不是对Generic Access服务下的设备名属性的写操作。如果是就保存名字到FLASH中，更新从设备名。当从设备断开连接后，主设备再扫描就能看到新的设备名字了，可以将地址后缀增加一个标签来表明此地址是需要被记录的。
在替代实施例中，如图4，步骤S201之后还包括：
S2061、判断预设的数据库中是否已经存有所述蓝牙设备名称；
S2062、若有，则将数据库中蓝牙设备名称的搜索次数增加1；
S2063、若没有，则将所述蓝牙设备名称存入数据库，并将搜索次数记为1。
该步骤中，在主设备的密接app中定义一个保存检索蓝牙地址的数据库表，例如，主设备每隔30s检索一次周围的设备，从设备同时做到每个30s检测一次周围的设备，并做到数据库中检索次数的修改。如果连续超过5min检索到同一设备，则主设备和从设备都会重新将当前的数据信息进行encoder编码，并且把语义向量更新，把更新后的语义向量更新至蓝牙地址。由于手机瞬时状态是不断更新的，他人即是获取了状态向量并且尝试解码，由于信息不断更新，其中的数值很难正确解读。
本实施例的方法能够实现密接信息的及时变化，使数据信息被破解的可能性降低，提高设备安全性。
实施例三
替代实施例中，上述步骤为设备作为主设备的时候，可以每隔预设时间间隔扫描一次周围的密接设备。当设备为从设备时，如图5，执行下述步骤：
S301、将密接信息使用预设的编解码模型进行编码；
该步骤通过动态将密接数据数据编码形成新的状态向量，具体：设备端将密接信息保存在flash中，并从flash中读取名称，具体地，Nordic的协议栈中默认会有一个Generic Access服务，该服务为通用属性规范服务，为设备提供了一种确定信息的方式（包含自身设备的名称更改）手机访问该服务并且保存新的名称到flash中。保存存放在flash中名称的地址和长度，从user_config.h里取出，放到USER_DEVICE_NAME 和 USER_DEVICE_NAME_LEN。
S302、将编码后的密接信息作为蓝牙设备名称；
S303、每隔预设时间间隔发送一次蓝牙设备名称。
该步骤即将的更新本机蓝牙名称进行广播。例如，预设时间间隔为30秒。
在蓝牙调用gapm_start_advertise_cmd之前从flash中读取更新名称，并更新到NVDS_TAG_DEVICE_NAME里，重新更新广播内容。
在替代实施例中，如图6，步骤S303之后还包括：
S304、基于更新后的密接信息使用预设的编解码模型进行编码；
S305、将编码后的密接信息作为更新后的蓝牙设备名称。
通过周期性更新密接信息，作为更新后的蓝牙设备名称，实现了密接信息的及时更新。
实施例四
如图7，本实施例提供了一种获取密接人员信息装置4，包括如下模块：
获取模块401，用于在预设距离内，扫描并获取一个或多个密接设备的蓝牙设备名称；
解码模块402，用于将所述蓝牙设备名称使用预设的编解码模型进行解码。其中，所述编解码模型的创建过程还包括：获取历史密接数据，所述历史密接数据包括用户姓名、个人密接风险系数、个人健康状态和/或活动地区；将所述历史密接数据转换为预设语句定义的状态向量，将所述状态向量作为输入集；将所述输入集转换为n×1维向量作为测试集；基于所述输入集和测试集进行神经网络训练，生成编解码模型。
密接信息生成模块403，用于将解码后的所述蓝牙设备名称作为所述密接设备的密接信息。
在替代实施例中，如图8，还包括：
写操作模块404，用于基于解码后的蓝牙设备名称生成写操作信号；
发送模块405，用于将所述写操作信号发送至所述设备，以使所述设备基于所述写操作信号修改所述蓝牙设备名称。
还包括距离判断模块406，用于基于所述蓝牙设备名称确定与一个或多个设备的距离；判断所述距离是否小于或等于预设距离；若小于或等于，则获取所述设备的蓝牙设备名称；若大于，则不获取所述设备的蓝牙设备名称。
还包括：
搜索模块407，用于判断预设的数据库中是否已经存有所述蓝牙设备名称；若有，则将数据库中蓝牙设备名称的搜索次数增加1；若没有，则将所述蓝牙设备名称存入数据库，并将搜索次数记为1。
还包括：
编码模块408，用于将密接信息使用预设的编解码模型进行编码；将编码后的密接信息作为蓝牙设备名称；每隔预设时间间隔发送一次蓝牙设备名称。
设备名更新模块409，用于每隔预设时间间隔发送一次蓝牙设备名称之后，在基于更新后的密接信息使用预设的编解码模型进行编码；将编码后的密接信息作为更新后的蓝牙设备名称。
本发明实施例所提供的一种获取密接人员信息装置可执行本发明任意实施例所提供的获取密接人员信息方法，具备功能模块相应的执行方法和有益效果。
实施例五
本实施例提供了一种服务器的结构示意图，如图9所示，该服务器包括处理器501、存储器502、输入装置503和输出装置504；服务器中处理器501的数量可以是一个或多个，图中以一个处理器501为例；设备/终端/服务器中的处理器501、存储器502、输入装置503和输出装置504可以通过总线或其他方式链接，图9中以通过总线链接为例。
存储器502作为一种计算机可读存储介质，可用于存储软件程序、计算机可执行程序以及模块，如本发明实施例中的获取密接人员信息方法对应的程序指令/模块。处理器501通过运行存储在存储器502中的软件程序、指令以及模块，从而执行设备/终端/服务器的各种功能应用以及数据处理，即实现上述的获取密接人员信息方法。
存储器502可主要包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需的应用程序；存储数据区可存储根据终端的使用所创建的数据等。此外，存储器502可以包括高速随机存取存储器，还可以包括非易失性存储器，例如至少一个磁盘存储器件、闪存器件、或其他非易失性固态存储器件。在一些实例中，存储器502可进一步包括相对于处理器501远程设置的存储器，这些远程存储器可以通过网络链接至设备/终端/服务器。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通信网及其组合。
输入装置503可用于接收输入的数字或字符信息，以及产生与设备/终端/服务器的用户设置以及功能控制有关的键信号输入。输出装置504可包括显示屏等显示设备。
本发明实施例五通过提供一种服务器，可执行本发明任意实施例所提供的获取密接人员信息方法，具备执行方法相应的功能模块和有益效果。
实施例六
本发明实施例六还提供了一种计算机可读存储介质，其上存储有计算机程序，该程序被处理器执行时实现如本发明任意实施例所提供的获取密接人员信息方法：
扫描并获取一个或多个密接设备的蓝牙设备名称；
将所述蓝牙设备名称使用预设的编解码模型进行解码；
将解码后的所述蓝牙设备名称作为所述密接设备的密接信息。
本发明实施例的计算机可读存储介质，可以采用一个或多个计算机可读的介质的任意组合。计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质。计算机可读存储介质例如可以是但不限于电、磁、光、电磁、红外线、或半导体的装置、装置或器件，或者任意以上的组合。计算机可读存储介质的更具体的例子（非穷举的列表）包括：具有一个或多个导线的电链接、便携式计算机磁盘、硬盘、随机存取存储器（RAM）、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本文件中，计算机可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行装置、装置或者器件使用或者与其结合使用。
计算机可读的信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读的信号介质还可以是计算机可读存储介质以外的任何计算机可读介质，该计算机可读介质可以发送、传播或者传输用于由指令执行装置、装置或者器件使用或者与其结合使用的程序。
存储介质上包含的程序代码可以用任何适当的介质传输，包括但不限于无线、电线、光缆、RF等等，或者上述的任意合适的组合。
可以以一种或多种程序设计语言或其组合来编写用于执行本发明操作的计算机程序代码，程序设计语言包括面向对象的程序设计语言—诸如Java、Smalltalk、C++，还包括常规的过程式程序设计语言诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或终端上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络——包括局域网(LAN)或广域网(WAN)—链接到用户计算机，或者，可以链接到外部计算机（例如利用因特网服务提供商来通过因特网链接）。
注意，上述仅为本发明的较佳实施例及所运用技术原理。本领域技术人员会理解，本发明不限于这里所述的特定实施例，对本领域技术人员来说能够进行各种明显的变化、重新调整和替代而不会脱离本发明的保护范围。因此，虽然通过以上实施例对本发明进行了较为详细的说明，但是本发明不仅仅限于以上实施例，在不脱离本发明构思的情况下，还可以包括更多其他等效实施例，而本发明的范围由所附的权利要求范围决定。

Claims (10)

  1. 一种获取密接人员信息的方法，由具有蓝牙设备名称扫描功能的设备执行，其特征在于，包括：
    扫描并获取一个或多个密接设备的蓝牙设备名称；
    将所述蓝牙设备名称使用预设的编解码模型进行解码；
    将解码后的所述蓝牙设备名称作为所述密接设备的密接信息。
  2. 根据权利要求1的方法，其特征在于，所述将解码后的所述蓝牙设备名称作为所述密接设备的密接信息之后，还包括：
    基于解码后的蓝牙设备名称生成写操作信号；
    将所述写操作信号发送至所述设备，以使所述设备基于所述写操作信号修改所述蓝牙设备名称。
  3. 根据权利要求1的方法，其特征在于，所述编解码模型的创建过程还包括：
    获取历史密接数据，所述历史密接数据包括用户姓名、个人密接风险系数、个人健康状态和/或活动地区；
    将所述历史密接数据转换为预设语句定义的状态向量，将所述状态向量作为输入集；
    将所述输入集转换为n×1维向量作为测试集；
    基于所述输入集和测试集进行神经网络训练，生成编解码模型。
  4. 根据权利要求1的方法，其特征在于，所述在预设距离内，获取一个或多个与所述设备密接的密接设备的蓝牙设备名称，还包括：
    基于所述蓝牙设备名称确定与一个或多个设备的距离；
    判断所述距离是否小于或等于预设距离；
    若小于或等于，则获取所述设备的蓝牙设备名称；
    若大于，则不获取所述设备的蓝牙设备名称。
  5. 根据权利要求1的方法，其特征在于，扫描并获取一个或多个密接设备的蓝牙设备名称之后，还包括：
    判断预设的数据库中是否已经存有所述蓝牙设备名称；
    若有，则将数据库中蓝牙设备名称的搜索次数增加1；
    若没有，则将所述蓝牙设备名称存入数据库，并将搜索次数记为1。
  6. 根据权利要求1的方法，其特征在于，还包括：
    将密接信息使用预设的编解码模型进行编码；
    将编码后的密接信息作为蓝牙设备名称；
    每隔预设时间间隔发送一次蓝牙设备名称。
  7. 根据权利要求6的方法，其特征在于，在所述每隔预设时间间隔发送一次蓝牙设备名称之后，还包括：
    基于更新后的密接信息使用预设的编解码模型进行编码；
    将编码后的密接信息作为更新后的蓝牙设备名称。
  8. 一种获取密接人员信息的装置，其特征在于，包括：
    获取模块，用于在预设距离内，扫描并获取一个或多个密接设备的蓝牙设备名称；
    解码模块，用于将所述蓝牙设备名称使用预设的编解码模型进行解码；
    密接信息生成模块，用于将解码后的所述蓝牙设备名称作为所述密接设备的密接信息。
  9. 一种服务器，包括存储器、处理器及存储在存储器上并可在处理器上运行的程序，其特征在于，所述处理器执行所述程序时实现如权利要求1-7任一所述的获取密接人员信息方法。
  10. 一种终端可读存储介质，其上存储有程序，其特征在于，所述程序被处理器执行时能够实现如权利要求1-7任一所述的获取密接人员信息方法。
PCT/CN2021/118087 2021-01-20 2021-09-14 获取密接人员信息方法、装置、服务器和存储介质 WO2022156236A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110077477.XA CN112866991B (zh) 2021-01-20 2021-01-20 获取密接人员信息方法、装置、服务器和存储介质
CN202110077477.X 2021-01-20

Publications (1)

Publication Number Publication Date
WO2022156236A1 true WO2022156236A1 (zh) 2022-07-28

Family

ID=76008322

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/118087 WO2022156236A1 (zh) 2021-01-20 2021-09-14 获取密接人员信息方法、装置、服务器和存储介质

Country Status (2)

Country Link
CN (1) CN112866991B (zh)
WO (1) WO2022156236A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112866991B (zh) * 2021-01-20 2023-07-11 南方科技大学 获取密接人员信息方法、装置、服务器和存储介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101394201A (zh) * 2008-11-12 2009-03-25 李海 一种蓝牙设备发送信息的快捷方法和系统
US20160269979A1 (en) * 2015-03-12 2016-09-15 650 Industries, Inc. Method and apparatus for fast communication of information during bluetooth discovery phase
CN111446006A (zh) * 2020-04-08 2020-07-24 陈恬慧 一种传染病疫情中密切接触者的追踪方法
CN112188405A (zh) * 2020-09-29 2021-01-05 武汉大学 一种基于智能手机的安全距离感知与追溯系统及方法
CN112203229A (zh) * 2020-09-25 2021-01-08 中国科学院计算技术研究所苏州智能计算产业技术研究院 基于蓝牙扫描的短距疫情传播网络构建方法
CN112866991A (zh) * 2021-01-20 2021-05-28 南方科技大学 获取密接人员信息方法、装置、服务器和存储介质

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8509756B2 (en) * 2010-08-25 2013-08-13 At&T Intellectual Property I, L.P. System and method for reporting loss of broadband connectivity
CA3238603A1 (en) * 2014-03-18 2015-09-18 Smartrek Technologies Inc. Mesh network system and techniques
CN111918215A (zh) * 2020-06-30 2020-11-10 王云峰 通过蓝牙对传染病密切接触者进行追踪的方法与系统

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101394201A (zh) * 2008-11-12 2009-03-25 李海 一种蓝牙设备发送信息的快捷方法和系统
US20160269979A1 (en) * 2015-03-12 2016-09-15 650 Industries, Inc. Method and apparatus for fast communication of information during bluetooth discovery phase
CN111446006A (zh) * 2020-04-08 2020-07-24 陈恬慧 一种传染病疫情中密切接触者的追踪方法
CN112203229A (zh) * 2020-09-25 2021-01-08 中国科学院计算技术研究所苏州智能计算产业技术研究院 基于蓝牙扫描的短距疫情传播网络构建方法
CN112188405A (zh) * 2020-09-29 2021-01-05 武汉大学 一种基于智能手机的安全距离感知与追溯系统及方法
CN112866991A (zh) * 2021-01-20 2021-05-28 南方科技大学 获取密接人员信息方法、装置、服务器和存储介质

Also Published As

Publication number Publication date
CN112866991B (zh) 2023-07-11
CN112866991A (zh) 2021-05-28

Similar Documents

Publication Publication Date Title
EP3020040B1 (en) Method and apparatus for assigning keyword model to voice operated function
CN101543011B (zh) 将多媒体内容和解码装置捆绑的方法
US20090187410A1 (en) System and method of providing speech processing in user interface
CN105682253A (zh) 建立通信的方法、设备、终端和计算机可读存储介质
KR20140045829A (ko) 사물 인터넷을 위한 인증 방법과 그를 위한 디바이스 및 인증 장치
KR20200073718A (ko) 전자 장치 및 이의 제어 방법
CN109495492A (zh) 用于智能水务行业的通信系统
US20240078385A1 (en) Method and apparatus for generating text
WO2022156236A1 (zh) 获取密接人员信息方法、装置、服务器和存储介质
CN113742463B (zh) 旅游场景下的对话预测方法、装置、电子设备、存储介质
CN103647763A (zh) 一种移动终端广告调用方法和系统
KR20130070947A (ko) 단말의 음성인식을 제어하는 서버 및 방법, 그리고 단말
CN112802485B (zh) 语音数据处理方法、装置、计算机设备及存储介质
KR20070013079A (ko) 객체 인식을 통한 원격감시 영상데이터의 송수신 방법 및그 시스템
CN201307915Y (zh) 无线数字音频视频传输设备及其发射端和接收端
CN113918246A (zh) 功能控制方法、功能控制装置、存储介质与电子设备
CN113342811A (zh) HBase表格数据处理方法及装置
JPWO2007046369A1 (ja) 情報処理装置
CN114422587A (zh) 数据处理方法、装置、计算机设备和存储介质
CN109302542A (zh) 基于gsm的远程监控方法、装置、设备及存储介质
CN113055713B (zh) 视频图像超分方法及装置、存储介质和电子设备
KR100860387B1 (ko) 지반 및 구조물 정보 제공 시스템 및 그를 이용한 정보제공 방법
Saleem et al. End-to-end security enabled intelligent remote IoT monitoring system
US20230123683A1 (en) Encoding / Decoding System and Method
Huynh et al. Jarvis: A voice-based context-as-a-service mobile tool for a smart home environment

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: 21920614

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21920614

Country of ref document: EP

Kind code of ref document: A1