WO2022142442A1

WO2022142442A1 - Intimate contact determining method and apparatus, electronic device, and medium

Info

Publication number: WO2022142442A1
Application number: PCT/CN2021/116604
Authority: WO
Inventors: 宋轩; 赵奕丞; 张浩然; 陈达寅; 颜秋阳; 江亦凡
Original assignee: 南方科技大学
Priority date: 2020-12-30
Filing date: 2021-09-06
Publication date: 2022-07-07
Also published as: CN112635077A

Abstract

An intimate contact determining method and apparatus, an electronic device, and a medium. The intimate contact determining method comprises: on the basis of the close contact technology, determining other acquisition values of other sensors in other devices located near a local device; using the other acquisition values, a local acquisition value and the signal intensity of the close contact technology as feature data in a training sample, wherein the training sample is associated with the local device and the other devices; and determining label data in the training sample, wherein the training sample is used for training an intimate contact determining model. Therefore, the accuracy of an intimate contact determining model in determining intimate contact between people is improved.

Description

A close contact judgment method, device, electronic device and medium

technical field

The invention relates to the technical field of artificial intelligence, and in particular, to a method, device, electronic device and medium for judging close contact.

Background technique

Close contact refers to the distance between a person and the relative physical location of other people within a certain time frame, which is less than the distance during normal contact. People who live, study or work together are more likely to be in close contact than strangers. Information about a person's close contacts is a good reflection of that person's network. Effectively obtaining a person's close contact information is of great significance for the prevention and traceability of infectious diseases and the study of interpersonal networks.

At present, most of the methods for judging whether there is close contact between people are based on a single Bluetooth technology. Due to the defect of unstable signal in the Bluetooth technology itself, these methods are often inaccurate in judging whether there is close contact between people.

technical problem

Embodiments of the present invention provide a method, device, electronic device and medium for judging close contact, so as to achieve the purpose of improving the accuracy of judging whether there is close contact between people.

technical solutions

In a first aspect, an embodiment of the present invention provides a method for judging close contact, including:

Determine other acquired values of other sensors in other devices located near the local device based on proximity technology;

Determine the local acquisition value of the local sensor in the local device;

Using the other collected values, the local collected values and the signal strength of the proximity technology as characteristic data in the training samples; wherein the training samples are associated with the local device and the other devices;

Determine the label data in the training sample; wherein, the training sample is used to train a close contact judgment model.

In a second aspect, an embodiment of the present invention further provides a device for determining close contact, the device comprising:

A module for determining other collected values, used to determine other collected values of other sensors in other devices located near the local device based on the proximity technology;

The local collection value determination module is used to determine the local collection value of the local sensor in the local device;

A feature data determination module, configured to use the other collected values, the local collected values, and the signal strength of the close-contact technique as feature data in the training samples; wherein the training samples are related to the local device and the other device association;

The sample label determination module is used to determine the label data in the training sample; wherein, the training sample is used to train a close contact judgment model.

In a third aspect, an embodiment of the present invention further provides an electronic device, the device comprising:

one or more processors;

memory for storing one or more programs;

When the one or more programs are executed by the one or more processors, the one or more processors implement a method for determining close contact according to any embodiment of the present invention.

In a fourth aspect, an embodiment of the present invention further provides a non-transitory computer-readable storage medium storing computer instructions, the computer instructions being used to make the computer execute the method for determining a close contact in any of the embodiments .

beneficial effect

The technical solution provided by the embodiments of the present invention determines other collected values of other sensors in other devices located near the local device based on the proximity contact technology; determines the local collected values of the local sensors in the local device; The locally collected value and the signal strength of the close-contact technique are used as characteristic data in the training sample; they are used to train the close-contact judgment model. The embodiment of the present invention comprehensively considers the sensor acquisition value in the device, and extracts richer feature information from the sensor acquisition value, thereby improving the accuracy and reliability of the relative position information acquired based on the close contact technology, and further improving the accuracy of close contact judgment. Accuracy.

Description of drawings

1 is a flowchart of a method for determining close contact in Embodiment 1 of the present invention;

Fig. 2 is the flow chart of a kind of close contact judgment method in the second embodiment of the present invention;

3 is a schematic structural diagram of a close contact judging device in Embodiment 3 of the present invention;

FIG. 4 is a schematic structural diagram of an electronic device to which a method for determining close contact in an embodiment of the present invention is applicable.

Embodiments of the present invention

The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention, but not to limit the present invention. In addition, it should be noted that, for the convenience of description, the drawings only show some but not all structures related to the present invention.

Example 1

FIG. 1 is a flow chart of a method for judging close contact in Embodiment 1 of the present invention. This embodiment can be applied to the situation of judging whether there is close contact between people. The method can be performed by a close contact judging device, which can be implemented in software and/or hardware, and can be configured in an electronic device. As shown in Figure 1, the method specifically includes:

S110. Determine other collected values of other sensors in other devices located near the local device based on the short-range contact technology.

Among them, the short-range contact technology refers to a short-range wireless communication technology, which is a short-distance communication in which both parties of the communication transmit information through radio waves and the transmission distance is limited to a short range. The close-contact technology may be Bluetooth technology and/or WiFi (Wireless Fidelity, wireless fidelity) technology, and the like. When the local device and other devices access the same WiFi at the same time period, other devices located near the local device can be determined based on the WiFi technology. In addition, Bluetooth is almost a standard configuration for mobile communication devices such as mobile phones, and almost every mobile phone is equipped with a Bluetooth module. It is only necessary to turn on the Bluetooth in the device, and other devices located near the local device can also be determined based on the Bluetooth technology under the condition that the communication conditions of the Bluetooth technology are satisfied.

Among them, the vicinity of the local device refers to the communication range of the local device’s close-contact technology, and correspondingly, other devices refer to the devices that are centered on the local device and are located in the effective communication range of the close-contact technology, that is, other devices are located close to the local device. The distance contact technology can communicate within the range. Optionally, the local device and other devices may be portable mobile communication devices such as cell phones and/or tablet computers.

When the proximity contact technology is the Bluetooth technology, when the Bluetooth of the local device scans other devices, the local device also determines the collected values of other sensors configured in the other devices. Among them, other sensors refer to sensors configured in other devices. The number of other devices scanned by the local device is at least one. Optionally, other determined values collected by other sensors in other devices are stored to the cloud server.

In an optional embodiment, the identification information of other devices located near the local device is acquired based on the proximity contact technology; other acquisition values of other sensors in the other devices are acquired from the server according to the identification information.

The identification information refers to unique information that can identify the device, and optionally, the identification information is MAC (Media Access Control Address, media access control address) address. The server stores the device identification and other collected values of other sensors in the device identified by the device identification. Optionally, store the acquired identification information of other devices in a local database or the cloud. The embodiment of the present invention obtains the acquisition value of the sensor in the device from the server according to the device identification, separates the acquisition process of the sensor acquisition value of the device from the device identification acquisition process, improves the data management efficiency, and simplifies the data acquisition operation.

In an optional embodiment, the sensor includes at least one of a gravity sensor, an acceleration sensor, a gyro sensor, a light sensor and a distance sensor.

Among them, both the gravity sensor and the acceleration sensor can measure the acceleration of the device due to gravity, and the gyroscope sensor can accurately determine the orientation of the moving device. Combining the collected values of these three sensors, the moving state of the device can be obtained. The light sensor can capture the brightness of the environment in which the device is located. The distance sensor can capture the distance between the user's head and the device. Whether the user is using the device and the external environment where the device is located can be determined according to the values collected by the light sensor and the distance sensor.

Optionally, while acquiring the values collected by the sensors in the other devices, the on-state data of the screens of the other devices and the surrounding noise level data of the other devices are acquired. Under normal circumstances, when the screen of the device is turned on, there is a high probability that the device is being used by the user. At this time, the signal channel and signal antenna of the close-contact technology are in an unobstructed state, and the network state of the close-contact technology good. On the contrary, when the screen of the device is turned off, there is a high probability that the device is not being used by the user at this time. Optionally, the device state and the user behavior state can be determined by combining the open state data of the screen of the other device with other acquisitions of other sensors of the other device. Exemplarily, the collected values of the gravity sensor, the acceleration sensor and the gyroscope sensor can be combined to obtain the moving state of the device. If the screen of the device is turned off at this time, it can be inferred that the device is not in use and the device is moving. Combined with the collected value of the light sensor to determine the brightness of the environment where the current device is located, and determine whether the current device is held by the user or placed in a backpack or pocket, so as to infer the signal channel and signal antenna of the close-contact technology at this time. The state of the network and the current state of proximity technology. If other acquisition values of other sensors in other devices are obtained when the status of the signal channel and signal antenna of the current proximity technology and the network status of the current proximity technology are not good, it indicates that the local device is related to the other device. The relative positions of the devices are very close. Since the above-mentioned devices are carried by the users, it reflects that the users who use the local device have a high possibility of being in close contact with the users who use other devices.

Optionally, the surrounding noise level data of other devices can be specifically acquired through the microphone of the device. The surrounding noise level data of other devices can not only indicate whether the user using the device is in a noisy environment, but also can combine the gravity sensor, acceleration sensor and gyroscope sensor to obtain the device movement status to determine whether the user using the device is interacting with other devices. chat with other people to determine the likelihood that the user of the device will be in close contact with other people.

S120. Determine the local collection value of the local sensor in the local device.

The locally collected value refers to the collected value of the sensor configured in the local device.

S130. Use the other collected values, the local collected values, and the signal strength of the close-contact technique as characteristic data in the training sample; wherein the training sample is associated with the local device and the other device.

The local device and other devices located near the local device form a device pair, and the collected values of the local sensors configured in the local device, the collected values of other sensors configured in other devices, and the signal strength of the proximity technology together constitute characteristic data. Exemplarily, in the case that the close-contact technology is the Bluetooth technology, the three other devices located near the local device from the Bluetooth scan of the local device are the other device 1 , the other device 2 and the other device 3 respectively. Then the local device and other device 1 can form a first device pair, the local device and other device 2 can form a second device pair, and the local device and other device 3 can form a third device pair, each device pair in the local device and other devices The collected values of the sensors in the training sample together constitute one feature data in the training sample. The collected values of the local sensors in the local device, the collected values of sensors in all other devices scanned by the local device at one time, and the signal strength of the close-contact technology together constitute a set of characteristic data.

Exemplarily, the short-distance contact technology is Bluetooth technology, and the signal strength of the short-distance contact technology is the strength of the Bluetooth signal. In addition to the bluetooth signal strength data, other collected values and the local collected values are also used as the characteristic data of the training samples, which can effectively avoid the problem of low accuracy of close contact judgment caused by only taking a single bluetooth signal strength as characteristic data .

In an optional embodiment, the current scan time of any other device currently scanned by the local device is determined; the current scan time is determined between the current scan time and the last scan time of the local device to the other device. The time interval is also used as the feature data in the training sample.

When the local device scans any other device near the local device based on the proximity technology, the identification information of the other device scanned by the local device and the scan time of the other device are stored in the local database or the cloud. In response to the local device scanning other devices, obtain the identification information of other devices, obtain the last scan time of the local device scanning to the same other device from the local database or the cloud according to the identification information, and compare the time interval between the last scan time and the current time, Together with the collected value of the local sensor in the local device, the collected value of other sensors in other devices, and the signal strength of the close-contact technology, it is used as the characteristic data of the training sample. When the time interval between the last scan of the local device and the last scan time of the other device is shorter, it indicates that the frequency of contact between the local device and the other device is higher, which indicates that the user using the local device is not connected to other people. The greater the likelihood of close contact. Taking the time interval between the last scan time scanned to the other device as the characteristic data of the training sample can improve the accuracy of the close contact judgment.

S140. Determine label data in the training sample; wherein the training sample is used to train a close contact judgment model.

After obtaining the characteristic data of the training samples, it is necessary to add labels to the characteristic data. Specifically, corresponding tag data is added to the feature data corresponding to each pair of devices formed by other devices scanned by the local device based on the proximity technology. Among them, the label data is a probability value used to indicate that the user using the local device is in close contact with others, and the value can be 0~1, and the label data can be marked by the user. The training samples and the label data of the samples are used as the input of the close contact judgment model to train the close contact judgment model. Among them, the close contact judgment model is used to output the deep learning algorithm model of the close contact probability between the local device and other devices. Exemplarily, the close contact judgment model is DNN (Deep Neural Networks, deep neural network) model.

Optionally, the close contact probability output from the close contact judgment model is input into the close contact judgment model as feature data in the training sample. As a device is scanned by more devices, the close contact judgment model will tend to give that device a higher probability of close contact.

In an optional embodiment, the target acquisition value of the target sensor in the target device located near the device to be tested is determined based on the proximity contact technology; the acquisition value to be measured of the sensor to be tested in the device to be tested is determined; The target acquisition value and the to-be-measured acquisition value are input into the close contact judgment model, and the probability of close contact between the device to be tested and the target device is obtained.

Among them, the device under test refers to the device that needs to determine whether there is close contact with other devices. The target device refers to the device that is located in the effective communication range of the close-contact technology with the device under test as the center.

Specifically, the trained close contact judgment model can be deployed on the background server of the close contact judgment application software. The application software can effectively mobilize the Bluetooth configured in the device registered by the software, and periodically scan the location near the tested device through Bluetooth. The target device is obtained, the identification information of the target device is obtained, and the sensor acquisition value configured in the device is read according to the identification information of the target device. Then, the read sensor collection value is input into the close contact judgment model, and the close contact judgment model outputs the probability of close contact between the device under test and the target device.

Embodiment 2

FIG. 2 is a flowchart of a method for determining close contact in Embodiment 2 of the present invention. This embodiment is further optimized on the basis of the above-mentioned embodiment. The specific optimization is that the determining the label data in the training sample includes: regularly obtaining the label content of the local user; wherein the label content includes at least one of the following: whether the local user has close contact with others, the local user The state data of the local user behavior and the local device location state data in the case of close contact with others; and the label data in the training sample is determined according to the label content.

As shown in Figure 2, the method includes:

S210. Determine other collected values of other sensors in other devices located near the local device based on the short-range contact technology.

S220. Determine the local collection value of the local sensor in the local device.

S230. Use the other collected values, the local collected values, and the signal strength of the proximity technology as feature data in the training sample; wherein the training sample is associated with the local device and the other device.

S240. Acquire the marked content of the local user periodically; wherein the marked content includes at least one of the following: whether the local user is in close contact with others, status data of the local user's behavior under the condition that the local user is in close contact with others, and the local device location status data.

Among them, whether the local user has close contact with other people is given by the local user based on the personal judgment of the close contact. The local user behavior state includes at least one of the following: staying in a place, walking on the road, and in a vehicle. The local device location state includes at least one of the following: a handheld state, in a handbag or pocket, and on a desk. The behavior status of the local user and the location status of the local device will affect the signal channel and signal antenna status of the proximity technology, thereby affecting the network status of the proximity technology, which in turn affects the judgment of whether the local user has close contact with other people. accuracy.

In an optional embodiment, a marked questionnaire is generated according to the local user behavior and the network status of the local close-contact communication technology; the marked questionnaire is displayed through the local device periodically; the marked questionnaire is displayed according to the local user Fill in the information of the sex questionnaire, and generate the annotation content of the local user.

The labeled questionnaire refers to a questionnaire used to collect user annotations. Optionally, the annotated questionnaire includes at least one of: whether the local user has close contact with others, status data of the local user's behavior under the condition that the local user is in close contact with others, and the local device location status data.

The network status of the local proximity communication technology is affected by the status of the signal channel and the signal antenna of the proximity communication technology, and the signal channel and the signal antenna of the proximity communication technology are also affected by the location status of the local device. Taking the Bluetooth in the mobile phone as an example, the mobile phone placed in the user's briefcase and the mobile phone held by the user have different Bluetooth signal channels and signal antennas. The network status of the mobile phone held by the user is stronger than that of the mobile phone placed The network status of the phone's Bluetooth in the user's briefcase. The user's behavior directly determines the possibility of the user being in close contact with others.

Optionally, the application software for close contact judgment can periodically display the marked questionnaire to the device registered in the application software. Exemplarily, the marked questionnaire can be pushed to the local device every 15 minutes, wherein the local device is in the close contact judgment. The device registered in the application software. The local user fills in the marked questionnaire, and sends the local user's filling information on the marked questionnaire to the close contact judgment application software through the local device within the specified time, and the application software generates the local user according to the filling information of the local user on the marked questionnaire. the labeling content. In the embodiment of the present invention, the user behavior status, device location status, and whether the user has close contact with others can be obtained in time by periodically sending a labeled questionnaire to the user, thereby making the obtained tag data more accurate, thereby improving the accuracy of close contact judgment. .

S250. Determine the label data in the training sample according to the label content, where the training sample is used to train a close contact judgment model.

Among them, the marked content is related to the information that the user fills in the marked questionnaire. Exemplarily, as to whether the local user has close contact with others, the marked content is 0 or 1, 0 means no close contact with others; 1 means with close contact with others. According to the set algorithm, a value between 0 and 1 is generated from the label content of the local user that is regularly collected within the set time period, and the value is used as the label data of the training sample. Exemplarily, if the set duration is 1 hour, and 15 minutes is used as the timing time, 4 times of marked content is obtained within 1 hour. At the same time, if the local device takes 1 minute as a cycle, other devices located near the local device are scanned based on the proximity technology. The local device will scan 15 times within 15 minutes. The content of the 4 annotations is expanded in the same proportion to 15 scans for each annotation, and the 60 values of 0 or 1 within one hour are used as the first value. That is to say, a user's annotation content corresponds to 15 sets of feature data. As an example, assuming that the 4-time annotation content is 0, 1, 0, and 1, respectively, in the first 15 minutes of an hour, the obtained 15 The first value corresponding to the set of feature data will be 15 0s; in the second 15 minutes within an hour, the first value corresponding to the other 15 sets of feature data obtained will be 15 1s, which can be determined The first values corresponding to the 60 sets of characteristic data obtained within one hour, and then the 60 first values corresponding to the above 60 sets of characteristic data are smoothed by using the EMA (Exponential Moving Average) method, so that the above The 60 first values are converted into 60 second values between 0 and 1, which are used as label data for 60 sets of feature data obtained within one hour. Exemplarily, if the first values corresponding to 15 sets of characteristic data obtained in the second 15 minutes of an hour are 15 1s, 15 second values can be obtained after the 15 1s are processed by the EMA algorithm. The 15 second values are 0.125, 0.234, 0.33, 0.414, 0.487, 0.551, 0.607, 0.656, 0.699, 0.737, 0.77, 0.799, 0.824, 0.846, 0.865, and the above second value is the second one within an hour Label data for 15 sets of feature data acquired within 15 minutes. The second value is an exponential moving average obtained after the first value is processed by the EMA algorithm, the number of the second value is the same as the number of the first value, and the second value is the label data of each set of characteristic data.

Optionally, the weight of the second numerical value is generated according to the state data of the local user behavior and the local equipment location state data under the situation that the local user is in close contact with others, and the numerical value after the weighting calculation is used as the final label data, Combining the user's subjective judgment on the probability of close contact with the objective user behavior status data and device location status data makes the obtained tag data more accurate.

The local device may scan multiple other devices at one time, forming multiple device pairs. All device pairs formed by the local device scan once are one set of feature data, and each device pair is used as one piece of feature data that composes the set of feature data. One set of feature data may include at least one piece of feature data, and the label data of each set of feature data is consistent with the label data of each piece of feature data constituting the set of feature data.

In the embodiment of the present invention, the labeling content of the local user is obtained regularly, the labeling data in the training sample is determined according to the labeling content, and the close contact judgment model is trained by using the training sample. The embodiment of the present invention determines the label data of the training sample according to the label content of the local user obtained periodically, so that the label data of the training sample is more accurate, thereby improving the accuracy of the close contact judgment.

Embodiment 3

FIG. 3 is a schematic structural diagram of a close contact judging device in Embodiment 3 of the present invention. This embodiment is applicable to the situation of judging whether there is close contact between people. The apparatus may be implemented in software and/or hardware, and may be configured in an electronic device.

As shown in FIG. 3 , the apparatus may include: other collected value determination module 310 , local collected value determination module 320 , feature data determination module 330 and sample label determination module 340 .

other collected value determination module 310, configured to determine other collected values of other sensors in other devices located near the local device based on the proximity technology;

a local collection value determination module 320, configured to determine the local collection value of the local sensor in the local device;

A feature data determination module 330, configured to use the other collected values, the local collected values, and the signal strength of the close-contact technique as feature data in the training sample; wherein the training sample is related to the local device and the other device associations;

The sample label determination module 340 is configured to determine the label data in the training samples; wherein, the training samples are used to train a close contact judgment model.

Optionally, the device further includes: a current scan time determination module, used to determine the current scan time of any other device currently scanned by the local device; a feature data determination module 330, also used to compare the current scan time with the current scan time. The time interval between the last scan of the local device and the last scan time of the other device is also used as the feature data in the training sample.

Optionally, the sample label determination module 340 includes: a label content acquisition sub-module, configured to obtain the label content of the local user at regular intervals; wherein the label content includes at least one of the following: whether the local user has close contact with others, whether The state data of the behavior of the local user and the location state data of the local device when the local user is in close contact with others; the label data determination sub-module is configured to determine the label data in the training sample according to the label content.

Optionally, the marked content acquisition sub-module includes: a marked questionnaire generation unit, which is used for generating marked questionnaires according to local user behavior and the network status of the local close-contact communication technology; and a marked questionnaire display unit, which is used for regularly passing all The local device displays the marked questionnaire; the marked content generating unit is configured to generate the marked content of the local user according to the filling information of the marked questionnaire by the local user.

Optionally, the sensor includes: at least one of a gravity sensor, an acceleration sensor, a gyroscope sensor, a light sensor and a distance sensor.

Optionally, the other collected value determination module 310 includes: an identification information acquisition sub-module for acquiring identification information of other devices located near the local device based on the proximity contact technology; other collected value acquisition sub-module for obtaining identification information according to the The identification information is obtained, and other acquisition values of other sensors in the other devices are obtained from the server.

Optionally, the device further includes: a target collection value determination module, configured to determine the target collection value of a target sensor located in a target device near the device to be tested based on the proximity contact technology; a target collection value determination module, used is used to determine the to-be-measured acquisition value of the sensor to be measured in the device to be tested; the close contact probability determination module is used to input the target acquisition value and the to-be-measured acquisition value into the close contact judgment model to obtain the to-be-measured value The probability that there is close contact between the device and the target device.

A close contact judging device provided by an embodiment of the present invention can execute a close contact judging method provided by any embodiment of the present invention, and has functional modules and beneficial effects corresponding to executing a close contact judging method.

Embodiment 4

According to embodiments of the present invention, the present invention further provides an electronic device and a readable storage medium.

FIG. 4 is a schematic structural diagram of an electronic device implementing a method for determining a close contact according to an embodiment of the present invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic devices may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are by way of example only, and are not intended to limit implementations of the application described and/or claimed herein.

As shown in FIG. 4, the electronic device includes: one or more processors 410, a memory 420, and interfaces for connecting various components, including a high-speed interface and a low-speed interface. The various components are interconnected using different buses and may be mounted on a common motherboard or otherwise as desired. Processor 410 may process instructions executed within the electronic device, including instructions stored in or on memory to display graphical information of the GUI on an external input/output device, such as a display device coupled to an interface. In other embodiments, multiple processors 410 and/or multiple buses may be used with multiple memories and multiple memories, if desired. Likewise, multiple electronic devices may be connected, with each device providing some of the necessary operations (eg, as an array of devices, a set of blade devices, or a multiprocessor system). A processor 410 is taken as an example in FIG. 4 .

The memory 420 is the non-transitory computer-readable storage medium provided by the present application. The memory stores instructions executable by at least one processor, so that the at least one processor executes the method for determining close contact provided by the present application. The non-transitory computer-readable storage medium of the present application stores computer instructions, and the computer instructions are used to cause the computer to execute the method for determining a close contact provided by the present application.

As a non-transitory computer-readable storage medium, the memory 420 can be used to store non-transitory software programs, non-transitory computer-executable programs and modules, such as a program corresponding to a method for determining close contact based on big data in the embodiment of the present invention. Instructions/modules (eg, shown in FIG. 3 including additional collected value determination module 310, local collected value determination module 320, feature data determination module 330, and sample label determination module 340). The processor 410 executes various functional applications and data processing of the electronic device by running the non-transitory software programs, instructions and modules stored in the memory 420 , that is, implementing a method for determining close contact in the above method embodiments.

The memory 420 may include a stored program area and a stored data area, wherein the stored program area may store an operating system and an application program required for at least one function; data etc. Additionally, memory 420 may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory 420 may optionally include memory disposed remotely with respect to the processor 410, and these remote memories may be connected to the electronic device for performing a method of close contact determination 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 electronic device for performing a close contact determination method may further include: an input device 430 and an output device 440 . The processor 410, the memory 420, the input device 430, and the output device 440 may be connected through a bus or in other ways, and the connection through a bus is taken as an example in FIG. 4 .

The input device 430 can receive input numerical or character information, and generate key signal input related to user settings and function control of an electronic device performing a close contact determination method, such as a touch screen, a keypad, a mouse, a trackpad, a touchpad , a pointing stick, one or more mouse buttons, a trackball, and an input device such as a joystick. The output device 440 may include a display device, auxiliary lighting devices (eg, LEDs), haptic feedback devices (eg, vibration motors), and the like. The display device may include, but is not limited to, a liquid crystal display (LCD), a light emitting diode (LED) display, and a plasma display. In some implementations, the display device may be a touch screen.

Various implementations of the systems and techniques described herein can be implemented in digital electronic circuitry, integrated circuit systems, application specific ASICs (application specific integrated circuits), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include being implemented in one or more computer programs executable and/or interpretable on a programmable system including at least one programmable processor that The processor, which may be a special purpose or general-purpose programmable processor, may receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device an output device.

These computational programs (also referred to as programs, software, software applications, or codes) include machine instructions for programmable processors, and may be implemented using high-level procedural and/or object-oriented programming languages, and/or assembly/machine languages calculation program. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and/or apparatus for providing machine instructions and/or data to a programmable processor ( For example, magnetic disks, optical disks, memories, programmable logic devices (PLDs), including machine-readable media that receive machine instructions as machine-readable signals. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.

To provide interaction with a user, the systems and techniques described herein may be implemented on a computer having: a display device (eg, a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user ); and a keyboard and pointing device (eg, a mouse or trackball) through which a user can provide input to the computer. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (eg, visual feedback, auditory feedback, or tactile feedback); and can be in any form (including acoustic input, voice input, or tactile input) to receive input from the user.

The systems and techniques described herein can be implemented on a computing system that includes back-end components (eg, as a data server), or a computing system that includes middleware components (eg, an application server), or a computing system that includes front-end components (eg, a user computer having a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or including such backend components, middleware components, Or any combination of front-end components in a computing system. The components of the system may be interconnected by any form or medium of digital data communication (eg, a communication network). Examples of communication networks include: Local Area Networks (LANs), Wide Area Networks (WANs), the Internet, and blockchain networks.

A computer system can include clients and servers. Clients and servers are generally remote from each other and usually interact through a communication network. The relationship of client and server arises by computer programs running on the respective computers and having a client-server relationship to each other.

It should be understood that steps may be reordered, added or deleted using the various forms of flow shown above. For example, the steps described in the present application can be performed in parallel, sequentially or in different orders, and as long as the desired results of the technical solutions disclosed in the present application can be achieved, no limitation is imposed herein.

The above-mentioned specific embodiments do not constitute a limitation on the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modifications, equivalent replacements and improvements made within the spirit and principles of this application shall be included within the protection scope of this application.

Note that the above are only preferred embodiments of the present invention and applied technical principles. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the protection scope of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and can also include more other equivalent embodiments without departing from the concept of the present invention. The scope is determined by the scope of the appended claims.

Claims

A method for judging close contact, characterized in that the method comprises:

Determine other acquired values of other sensors in other devices located near the local device based on proximity technology;

Determine the local acquisition value of the local sensor in the local device;

Using the other collected values, the local collected values and the signal strength of the proximity technology as characteristic data in the training samples; wherein the training samples are associated with the local device and the other devices;

Determine the label data in the training sample; wherein, the training sample is used to train a close contact judgment model.
The method according to claim 1, wherein the method further comprises:

Determine the current scan time when the local device is currently scanned to any other device;

The time interval between the current scan time and the last scan time when the local device scanned the other device last time is also used as the feature data in the training sample.
The method according to claim 1, wherein the determining the label data in the training sample comprises:

Acquire the marked content of the local user regularly; wherein, the marked content includes at least one of the following: whether the local user has close contact with others, the status data of the local user's behavior under the condition that the local user is in close contact with others, and the Local device location status data;

According to the labeled content, the labeled data in the training sample is determined.
The method according to claim 3, wherein the timed acquisition of the marked content of the local user comprises:

Generate annotated questionnaires based on local user behavior and local proximity communication technology network status;

periodically displaying the marked questionnaire through the local device;

According to the filling information of the marked questionnaire by the local user, the marked content of the local user is generated.
The method according to claim 1, wherein the sensor comprises: at least one of a gravity sensor, an acceleration sensor, a gyroscope sensor, a light sensor and a distance sensor.
The method according to claim 1, characterized in that, determining other collected values of other sensors in other devices located near the local device based on the proximity technology, comprising:

Obtain the identification information of other devices located near the local device based on the proximity technology;

According to the identification information, other acquisition values of other sensors in the other device are acquired from the server.
The method according to claim 1, wherein the method further comprises:

Determine the target acquisition value of the target sensor in the target device located near the device to be tested based on the proximity contact technology;

Determine the acquisition value to be measured of the sensor to be measured in the device to be tested;

The target acquisition value and the to-be-measured acquisition value are input into the close contact judgment model to obtain the probability of close contact between the device to be tested and the target device.
A close contact judgment device, characterized in that the device comprises:

A module for determining other collected values, used to determine other collected values of other sensors in other devices located near the local device based on the proximity technology;

The local collection value determination module is used to determine the local collection value of the local sensor in the local device;

A feature data determination module, configured to use the other collected values, the local collected values, and the signal strength of the close-contact technique as feature data in the training samples; wherein the training samples are related to the local device and the other device association;

The sample label determination module is used to determine the label data in the training sample; wherein, the training sample is used to train a close contact judgment model.
An electronic device, characterized in that the device comprises:

one or more processors;

memory for storing one or more programs;

When the one or more programs are executed by the one or more processors, the one or more processors implement a method for determining close contact according to any one of claims 1-7.
A non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to make the computer execute the method for determining a close contact according to any one of claims 1-7.