Prison bracelet-based early warning method and device, computer equipment and storage medium

Abstract

The application discloses a kind of early warning method, device, computer equipment and storage medium based on prison bracelet, comprising: obtaining the indoor map of the room where multiple prison bracelets are located, and obtaining the acquisition data of multiple prison bracelets, wherein the acquisition data includes physiological data and the signal strength data of the connection between Bluetooth device and prison bracelet;According to the signal strength data of the connection between Bluetooth device and prison bracelet, the first position coordinates of multiple prison bracelets are calculated;Multiple first position coordinates are added to the indoor map, to form a prison bracelet map;Multiple first position coordinates in prison bracelet map are connected into a pattern;Determine whether the pattern is a regular pattern;If not, determine whether the physiological data exceeds the first preset threshold;If yes, early warning is carried out.This early warning method is simple and effective, low in cost, and small in calculation, can timely find the abnormal situation between prisoners, and avoid the occurrence of vicious events.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of intelligent supervision, in particular, relates to a warning method and device based on a prison bracelet, computer equipment and a storage medium. BACKGROUND

[0002] Most of the prisoners in prison are long-term prisoners with heavy crimes, great social harm and deep subjective malice. These prisoners have a higher probability of committing serious supervision accidents such as self-injury, escape, violence, and harm to others during their imprisonment. In order to ensure the long-term stability of the prison, the bracelet, as one of the high-tech devices that can monitor, discipline and collect the daily behavior data of prisoners, can realize intelligent management of prisons. Intelligent management of prisons is conducive to all-weather, all-round and whole-process supervision and control of the behavior of prisoners, improves the safety prevention coefficient and emergency response ability of prisons, maximizes the safety of prisons, and at the same time improves the management efficiency and effectiveness of prisons and reduces the work burden of prison guards.

[0003] The existing prison bracelet used in prisons has many functions, such as electronic fence, historical trajectory query, multiple precise positioning, anti-disassembly alarm, health monitoring and the like, but it does not have a good early warning effect for some special alarm scenes. SUMMARY

[0004] The main purpose of the present application is to provide a warning method and device based on a prison bracelet, computer equipment and a storage medium, which aims to solve the technical problem that there is no good early warning effect for some special alarm scenes.

[0005] The present application discloses the following technical solutions:

[0006] A warning method based on a prison bracelet, comprising:

[0007] Obtain the indoor map of the room where the plurality of prison bracelets are located, and obtain the collection data of the plurality of prison bracelets, wherein the collection data at least includes physiological data and signal strength data of the Bluetooth device connected with the prison bracelet;

[0008] According to the signal strength data of the Bluetooth device connected with the prison bracelet, the first position coordinates of the plurality of prison bracelets are calculated;

[0009] The plurality of first position coordinates are added to the indoor map correspondingly to form a prison bracelet map;

[0010] The plurality of first position coordinates in the prison bracelet map are connected into a graph;

[0011] Determine whether the graph is a regular graph;

[0012] If not, it is judged whether the physiological data exceeds a first preset threshold value;

[0013] If yes, a warning is performed.

[0014] Further, the step of calculating the first position coordinates of the plurality of prison bracelets according to the signal strength data of the Bluetooth devices connected with the prison bracelets comprises:

[0015] According to the signal strength data, the distance between each Bluetooth device and the prison bracelet is calculated;

[0016] The second position coordinates of each Bluetooth device are obtained;

[0017] According to the second position coordinates of each Bluetooth device and the distance between each Bluetooth device and the prison bracelet, the first position coordinates of the prison bracelet are calculated.

[0018] Further, the step of adding the plurality of first position coordinates to the indoor map to form a prison bracelet map after the step comprises:

[0019] The prison bracelet map and the physiological data are input into a neural network model for calculation to obtain a probability value of the prison bracelet wearer fighting, wherein the neural network model is trained by a training set;

[0020] It is judged whether the probability value exceeds a second preset threshold value;

[0021] If yes, a warning is performed.

[0022] Further, the step of obtaining the collection data of the plurality of prison bracelets after the step comprises:

[0023] According to the physiological data, it is judged whether there is a sleep deficiency within a day;

[0024] If yes, the number of days of sleep deficiency is calculated;

[0025] If the number of days exceeds a fourth preset threshold value, a warning is performed.

[0026] Further, the step of judging whether there is a sleep deficiency within a day according to the physiological data comprises:

[0027] According to the physiological data, the sleep state is judged, wherein the sleep state comprises a light sleep state, a deep sleep state and a sleep wake state;

[0028] The first duration of the light sleep state, the second duration of the deep sleep state and the third duration of the sleep wake state are recorded;

[0029] If the first time length exceeds a fifth preset threshold, and / or the second time length is lower than a sixth preset threshold, and / or the third time length exceeds a seventh preset threshold;

[0030] It is concluded that sleep deficiency occurs within a day.

[0031] Further, the collected data further includes monitoring data, after the step of acquiring the collected data of the plurality of prison bracelets, the method further comprises:

[0032] According to the monitoring data, the time length of each person talking with the prison bracelet wearer is recorded;

[0033] If the time length of the talker talking with the prison bracelet wearer exceeds an eighth preset threshold;

[0034] The talker is marked as an intimate of the prison bracelet wearer.

[0035] If the prison bracelet wearer appears an abnormal situation, the intimate is directly locked.

[0036] Further, the early warning includes sending early warning information.

[0037] The application also provides a prison bracelet-based early warning device, comprising:

[0038] An acquisition module is configured to acquire an indoor map of a room where a plurality of prison bracelets are located, and acquire collected data of the plurality of prison bracelets, wherein the collected data at least includes physiological data and signal strength data of a Bluetooth device connected with the prison bracelet;

[0039] A calculation module is configured to calculate first position coordinates of the plurality of prison bracelets according to the signal strength data of the Bluetooth device connected with the prison bracelet;

[0040] A prison bracelet map forming module is configured to add the plurality of first position coordinates to the indoor map correspondingly to form a prison bracelet map;

[0041] A connection module is configured to connect the plurality of first position coordinates in the prison bracelet map into a pattern;

[0042] A regular pattern judging module is configured to judge whether the pattern is a regular pattern;

[0043] A first preset threshold judging module is configured to judge whether the physiological data exceeds a first preset threshold if the answer is no;

[0044] An early warning module is configured to perform early warning if the answer is yes.

[0045] The application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method according to any one of the preceding embodiments when executing the computer program.

[0046] The application further provides a computer readable storage medium, which stores a computer program, and the computer program implements the steps of the method according to any one of the preceding embodiments when executed by a processor.

[0047] Advantages:

[0048] In the application, the position relationship and physiological state of prisoners are used to determine abnormal situations. In a supervision place, the behavior of prisoners is regulated and limited, so when multiple prisoners are in a room, the position relationship between them will be in a regular state. For example, when they are in a cell, a classroom, a conversation room or a dining room, they will queue up to wait and stay, so the position relationship between them will be in a regular arrangement. Or, multiple prisoners sit on seats in a classroom or a dining room, and since the seats in these places are regularly arranged, the position relationship between these prisoners is also regularly arranged. Therefore, when multiple prisoners are in a room, and the position relationship between them is not regularly arranged, it indicates that these prisoners may have abnormal situations such as fighting. Of course, these prisoners may have some position disorder just after entering the room. At this time, the physiological data of the prisoners are used for judgment, for example, the heart rate or breathing rate of multiple prisoners increases, so it can be determined that the prisoners have fighting situations, and then a warning action is directly taken to help the supervisors quickly calm down the abnormal or violent events. This warning method is simple and effective, low in cost and small in calculation amount, and can timely find abnormal situations between prisoners and avoid the occurrence of serious events. BRIEF DESCRIPTION OF DRAWINGS

[0049] Figure 1 Fig. 1 is a flow diagram of a warning method based on a prison bracelet according to an embodiment of the application;

[0050] Figure 2 Fig. 2 is a structural schematic block diagram of a warning device based on a prison bracelet according to an embodiment of the application;

[0051] Figure 3 Fig. 3 is a structural schematic block diagram of a computer device according to an embodiment of the application.

[0052] The implementation, functional features and advantages of the application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0053] It should be understood that the specific embodiments described herein are merely illustrative of the present application and do not limit the present application.

[0054] With reference to Figure 1 An embodiment of the present application provides a prison bracelet-based early warning method, comprising the following steps:

[0055] S1: acquiring an indoor map of a room where a plurality of prison bracelets are located, and acquiring collection data of the plurality of prison bracelets, wherein the collection data at least includes physiological data and signal strength data of a Bluetooth device connected with the prison bracelet;

[0056] S2: calculating first position coordinates of the plurality of prison bracelets according to the signal strength data of the Bluetooth device connected with the prison bracelet;

[0057] S3: adding the first position coordinates to the indoor map correspondingly to form a prison bracelet map;

[0058] S4: connecting the first position coordinates in the prison bracelet map into a pattern;

[0059] S5: determining whether the pattern is a regular pattern;

[0060] S6: if not, determining whether the physiological data exceeds a first preset threshold;

[0061] S7: if yes, performing early warning.

[0062] In the above embodiment, the prisoners generally move indoors, and the moving area usually includes a cell, a classroom, a conversation room, a production workshop and the like. Compared with an open outdoor environment, the indoor environment is relatively complex and there are many obstructions. The obstructions can block the line of sight of the prison staff, or when the number of people in the room is large, the prison staff can also be blocked. If a fight occurs between the prisoners, the prison staff can not be able to discover it in time. The prison bracelet-based fight early warning can help the prison staff to discover the abnormal situation between the prisoners in time.

[0063] In the present application, the position relationship and physiological state of prisoners are used to judge abnormal situations. In a supervision place, the behavior of prisoners is regulated and limited, so when multiple prisoners are in a room, the position relationship between them will show a regular state. For example, when they are in a cell, classroom, conversation room, or dining room, they will queue up to wait and stay, and at this time, the position relationship between them will show a regular arrangement. Or multiple prisoners sit on seats in a classroom or dining room, and since the seats in these places are regularly arranged, the position relationship between these prisoners also shows a regular arrangement. Therefore, when multiple prisoners are in a room, the position relationship between them shows an irregular arrangement, indicating that these prisoners may have abnormal situations such as fighting. Of course, these prisoners may also have some position confusion just after entering the room. At this time, some physiological data of the prisoners are used for judgment, for example, the heart rate or breathing rate of multiple prisoners increases, so it can be determined that fighting has occurred between these prisoners, and then direct warning action is taken to help the instructors quickly calm down these abnormal or violent events. This warning method is simple and effective, low in cost, and small in calculation amount, and can timely discover abnormal situations between prisoners and avoid the occurrence of vicious events.

[0064] As described in step S1 above, the indoor map of the room where the multiple prison bracelets are located is obtained, and the collection data of the multiple prison bracelets is obtained, wherein the collection data includes physiological data and signal strength data of the Bluetooth device connected with the prison bracelet;

[0065] After a prisoner wearing a prison bracelet enters a room, the indoor map of the room is obtained. Specifically, all map data of the supervision place can be collected, marked, and stored, and the map of a certain room is needed. The corresponding map data is retrieved according to the mark of the room.

[0066] The prison bracelet worn by a prisoner includes a heart rate monitoring module, a body temperature monitoring module, a blood pressure monitoring module, a Bluetooth module, etc. The prison bracelet collects various data through these modules, including physiological data, listening data, and signal strength data of the Bluetooth device connected with the prison bracelet. The system uses these data for calculation.

[0067] As described in step S2 above, the first position coordinates of the multiple prison bracelets are calculated according to the signal strength data of the Bluetooth device connected with the prison bracelet;

[0068] The Bluetooth device is a device supporting Bluetooth wireless connection. In the present application, the Bluetooth device needs to access multiple prison bracelets, so a Bluetooth local area network can be installed indoors in the supervision site, the local area network is configured as a multi-user based network connection mode, and it is ensured that the Bluetooth device is always the master device of the Bluetooth local area network. Specifically, the Bluetooth device can be a Bluetooth router, which uses bidirectional communication technology, supports up to 40 devices to be connected at the same time, and can scan more than 300 Bluetooth broadcast packets per second.

[0069] The Bluetooth device has Bluetooth broadcast, Bluetooth scanning and Bluetooth connection functions. The Bluetooth device continuously emits its own Bluetooth broadcast information to the surrounding area. After the prison bracelet is wirelessly connected with the Bluetooth device, the prison bracelet acts as a receiving end and receives the Bluetooth broadcast information emitted by the Bluetooth device. The closer the prison bracelet is to the Bluetooth device, the stronger the signal strength received by the prison bracelet, and the larger the signal strength data. The farther the prison bracelet is from the Bluetooth device, the weaker the signal strength received by the prison bracelet, and the smaller the signal strength data. The distance between the prison bracelet and the Bluetooth device can be obtained according to the signal strength value, and then the first position coordinate of the prison bracelet can be obtained according to the position of the Bluetooth device on the indoor map. This method has low requirements for the time system and is not affected by factors such as transmission delay and antenna delay. It does not require additional hardware to calculate the first position coordinate of the prison bracelet using the signal strength data of the Bluetooth device and the prison bracelet connected to the Bluetooth device. Therefore, the hardware cost, software cost and time cost are relatively low, the use is simple, and the method has the significant advantages of low cost, low energy consumption, low complexity and high sensitivity.

[0070] As described in steps S3 and S4 above, the first position coordinates are added to the indoor map in correspondence, and a prison bracelet map is formed.

[0071] Each prison bracelet is added to the indoor map in correspondence with the first position coordinate, and a prison bracelet map is formed.

[0072] As described in steps S4 and S5 above, the first position coordinates in the prison bracelet map are connected to form a pattern, and it is determined whether the pattern is a regular pattern.

[0073] The prison bracelet map includes the position information of each prison bracelet. The positions of the prison bracelets are connected as connection points, and the connection points of the positions of the prison bracelets are connected into lines on the prison bracelet map to form a pattern. If the pattern is a regular pattern, it indicates that the positional relationship between the multiple prisoners is regular, i.e., the prisoners are acting in a standard manner in the room and there is no situation of fighting. Specifically, the regular pattern can be a bar, a square, a rectangle, etc. For example, if the pattern is a bar, it indicates that the prisoners are queuing. If the pattern is not a regular pattern but an irregular pattern, it indicates that the prisoners are gathering in a disorderly manner, and there can be a situation of fighting.

[0074] If no, it is judged whether the physiological data exceeds the first preset threshold value according to steps S6 and S7 described above; if yes, a warning is performed.

[0075] It is now necessary to further judge whether the prisoners are fighting. The physiological data collected by the prison bracelet includes heart rate and breathing rate. If a person performs a violent movement such as fighting, his heart rate and breathing rate will increase. Therefore, if the physiological data of the prisoners exceeds the first preset threshold value, it can be determined that there is a situation of fighting among the prisoners, and a warning behavior can be performed at this time. The specific warning behavior can be to send a warning information to the correction personnel, or to send a warning information to the prisoners by using the prison bracelet or a loudspeaker.

[0076] In an embodiment, the step S2 of calculating the first position coordinates of the multiple prison bracelets according to the signal strength data of the connection between the Bluetooth devices and the prison bracelets comprises:

[0077] S201: calculating the distance between each Bluetooth device and the prison bracelet according to the signal strength data;

[0078] S202: obtaining the second position coordinates of each Bluetooth device;

[0079] S203: calculating the first position coordinates of the prison bracelet according to the second position coordinates of each Bluetooth device and the distance between each Bluetooth device and the prison bracelet.

[0080] In the above embodiment, as described in step S201, the Bluetooth device is the sending end, continuously emitting its Bluetooth broadcast information to the surroundings, and the prison bracelet is the receiving end, receiving the Bluetooth broadcast information. Alternatively, the Bluetooth device can also be the receiving end, and the prison bracelet can be the sending end. The farther the receiving end is from the sending end, the weaker the received signal strength value; the closer the receiving end is to the sending end, the stronger the received signal strength value. The signal strength value of the wireless signal received by the receiving end is generally a negative value. The larger the signal strength value, the stronger the signal. The signal strength value ranges from 0 to -100. 0 is an ideal case and does not exist in actual applications.

[0081] The distance between each Bluetooth device and the prison bracelet can be calculated using the formula d = 10^(abs(RSSI)-A) / (10*n)). Where d is the distance between the Bluetooth device and the prison bracelet, RSSI is the signal strength data (negative value), A is the signal strength when the sending end and the receiving end are 1 meter apart, and n is the environmental attenuation factor. The values of A and n need to be tested on the site to obtain. The environmental attenuation factor is different for different sites, and even different object obstructions in the same site can affect the environmental attenuation factor. However, in the same site, A and n can be set as parameters with default values.

[0082] As described in steps S202 and S203, multiple Bluetooth devices are generally set indoors, and the positions of each Bluetooth device are fixed. For example, a room has three Bluetooth devices, and the position of the access end, i.e., the prison bracelet, can be approximately calculated using the three-point positioning principle. That is, the intersection of the 360-degree diffusion of the sending end signal forming a spherical surface, and the first position coordinate of the prison bracelet is calculated.

[0083] In an embodiment, after step S3 of adding multiple first position coordinates corresponding to the prison bracelet map to the indoor map to form the prison bracelet map, the following steps are included:

[0084] S301: input the prison bracelet map and the physiological data into a neural network model for calculation to obtain a probability value of the prison bracelet wearer engaging in fighting, wherein the neural network model is trained by a training set;

[0085] S302: determine whether the probability value exceeds a second preset threshold;

[0086] S303: if yes, perform a warning.

[0087] In the above embodiment, the training set includes the position relationship and physiological data of each person in the fight scene, the neural network model has the ability of autonomous learning, the neural network model is trained through the training set, and the prediction capability of the neural network model can be improved. The prison bracelet map and the physiological data are input into the trained neural network model, and the neural network model can output a probability value of the current scene being a fight scene. If the probability value exceeds a second preset threshold, it indicates that the scene is a fight scene.

[0088] Or the position relationship and physiological data of each person in a plurality of normal scenes can be used to form a training set, the prison bracelet map and the physiological data are input into the trained neural network model, and the neural network model can output a probability value of the current scene being a normal scene. If the probability value exceeds a preset threshold, it indicates that the scene is a normal scene.

[0089] Or two neural networks can be trained at the same time. The position relationship and physiological data of each person in a plurality of fight scenes are used to train the neural network into a first neural network, and the position relationship and physiological data of each person in a plurality of normal scenes are used to train the neural network into a second neural network. Then the prison bracelet map and the physiological data are input into the two neural networks, and the results predicted by the two neural networks are weighted and summed to obtain the final result. Using this way to predict can make the judgment more accurate.

[0090] In an embodiment, after the step S1 of acquiring the collection data of the plurality of prison bracelets, the method further includes:

[0091] S101: judging whether there is a sleep deficiency condition in a day according to the physiological data;

[0092] S102: if there is, calculating the number of days of the sleep deficiency condition;

[0093] S103: if the number of days exceeds a fourth preset threshold, performing a warning.

[0094] In the above embodiment, the sleep condition is closely related to the physiological health and psychological health of a person. In order to improve the reform effect and management effect, the sleep condition of the prisoner should be paid attention to in time. If the prisoner has a long-term sleep deficiency condition, a warning should be given in time, and the information is sent to the management personnel.

[0095] The prison bracelet collects physiological data of the prisoner, and then the system judges the sleep condition of the prisoner according to the physiological data. It is judged whether the prisoner has sleep deprivation for consecutive days. Specifically, if the prisoner has sleep deprivation on a certain day, the number of days of sleep deprivation of the prisoner is recorded as 1; then it is judged whether the number of days of sleep deprivation of the prisoner exceeds the fourth preset threshold, if not, it is judged whether the prisoner has sleep deprivation the next day, if yes, the number of days of sleep deprivation of the prisoner is recorded as 2; then it is judged whether the number of days of sleep deprivation of the prisoner exceeds the fourth preset threshold, and so on. If the number of days of sleep deprivation of the prisoner exceeds the fourth preset threshold, a warning is given; if the prisoner has no sleep deprivation in a day, the number of days of sleep deprivation of the prisoner is recorded as 0.

[0096] In an embodiment, the step S101 of judging whether there is sleep deprivation in a day according to the physiological data comprises:

[0097] S111: judging the sleep state according to the physiological data, wherein the sleep state comprises light sleep state, deep sleep state and sleep wake state;

[0098] S112: recording the first duration of the light sleep state, the second duration of the deep sleep state and the third duration of the sleep wake state;

[0099] S113: if the first duration exceeds the fifth preset threshold, and / or the second duration is lower than the sixth preset threshold, and / or the third duration exceeds the seventh preset threshold;

[0100] S114: it is concluded that there is sleep deprivation in a day.

[0101] In the above embodiment, the physiological data comprises heart rate, respiratory rate and body movement amplitude and frequency. According to the heart rate, respiratory rate and body movement amplitude and frequency, it is judged whether the prisoner is in light sleep state, deep sleep state or sleep wake state.

[0102] Then the first duration of the light sleep state, the second duration of the deep sleep state and the third duration of the sleep wake state are recorded.

[0103] The human body generally gets sufficient rest in deep sleep state, and the human body will be damaged if the duration of light sleep state is too long. If the first duration exceeds the fifth preset threshold, it is determined that the prisoner has sleep deficiency in a day; or if the second duration is lower than the sixth preset threshold, it is determined that the prisoner has sleep deficiency in a day; or if the third duration is lower than the seventh preset threshold, it is determined that the prisoner has sleep deficiency in a day.

[0104] In an embodiment, the collected data further includes monitoring data, and after the step S1 of acquiring the collected data of the plurality of prison bracelets, the method further includes:

[0105] S121: recording the duration of conversation between each person and the prison bracelet wearer according to the monitoring data;

[0106] S122: if the duration of conversation between the converser and the prison bracelet wearer exceeds an eighth preset threshold;

[0107] S123: marking the converser as an intimate of the prison bracelet wearer;

[0108] S124: if the prison bracelet wearer has an abnormal situation, directly locking the intimate.

[0109] In the above embodiment, the relationship intimacy between prisoners is recognized by the prison bracelet. The identity of the person who has a conversation with the prison bracelet wearer is recognized by using the voice recognition technology and the identity library. The identity library stores the identities of the people in the management place. If the identity library does not exist, the person is marked and stored. The number and time of conversations with the current prison bracelet wearer are recorded, and if the number and time of conversations reach the eighth preset threshold, the person is marked as an intimate of the prison bracelet wearer. If the current bracelet wearer has a psychological problem, the intimate can be directly locked, and the correction staff can more effectively help the prison bracelet wearer solve the psychological problem through the intimate.

[0110] In an embodiment, the warning includes sending a warning message.

[0111] In the above embodiment, if it is determined that there is a fight, a warning is given. The operation of the warning includes sending the location of the current plurality of prison bracelets to the management system, and the management system sends the warning message to the terminal of the closest correction staff, so that the correction staff can stop the fight as soon as possible.

[0112] The application also provides a warning device based on a prison bracelet, which includes:

[0113] An acquisition module 10 is configured to acquire an indoor map of a room where a plurality of prison bracelets are located, and acquire acquisition data of the plurality of prison bracelets, wherein the acquisition data at least includes physiological data and signal strength data of a Bluetooth device connected with the prison bracelet;

[0114] A calculation module 20 is configured to calculate first position coordinates of the plurality of prison bracelets according to the signal strength data of the Bluetooth device connected with the prison bracelet;

[0115] A prison bracelet map forming module 30 is configured to add the plurality of first position coordinates to the indoor map correspondingly to form a prison bracelet map;

[0116] A connection module 40 is configured to connect the plurality of first position coordinates in the prison bracelet map into a graph;

[0117] A regular graph judging module 50 is configured to judge whether the graph is a regular graph;

[0118] A first preset threshold judging module 60 is configured to judge whether the physiological data exceeds a first preset threshold if the judgment result of the regular graph judging module 50 is no;

[0119] A warning module 70 is configured to perform a warning if the judgment result of the first preset threshold judging module 60 is yes.

[0120] Reference Figure 3 In the embodiments of the present application, a computer device is also provided, which can be a server. The computer device comprises a processor, a memory, a network interface and a database connected through a system bus. The processor of the computer device is configured to provide calculation and control capabilities. The memory of the computer device comprises a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium. The database of the computer device is configured to store physiological data, monitoring data and the like. The network interface of the computer device is configured to communicate with an external terminal through a network connection. The computer program is executed by the processor to implement the prison bracelet-based warning method of any of the above embodiments

[0121] The embodiments of the present application also provide a computer readable storage medium, which stores a computer program. The computer program is executed by the processor to implement the prison bracelet-based warning method of any of the above embodiments

[0122] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiment methods can be included. Any reference to memory, storage, databases, or other media in this application and in examples provided herein, unless specifically stated otherwise, can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM can be available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0123] It should be noted that in this document, the terms "comprising", "including", or any other variant thereof are intended to cover non-exclusive inclusions, so that processes, devices, articles, or methods that include a series of elements not only include those elements, but also include other elements not explicitly listed, or include elements inherent to such processes, devices, articles, or methods. Without more limitations, the element defined by the statement "comprising a" does not exclude the presence of other identical elements in the process, device, article, or method that includes the element.

[0124] The above description is only the preferred embodiment of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation, or direct or indirect application in other related technical fields, based on the content of the specification and drawings of the present application, are also included in the patent protection scope of the present application.

Claims

1. A prison bracelet-based early warning method, characterized in that, The method comprises the following steps: obtaining an indoor map of a room where a plurality of prison bracelets are located, and obtaining collection data of the plurality of prison bracelets, wherein the collection data at least includes physiological data and signal strength data of a Bluetooth device connected with the prison bracelet; calculating first position coordinates of the plurality of prison bracelets according to the signal strength data of the Bluetooth device connected with the prison bracelet; adding the plurality of first position coordinates to the indoor map to form a prison bracelet map; connecting the plurality of first position coordinates in the prison bracelet map into a pattern; judging whether the pattern is a regular pattern, if the pattern is a regular pattern, it indicates that the positional relationship between a plurality of prisoners presents regularity; if not, judging whether the physiological data exceeds a first preset threshold; if the physiological data exceeds the first preset threshold, a warning is given; the collection data further includes monitoring data, after the step of obtaining the collection data of the plurality of prison bracelets, comprising: based on voice recognition technology, using an identity library to identify the identity of a conversationalist who has a conversation with a prison bracelet wearer; wherein the identity library stores the identities of people in a supervised place; if the identity library does not exist the identity of the conversationalist, the corresponding conversationalist is marked and stored; according to the monitoring data, recording the duration of each person's conversation with the prison bracelet wearer; if the duration of the conversation between the conversationalist and the prison bracelet wearer exceeds an eighth preset threshold; the conversationalist is marked as an intimate of the prison bracelet wearer; if the prison bracelet wearer has an abnormal situation, the intimate is directly locked.

2. The prison bracelet based alert method of claim 1, wherein, The step of calculating the first position coordinates of the plurality of prison bracelets according to the signal strength data of the Bluetooth device connected with the prison bracelet comprises: calculating the distance between each Bluetooth device and the prison bracelet according to the signal strength data; obtaining the second position coordinates of each Bluetooth device; calculating the first position coordinates of the prison bracelet according to the second position coordinates of each Bluetooth device and the distance between each Bluetooth device and the prison bracelet.

3. The prison bracelet based alert method of claim 2, wherein, After the step of adding the plurality of first position coordinates to the indoor map to form a prison bracelet map, comprising: inputting the prison bracelet map and the physiological data into a neural network model to calculate the probability value of the prison bracelet wearer fighting, wherein the neural network model is trained by a training set; judging whether the probability value exceeds a second preset threshold; if yes, a warning is given.

4. The prison bracelet based alert method of claim 1, wherein, After the step of obtaining the collection data of the plurality of prison bracelets, comprising: judging whether there is a sleep deficiency within a day according to the physiological data; if yes, calculating the number of days of sleep deficiency; if the number of days exceeds a fourth preset threshold, a warning is given.

5. The prison bracelet based alert method of claim 4, wherein, The step of judging whether there is a sleep deficiency within a day according to the physiological data comprises: judging the sleep state according to the physiological data, wherein the sleep state includes light sleep state, deep sleep state and wake-up state; record a first time length of the light sleep state, a second time length of the deep sleep state, and a third time length of the wake-up state; if the first time length exceeds a fifth preset threshold, and / or the second time length is lower than a sixth preset threshold, and / or the third time length exceeds a seventh preset threshold, it is concluded that sleep deficiency occurs within a day.

6. The prison bracelet based alert method of claim 1, wherein, The early warning includes sending early warning information.

7. A prison bracelet-based early warning device for performing the method of any one of claims 1-6, characterized by, Comprise: an acquisition module, configured to acquire an indoor map of a room where a plurality of prison bracelets are located, and acquire collection data of the plurality of prison bracelets, wherein the collection data at least includes physiological data and signal strength data of a Bluetooth device connected with the prison bracelet; a calculation module, configured to calculate first position coordinates of the plurality of prison bracelets according to the signal strength data of the Bluetooth device connected with the prison bracelet; a prison bracelet map forming module, configured to add the plurality of first position coordinates to the indoor map correspondingly to form a prison bracelet map; a connection module, configured to connect the plurality of first position coordinates in the prison bracelet map into a pattern; a regular pattern judging module, configured to judge whether the pattern is a regular pattern; a first preset threshold judging module, configured to judge whether the physiological data exceeds a first preset threshold if the pattern is not the regular pattern; an early warning module, configured to perform early warning if the physiological data exceeds the first preset threshold.

8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that, The processor executes the computer program to realize the steps of the method in any one of claims 1 to 6.

9. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to realize the steps of the method in any one of claims 1 to 6.

Images