Special group monitoring device and method

Abstract

The invention provides a special group monitoring device and method. The device comprises a motion module, a positioning module, a physiology module, a data transmission module, a data storage module, a data processing module and an alarm module which are in communication connection. The motion module is used for monitoring motion data of a prisoner; the positioning module is used for acquiring position information of a prisoner; the physiological module is used for monitoring physiological data of a prisoner; the data processing module is used for determining early warning information based on the motion data, the position information and the physiological data; and the alarm module is used for receiving the early warning information and giving an alarm to a worker. The method comprises the following steps: monitoring motion data of a prisoner; acquiring position information of a prisoner; monitoring physiological data of a prisoner; determining early warning information based on the motion data, the position information and the physiological data; and giving an alarm to a worker based on the early warning information. The method can be realized through a monitoring device of a special group.

Description

Technical Field

[0001] The present invention relates to the field of intelligent terminal technology, and in particular to a monitoring device and method for a special group. Background Art

[0002] Special groups, especially criminals, are highly harmful and difficult to manage, so it is necessary to continuously strengthen service management and prevent accidents. Timely capture and early warning of various abnormal behaviors of criminals in prisons is one of the important security supervision tasks of prisons.

[0003] In view of this, CN104122842B discloses an intelligent monitoring method and system for prison events. This method installs a fixed RFID positioning base station in the prison to analyze the radio frequency signals emitted by tags with unique identification codes worn by people entering the monitoring area. When the behavior characteristics of prisoners are abnormal, the system automatically activates the alarm plan, effectively preventing the occurrence of emergencies. However, it only analyzes the people in the monitoring area, which is relatively narrow.

[0004] Therefore, it is necessary to provide a monitoring method and device for special groups. By monitoring multiple data information of prisoners and providing early warning of prisoners' behavior, it is possible to efficiently judge the occurrence of abnormal events such as conflicts and feigning illness, thereby improving the prison's monitoring capabilities and management efficiency. Summary of the invention

[0005] The invention includes a monitoring device for a special group, the device including: a motion module, a positioning module, a physiological module, a data transmission module, a data storage module, a data processing module and an alarm module connected in communication; the motion module is used to monitor the motion data of at least one prisoner, and transmit the motion data to the data storage module through the data transmission module, the motion data including motion speed and acceleration; the positioning module is used to obtain the position information of the at least one prisoner, and transmit the position information to the data storage module through the data transmission module; the physiological module is used to monitor the physiological data of the at least one prisoner, and transmit the physiological data to the data storage module through the data transmission module; the data processing module is used to determine early warning information based on at least one of the motion data, the position information and the physiological data; the at least one prisoner includes at least one sick prisoner, the early warning information includes a first early warning, and the data processing module is further used to: based on The position information of the at least one sick prisoner is used to determine whether the at least one sick prisoner is alone; the motion characteristics of the at least one sick prisoner are extracted, and the motion characteristics include solitary motion characteristics and non-alone motion characteristics; based on the motion characteristics, the suspicion level of the at least one sick prisoner is determined; the data processing module is further used to: count the solitary motion feature vector and non-alone motion feature vector of the at least one sick prisoner to determine a first difference; extract the reference feature vector of the at least one sick prisoner in a rest scene, and determine the second difference based on the reference feature vector and the solitary motion feature vector; count the solitary physiological data and historical normal physiological data of the at least one sick prisoner to determine a third difference; determine the suspicion level based on the first difference, the second difference and the third difference; in response to the suspicion level meeting the first preset condition, issue the first warning, and the first warning is related to feigning illness; the alarm module is used to receive the warning information from the data processing module and alarm the staff.

[0006] The invention content includes a monitoring method for a special group, the method comprising: monitoring the motion data of at least one prisoner, the motion data including motion speed and acceleration; obtaining the position information of the at least one prisoner; monitoring the physiological data of the at least one prisoner; determining early warning information based on at least one of the motion data, the position information and the physiological data; the at least one prisoner includes at least one sick prisoner, the early warning information includes a first early warning, the early warning information determined based on at least one of the motion data, the position information and the physiological data includes: judging whether the at least one sick prisoner is alone based on the position information of the at least one sick prisoner; extracting the motion characteristics of the at least one sick prisoner, the motion characteristics including solitary motion characteristics and non-alone motion characteristics ; Based on the motion characteristics, determining the degree of suspicion of the at least one sick prisoner; the determination of the degree of suspicion of the at least one sick prisoner based on the motion characteristics includes: determining a first difference by counting the solitary motion feature vector and the non-solitary motion feature vector of the at least one sick prisoner; extracting a reference feature vector of the at least one sick prisoner in a resting scene, and determining a second difference based on the reference feature vector and the solitary motion feature vector; determining a third difference by counting the solitary physiological data and historical normal physiological data of the at least one sick prisoner; determining the degree of suspicion based on the first difference, the second difference and the third difference; in response to the degree of suspicion satisfying a first preset condition, issuing a first warning, the first warning being related to feigning illness; alerting staff based on the warning information.

[0007] The invention content includes a monitoring device for a special group, which includes at least one processor and at least one memory; the at least one memory is used to store computer instructions; the at least one processor is used to execute at least part of the computer instructions to implement a monitoring method for a special group.

[0008] Beneficial effects: The monitoring device for special groups built through multiple communication-connected modules implements the monitoring of special groups, realizes the comprehensive monitoring of multiple data information of prisoners, makes the behavioral warning of prisoners more accurate, and improves the monitoring ability and management efficiency of prisons. The suspicious degree of sick prisoners' feigning illness is determined by the movement characteristics of sick prisoners when they are alone and not alone, which is conducive to accurately judging whether there is a possibility and the size of the possibility of sick prisoners feigning illness, and then when the suspicious degree reaches the conditions, timely warning is issued, which is conducive to accurate and efficient monitoring of sick prisoners. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0010] Figure 1 is an exemplary module diagram of a monitoring device for a special group according to some embodiments of this specification;

[0011] Figure 2 is an exemplary flow chart of a monitoring method for a special group according to some embodiments of this specification;

[0012] Figure 3 This is an exemplary flow chart of issuing a second warning according to some embodiments of this specification. DETAILED DESCRIPTION

[0013] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0014] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0015] Unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0016] Flowcharts are used in this specification to illustrate the operations performed by the system according to the embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed precisely in order. Instead, the steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0017] The internal environment of the prison is extremely complex, and the high degree of harm and management difficulty of criminals make the difficulty of security management work high. With the advent of the Internet of Things and big data era, prison management is moving towards intelligent management. CN104122842B only uses RFID, that is, radio frequency identification technology, to analyze the radio frequency signals emitted by RFID tags worn by people entering the monitoring area. When the behavioral characteristics of prisoners are abnormal, the system automatically starts the alarm plan and only analyzes the people in the monitoring area, which has narrow restrictions. Therefore, in some embodiments of this specification, monitoring multiple data information of prisoners (such as the location information, movement data and / or physiological data of prisoners, etc.) and warning the prisoners' behavior can effectively prevent the occurrence of abnormal events such as conflicts and feigning illness, and improve the monitoring capabilities and management efficiency of prisons.

[0018] Figure 1 It is an exemplary module diagram of a monitoring device for a special group according to some embodiments of the present specification.

[0019] In some embodiments, the monitoring device 100 for a special group can be used to perform a monitoring method for a special group.

[0020] like Figure 1 As shown, the monitoring device 100 for a special group may include a motion module 110, a positioning module 120, a physiological module 130, a data transmission module 140, a data storage module 150, a data processing module 160 and an alarm module 170 that are communicatively connected.

[0021] The motion module 110 may refer to a module for monitoring the motion data of the prisoner. In some embodiments, the motion data is transmitted to the data storage module 150 via the data transmission module 140, and the motion data includes motion speed and acceleration. In some embodiments, the motion module may be distributed.

[0022] Distributed can mean that a prisoner wears a monitoring device containing a motion module on multiple parts of his body.

[0023] Distributed motion modules can monitor the motion data of multiple parts of the prisoner's body, avoiding the judgment errors caused by a single motion module, which is conducive to improving the accuracy of monitoring.

[0024] The positioning module 120 may refer to a module for obtaining the location information of the prisoner. In some embodiments, the location information is transmitted to the data storage module 150 via the data transmission module 140 .

[0025] The physiological module 130 may refer to a module for monitoring physiological data of a prisoner. In some embodiments, the physiological data is transmitted to the data storage module 150 via the data transmission module 140 .

[0026] The data transmission module 140 may refer to a module for transmitting relevant data information. In some embodiments, the data transmission module 140 is in communication connection with the motion module 110 , the positioning module 120 , the physiological module 130 , the data storage module 150 , and the data processing module 160 .

[0027] The data storage module 150 may refer to a module for storing relevant data information. In some embodiments, the data storage module 150 receives and stores the relevant data information transmitted by the data transmission module 140.

[0028] The data processing module 160 may refer to a module for processing relevant data generated during the monitoring of a special group. In some embodiments, the data processing module 160 receives data from the data transmission module 140 and transmits the data to the alarm module 170.

[0029] In some embodiments, the data processing module 160 may be configured to determine warning information based on at least one of motion data, location information, and physiological data.

[0030] In some embodiments, at least one prisoner includes at least one sick prisoner, and the warning information includes a first warning. The data processing module 160 can be further used to determine whether the at least one sick prisoner is alone based on the location information of the at least one sick prisoner; extract the motion characteristics of the at least one sick prisoner; determine the degree of suspicion of the at least one sick prisoner based on the motion characteristics; and issue a first warning in response to the degree of suspicion satisfying a first preset condition, the first warning being related to feigning illness.

[0031] In some embodiments, the data processing module 160 can be further used to count the solitary movement feature vector and non-solitary movement feature vector of at least one sick prisoner to determine a first difference; extract a reference feature vector of at least one sick prisoner in a resting scene, and determine a second difference based on the reference feature vector and the solitary movement feature vector; count the solitary physiological data and historical normal physiological data of at least one sick prisoner to determine a third difference; and determine the degree of suspicion based on the first difference, the second difference and the third difference.

[0032] In some embodiments, the warning information may also include a second warning, and the data processing module 160 may be further used to extract the motion characteristics of at least one prisoner based on the motion data in response to the motion data satisfying a second preset condition; determine the suspicious prisoner based on the motion characteristics; and issue a second warning based on the location information and motion characteristics of each suspicious prisoner in a preset time period.

[0033] In some embodiments, the data processing module 160 may be further configured to compare a current motion feature vector of at least one prisoner with a reference feature vector; and determine a suspected prisoner in response to the similarity between the current motion feature vector and the reference feature vector being lower than a motion threshold.

[0034] In some embodiments, the data processing module 160 can be further used to determine the target prisoner based on the location information of each suspicious prisoner in a preset time period; determine the severity of the conflict event based on the movement characteristics of the target prisoner; and issue a second warning in response to the severity of the conflict event meeting a third preset condition.

[0035] The alarm module 170 may refer to a module for alarming a special group of abnormal monitoring conditions. In some embodiments, the alarm module 170 is used to receive early warning information from the data processing module 160 and alarm the staff.

[0036] For more information about the various modules of the monitoring device for special groups, please refer to Figure 2 , Figure 3 and its related description.

[0037] In some embodiments of the present specification, a monitoring device for special groups constructed through multiple communication-connected modules implements monitoring of special groups, realizes comprehensive monitoring of multiple data information of prisoners, makes behavioral warnings for prisoners more accurate, and improves the monitoring capabilities and management efficiency of prisons.

[0038] It should be noted that the above description of a monitoring device for a special group and its internal modules is only for the convenience of description and cannot limit this specification to the scope of the embodiments. It is understandable that for those skilled in the art, after understanding the principle of the device, it is possible to arbitrarily combine the modules or form a sub-device to connect with other modules without deviating from this principle. In some embodiments, Figure 1 The motion module 110, positioning module 120, physiological module 130, data transmission module 140, data storage module 150, data processing module 160 and alarm module 170 disclosed in the specification can be different modules in one device, or one module can realize the functions of two or more modules mentioned above. For example, each module can share a storage module, or each module can have its own storage module. Such variations are all within the protection scope of this specification.

[0039] Figure 2 It is an exemplary flow chart of a monitoring method for a special group according to some embodiments of this specification. In some embodiments, process 200 can be executed by a monitoring device for a special group.

[0040] like Figure 2 As shown, the process 200 includes steps 210 to 250 .

[0041] Step 210, monitoring movement data of at least one prisoner.

[0042] The prisoner may refer to a person in custody who has committed a crime. At least one prisoner may be a prisoner wearing a monitoring device. The monitoring device may include sensors for monitoring speed and acceleration, such as a speed sensor, an accelerometer, and the like.

[0043] The motion data may refer to data related to the prisoner's motion. The motion data may include the prisoner's overall motion data and the motion data of the location where the monitoring device is worn. In some embodiments, the motion data may include motion speed and acceleration. The motion speed and acceleration may reflect the size and intensity of the prisoner's motion, etc.

[0044] In some embodiments, the prisoner's motion data may be acquired in a variety of ways, for example, by direct monitoring and acquisition by related equipment of the motion module (such as a speed sensor, an accelerometer, etc.).

[0045] Step 220, obtaining location information of at least one prisoner.

[0046] The location information may refer to relevant information that can be used to indicate the location of the prisoner, such as longitude and latitude coordinates.

[0047] In some embodiments, the location information of at least one prisoner may be obtained in a variety of ways, such as by directly locating and obtaining it through a device related to the positioning module (such as a GPS locator).

[0048] Step 230, monitoring physiological data of at least one prisoner.

[0049] Physiological data may refer to physiological parameter information of at least one prisoner. For example, the physiological data may include at least one of the heart rate, blood oxygen saturation, hypoxia index, blood circulation index, arrhythmia index, cardiopulmonary index, respiratory frequency and / or respiratory rate of at least one prisoner.

[0050] In some embodiments, the physiological data of at least one prisoner can be obtained in a variety of ways, for example, directly monitored and obtained by relevant equipment of the physiological module (such as a physiological parameter detector, etc.).

[0051] Step 240, determining warning information based on at least one of the motion data, position information and physiological data.

[0052] Early warning information may refer to information on early warning of prisoner behavior, health abnormalities, etc.

[0053] In some embodiments, the warning information may include a first warning and a second warning. For more information about the first warning and the second warning, please refer to the following and Figure 3 Related description.

[0054] In some embodiments, the data processing module can determine the warning information in a variety of ways based on at least one of the motion data, position information, and physiological data. For example, the data processing module can determine the warning information by looking up the table based on the motion data, position information, and physiological data, based on a first preset relationship table including the correspondence between the motion data, position information, physiological data, and the warning information.

[0055] In some embodiments, the at least one prisoner includes at least one sick prisoner, and the warning information includes a first warning. The data processing module can determine whether the at least one sick prisoner is alone based on the location information of the at least one sick prisoner; extract the motion characteristics of the at least one sick prisoner; determine the degree of suspicion of the at least one sick prisoner based on the motion characteristics; and issue a first warning in response to the degree of suspicion meeting a first preset condition.

[0056] Sick prisoners may refer to prisoners who are on sick leave.

[0057] In some embodiments, the first warning may be related to malingering. The first warning may refer to a warning that at least one sick prisoner is suspected of malingering. The first warning may include the sick prisoner number, the degree of suspicion, etc.

[0058] In some embodiments, the data processing module can determine whether there are other prisoners or management personnel within the preset range of the sick prisoner based on the location information of the sick prisoner. If not, the sick prisoner is considered to be alone; otherwise, the sick prisoner is considered not to be alone. The preset range of the sick prisoner can be a geographical range with a preset distance from the location of the sick prisoner.

[0059] In some embodiments, the value of the preset range of patients may be a system default value, or may be adjusted according to different situations.

[0060] Movement characteristics may refer to characteristics that characterize the movement of the prisoner.

[0061] In some embodiments, the motion characteristics may include velocity characteristics and acceleration characteristics.

[0062] Speed ​​features refer to features that can characterize the speed of the prisoner's movement. For example, speed features may include speed extremes, the number of speed direction changes, and the time that the speed exceeds a threshold.

[0063] The speed range refers to the difference between the maximum speed and the minimum speed within a period of time.

[0064] The number of speed direction changes may refer to the number of points at which the speed direction changes within a period of time. In some embodiments, the number of speed direction changes may be used to characterize the possibility of a conflict event, the severity of the conflict event, etc. The more speed direction changes, the greater the possibility of a conflict event, and the more severe the conflict event may be.

[0065] The speed exceeding threshold time may refer to the sum of the time periods in which the speed value is greater than the speed threshold within a period of time. The period of time may refer to a historical time period from the current time point, and the speed threshold may refer to the preset maximum speed of the prisoner under normal conditions. In some embodiments, the speed exceeding threshold time may be used to characterize whether the prisoner's current movement is abnormal. The longer the speed exceeding threshold time, the greater the possibility that the prisoner's current movement is abnormal.

[0066] Acceleration characteristics refer to characteristics that can characterize the acceleration of the prisoner's movement. For example, acceleration characteristics may include acceleration duration, acceleration exceeding threshold time, etc.

[0067] The acceleration duration may refer to the sum of the durations of the periods in which the acceleration value is greater than 0. In some embodiments, the presence of acceleration represents the presence of force, and the acceleration duration may be used to characterize the possibility of a conflict event and the severity of the conflict event. The longer the acceleration duration, the greater the possibility of a conflict event and the higher the severity of the conflict event.

[0068] The acceleration exceeding threshold time may refer to the total duration of the period in which the acceleration value is greater than the acceleration threshold value within a period of time. The acceleration threshold value may refer to the preset maximum value of the acceleration of the prisoner under normal conditions. In some embodiments, the acceleration exceeding threshold time may be used to characterize the severity of the conflict event. The longer the acceleration exceeding threshold time, the higher the severity of the conflict event.

[0069] In some embodiments of the present specification, velocity characteristics and acceleration characteristics are used to efficiently determine the possibility of a prisoner having a conflict, the severity of the conflict, and whether the prisoner's current movement is abnormal, thereby improving monitoring efficiency.

[0070] In some embodiments, in response to the motion module being distributed, the motion characteristics may include motion characteristics of each wearing position, and each set of motion characteristics may include speed characteristics and acceleration characteristics. For more information about distribution, see Figure 1 and its related description.

[0071] The wearing position may refer to the body part where each monitoring device is worn. For example, the wearing position may include the hands, feet, etc. of the prisoner.

[0072] For example, if a prisoner wears a monitoring device with a motion module on his hands and feet respectively, the prisoner's motion characteristics may include two groups of sub-motion characteristics: hand motion characteristics and foot motion characteristics. The hand motion characteristics may include hand speed characteristics and hand acceleration characteristics, and the foot motion characteristics may include foot speed characteristics and foot acceleration characteristics.

[0073] In some embodiments of the present specification, distributed motion modules can be used to avoid misjudgment caused by a single motion module, which is beneficial to improving the accuracy of monitoring.

[0074] In some embodiments, the motion characteristics may also include solitary motion characteristics and non-solo motion characteristics. The solitary motion characteristics may refer to the motion characteristics of the patient when he is alone. The solitary motion characteristics may include speed characteristics and acceleration characteristics when he is alone.

[0075] The non-alone motion characteristics may refer to the motion characteristics of the patient when he is not alone. The non-alone motion characteristics may include speed characteristics and acceleration characteristics when he is not alone.

[0076] In some embodiments, the data processing module can extract the motion characteristics of the patient in a variety of ways. For example, the data processing module can obtain the motion characteristics of the patient in a statistical calculation based on the motion data.

[0077] The degree of suspicion refers to the degree to which the suspect may have suspicious behavior (such as feigning illness, etc.). In some embodiments, the degree of suspicion can be represented by any value in the range of 0 to 10.

[0078] In some embodiments, the data processing module may determine the degree of suspicion of at least one criminal based on the motion features in a variety of ways. For example, the data processing module may determine the degree of suspicion of the criminal based on the motion features by looking up a second preset relationship table including a correspondence between the motion features and the degree of suspicion of the criminal.

[0079] In some embodiments, the data processing module can count the solitary movement feature vector and non-solitary movement feature vector of at least one sick prisoner to determine a first difference; extract a reference feature vector of at least one sick prisoner in a resting scene, and determine a second difference based on the reference feature vector and the solitary movement feature vector; count the solitary physiological data and historical normal physiological data of at least one sick prisoner to determine a third difference; and determine the degree of suspicion based on the first difference, the second difference and the third difference.

[0080] A motion feature vector may refer to a vector composed of motion features, for example, a motion feature vector M=(m1, m2, m3, m4, m5), wherein m1, m2, m3, m4, and m5 are different motion features such as speed extreme difference, number of speed direction changes, speed exceeding threshold time, acceleration duration, and acceleration exceeding threshold time.

[0081] The solitary motion feature vector may refer to a vector composed of solitary motion features, for example, the solitary motion feature vector M1=(m 11 , m 21 , m 31 , m 41 , m 51), where m 11 、m 21 、m 31 、m 41 、m 51 They are the values ​​of different motion characteristics when being alone.

[0082] The non-lonely motion feature vector may refer to a vector composed of non-lonely motion features, for example, the non-lonely motion feature vector M2=(m 12 , m 22 , m 32 , m 42 , m 52 ), where m 12 、m 22 、m 32 、m 42 、m 52 are the values ​​of different motion features when not alone, and the elements at the same position in M1 and M2 represent the same motion features (e.g., m 11 、m 12 is the speed difference between being alone and not alone).

[0083] The first difference may refer to the difference between the solitary motion feature vector and the non-solitary motion feature vector. In some embodiments, the larger the first difference, the higher the suspicious degree.

[0084] In some embodiments, the data processing module can determine the first difference in a variety of ways, such as by counting the solitary motion feature vectors and the non-solitary motion feature vectors of the criminal, calculating the difference between each motion feature in the two vectors, and determining the sum of the differences as the first difference.

[0085] In some embodiments, in response to the motion module being distributed, the first difference may include a weighted sum of differences between the solitary motion feature vector and the non-solitary motion feature vector of different wearing positions of at least one patient, to determine the difference.

[0086] In some embodiments, the weights of different wearing positions may be related to the physical characteristics and labor reform activity characteristics of at least one of the prisoners.

[0087] Physical characteristics refer to the characteristics that can reflect the prisoner's physical shape, such as upper body and lower body fat percentage.

[0088] The characteristics of labor reform activities refer to the relevant characteristics that can reflect the process of the prisoner's labor reform activities. For example, the time and speed of hand labor, the time and speed of foot labor, etc. For example, when the prisoner's hand labor is more (e.g., long time, fast speed) and the foot labor is less (e.g., short time, slow speed) in the labor reform activities, the prisoner's hands may not be able to lift up due to fatigue, but the feet are normal. In this case, it should not be judged that he is pretending to be sick based only on the hand movement characteristics, and the hand weight needs to be appropriately reduced. Then the weight of the difference between the solitary movement feature vector and the non-solitary movement feature vector corresponding to the hand is smaller, and the weight of the difference corresponding to the foot is larger.

[0089] In some implementations, the data processing module can determine the weights of different wearing positions in a variety of ways. For example, the data processing module can determine the hand weight by looking up the table based on the third preset relationship table including the correspondence between body shape features, labor reform activity features and hand weights, and correspondingly, the foot weight = 1-hand weight.

[0090] In some embodiments, in response to the fact that the motion module is distributed, for the patient, the difference of the same motion feature at different wearing positions is calculated for the solitary motion feature vector and the non-solitary motion feature vector, and a first weighted summation is performed based on the weights of different wearing positions, and then a second weighted summation is performed on the differences of different motion features after the first weighted summation based on the preset weights of different motion features to obtain the first difference. The preset weights of different motion features can be preset in advance by a person skilled in the art or set by the system by default.

[0091] For example, for the same prisoner, when the prisoner is alone, the hand movement feature vector and foot movement feature vector are A1=(a 11 , a 21 , a 31 , a 41 , a 51 )、B1=(b 11 , b 21 , b 31 , b 41 , b 51 ), the hand movement feature vector and foot movement feature vector of the patient when he is not alone are A2=(a 12 , a 22 , a 32 , a 42 , a 52 )、B2=(b 12 , b 22 , b 32 , b 42 , b 52 ); calculate the differences in the various hand movement characteristics when alone and when not alone: , , , then the difference in hand motion characteristics is A=(a1,a2,a3,a4,a5), where a1, a2, a3, a4, a5 are the different hand motion characteristics, such as the speed extreme difference, the number of speed direction changes, the speed exceeding threshold time, the acceleration duration, and the difference between the acceleration exceeding threshold time.

[0092] Similarly, calculate the differences in the movement characteristics of the feet when alone and when not alone: , , , then the difference in foot motion features is B=(b1,b2,b3,b4,b5), where b1,b2,b3,b4,b5 are the differences between different foot motion features. The elements at the same position of each motion feature vector above represent the values ​​of the same motion feature in different wearing positions and / or whether it is alone (such as a 11 、a 12 , b 11 , b 12 represents the speed difference value).

[0093] Based on the physical characteristics and labor reform activity characteristics of this prisoner, the hand weight n1 is determined by looking up the table, and the corresponding foot weight is n2, and ; Perform the first weighted summation on the difference between the same movement features of the hands and feet when they are alone and when they are not alone: , , , then the difference of different motion features C = (c1, c2, c3, c4, c5); preset 5 different motion features corresponding to each element in the same position of A and B, the corresponding weights are k1, k2, k3, k4, k5, and the differences of different motion features are weighted summed for the second time based on this preset weight: , and get the first difference.

[0094] In some embodiments of the present specification, the differences in body shape and labor reform activity characteristics of different sick prisoners correspond to different movement characteristics when pretending to be sick, which is conducive to accurately determining the weights of different wearing positions, thereby making the determination of the first difference more accurate and reasonable.

[0095] The reference feature vector may refer to a motion feature vector in a preset scene. In some embodiments, the preset scene may include normal labor, study, eating, resting, etc. For each preset scene, based on the prisoner's historical motion speed and historical acceleration in the preset scene, the historical motion feature vector is counted; the historical motion feature vector is used as the reference feature vector of the prisoner in the preset scene.

[0096] In some embodiments, under the same preset scenario, the reference feature vectors of different prisoners are different.

[0097] The second difference may refer to the difference between the reference feature vector and the solitary motion feature vector of the prisoner in the resting scene. In some embodiments, the greater the second difference, the higher the degree of suspicion.

[0098] In some embodiments, a reference feature vector of the prisoner in a resting scene is extracted, and the differences in the corresponding different motion features between the prisoner's solitary motion feature vector and the reference feature vector in the resting scene are calculated. Based on the preset weights of the different motion features, the differences in the different motion features are weighted and summed to obtain a second difference.

[0099] For example, the solitary motion feature vector M1 = (m 11 , m 21 , m 31 , m 41 , m 51 ), the reference feature vector M3 in the rest scene = (m 13 , m 23 , m 33 , m 43 , m 53 ), the corresponding differences in different motion characteristics: , , , , , based on the preset weights k1, k2, k3, k4, k5 of different motion features, the differences of different motion features are weighted summed: , and get the second difference.

[0100] The solitary physiological data may refer to the physiological data of the patient when he is alone, for example, the heart rate, blood oxygen saturation, hypoxia index, blood circulation index, arrhythmia index, cardiopulmonary index, respiratory frequency and / or respiratory rate, etc. of the patient when he is alone.

[0101] The historical normal physiological data may refer to the physiological data of the patient under normal conditions (when not sick) in the historical data.

[0102] The third difference may refer to the difference between the isolated physiological data and the historical normal physiological data. In some embodiments, the greater the third difference, the higher the degree of suspicion.

[0103] In some embodiments, multiple physiological data of the patient when he is alone and the corresponding historical normal physiological data are counted, the difference of each data is calculated, and the multiple data differences are summed and averaged to obtain a third difference.

[0104] In some embodiments, the data processing module may perform a weighted summation of the first difference, the second difference, and the third difference, and determine the degree of suspicion based on the sum of the differences in a variety of ways. For example, the data processing module may determine the degree of suspicion based on the sum of the differences by looking up a table based on a fourth preset relationship table including a correspondence between the sum of the differences and the degree of suspicion.

[0105] In some embodiments, the data processing module may determine the weights of the first difference, the second difference, and the third difference in a variety of ways, such as allocating weights according to a preset ratio, wherein the preset ratio may be preset by a person skilled in the art based on historical experience or set by system default.

[0106] In some embodiments, the weights corresponding to the first difference, the second difference, and the third difference are related to historical warning information of at least one patient.

[0107] Historical warning information may refer to warning-related information in historical data, such as the number of warnings, warning frequency, etc. In some embodiments, the more historical warning information there is (such as the more warnings, the higher the warning frequency), the greater the sum of the weights of the first difference and the second difference.

[0108] In some embodiments, the data processing module can determine the weights corresponding to the first difference, the second difference, and the third difference in a variety of ways. For example, the data processing module can search for the patient number based on the fifth preset relationship table including the correspondence between historical warning information and the sum of the weights of the first difference and the second difference, and inquire whether there is historical warning information for the patient. If so, the sum of the weights of the first difference and the second difference is determined by looking up the table. Correspondingly, the weight corresponding to the third difference = 1-the weight of the first difference-the weight of the second difference. Among them, the weights of the first difference and the second difference can be allocated according to the proportion of the first difference and the second difference.

[0109] In some embodiments of the present specification, historical warning information is used to reflect the prisoner's historical attitude. For prisoners with more negative attitudes, it is reasonably suspected that the difference in movement characteristics when alone and when not alone is due to feigning illness, and the sum of the weights of the first difference and the second difference is reasonably increased, which is conducive to determining the accuracy of the degree of suspicion.

[0110] In some embodiments of the present specification, the determined suspicion level is more comprehensive and accurate based on the first difference, the second difference, and the third difference.

[0111] The first preset condition may refer to a condition that the degree of suspicion must meet in order to issue the first warning, for example, the degree of suspicion is greater than a preset suspicion threshold.

[0112] In some embodiments, in response to the suspicion level meeting a first preset condition, the data processing module may issue a first warning, and the first warning may include the prisoner number and the prisoner's suspicion level.

[0113] In some embodiments of the present specification, the degree of suspicion of the sick prisoner's feigning illness is determined by the movement characteristics of the sick prisoner when he is alone and when he is not alone, which is conducive to accurately judging whether there is a possibility that the sick prisoner is feigning illness and the extent of the possibility, and then issuing a warning in time when the suspicion level reaches the conditions, which is conducive to accurate and efficient monitoring of the sick prisoner.

[0114] In some embodiments, the data processing module can determine the suspicious criminal based on the motion characteristics; based on the location information and motion characteristics of the suspicious criminal, issue a second warning. For more information, see Figure 3 and its related description.

[0115] Step 250, alerting staff based on the warning information.

[0116] Staff can refer to the management personnel who supervise prisoners, for example, prison guards.

[0117] In some embodiments, after receiving the early warning information from the data processing module, the alarm module can alert the staff in various ways, such as text alarm, sound alarm, etc.

[0118] In some embodiments of the present specification, based on location information, motion data and / or physiological data, etc., accurate warnings can be issued for prisoners' conflict behaviors, feigning illness, etc., thereby timely and effectively preventing the occurrence of emergencies to a certain extent, thereby improving the monitoring capabilities and management efficiency of prisoners.

[0119] It should be noted that the above description of the process 200 is only for example and illustration, and does not limit the scope of application of this specification. For those skilled in the art, various modifications and changes can be made to the process 200 under the guidance of this specification. However, these modifications and changes are still within the scope of this specification.

[0120] Figure 3 This is an exemplary flow chart of issuing a second warning according to some embodiments of this specification.

[0121] like Figure 3 As shown, the process 300 includes steps 310 to 330 .

[0122] In some embodiments, the second warning is related to a conflict event. The second warning may refer to a warning that a prisoner is suspected of having a conflict event. The second warning may include the number of the suspected prisoner, information about the conflict event, etc.

[0123] A conflict event may refer to a conflicting behavior in which a physical collision occurs, such as a fight, etc. In some embodiments, the occurrence of a conflict event may cause an abnormality in the acceleration characteristics of the prisoner.

[0124] Step 310: In response to the motion data satisfying a second preset condition, extracting at least one motion feature of a prisoner based on the motion data.

[0125] The second preset condition may refer to a preset condition for determining that the acceleration duration is abnormal. In some embodiments, the acceleration duration of the prisoner is continuously counted, and when the difference between the acceleration duration within a period of time and the acceleration duration in the reference feature vector is greater than the first preset threshold, it may refer to that the motion data meets the second preset condition, and all the motion features of the prisoner within a period of time are extracted.

[0126] For more information about motion data, acceleration duration, reference feature vectors, and motion features, see Figure 2 and its related description.

[0127] In some embodiments, the data processing module can extract the prisoner's motion features in a variety of ways. For example, the data processing module can obtain the prisoner's motion features through statistical calculations based on the motion data.

[0128] Step 320, determine the suspected criminal based on the movement characteristics.

[0129] Suspicious prisoners may refer to prisoners who have abnormal behavior and may cause conflicts.

[0130] In some embodiments, the data processing module can determine a suspicious prisoner based on the motion characteristics in a variety of ways. For example, it can determine whether the prisoner's motion characteristics are within a preset range. If they are within the preset range, the prisoner is not a suspicious prisoner. The preset range can refer to the range of the prisoner's motion characteristics under normal conditions. The preset range can be preset in advance by a person skilled in the art or set by system default.

[0131] In some embodiments, the data processing module may compare the current motion feature vector of at least one prisoner with a reference feature vector; and determine a suspicious prisoner in response to the similarity between the current motion feature vector and the reference feature vector being lower than a motion threshold.

[0132] The current motion feature vector may refer to a motion feature vector of the prisoner in a preset scene within the current time period.

[0133] For more information about reference eigenvectors, see Figure 2 and its related description.

[0134] In some embodiments, in response to the motion module being distributed, the reference feature vector of at least one prisoner in each preset scenario may include a reference feature vector for each wearing position. For more information about distribution, preset scenarios, and wearing positions, see Figure 1 and Figure 2 and its related description.

[0135] For example, in a labor scenario, the prisoner's reference feature vector includes two groups of sub-reference feature vectors: a hand reference feature vector and a foot reference feature vector, which correspond to the hand and foot movement feature vectors respectively.

[0136] In some embodiments of the present specification, by using a reference feature vector of at least one wearing position, it is possible to avoid judgment errors caused by a single motion module, which is beneficial to improving the accuracy of identifying suspicious criminals.

[0137] In some embodiments, the data processing module can compare the prison schedule, determine the preset scene in which the prisoner is in the current period, call the prisoner's reference feature vector in the preset scene, compare the prisoner's current motion feature vector with the reference feature vector in the preset scene, and calculate the similarity.

[0138] The similarity may refer to the similarity between the current motion feature vector and the reference feature vector. In some embodiments, the similarity is inversely proportional to the vector distance between the prisoner's current motion feature vector and the reference feature vector.

[0139] In some implementations, in response to the similarity between the prisoner's current motion feature vector and the reference feature vector in the preset scenario being lower than a motion threshold, it is determined that the prisoner may have a conflict event, and the prisoner is determined to be a suspicious prisoner.

[0140] The motion threshold may refer to the minimum value of the similarity between the motion feature vector of the prisoner in a normal state and the reference feature vector.

[0141] In some embodiments, the determination of a suspected criminal may be related to whether there are special events on the day's schedule.

[0142] Special events may refer to non-routine activities, such as special exercises, etc. In some embodiments, special events are not in the preset scenarios.

[0143] Due to the sporadic nature of special events, there is a lack of historical movement data of prisoners, and it is impossible to extract reference feature vectors under special events. Therefore, if there is a special event on the day's schedule, no second warning will be issued for the time period of the special event, that is, it is assumed that no conflict event will occur in this time period, and this time period will be directly ignored.

[0144] In some embodiments of the present invention, the influence of the existence of special events on the judgment of suspicious criminals is taken into account, so that the accuracy of determining the suspicious criminals is higher.

[0145] In some embodiments of the present specification, by comparing the prisoner's current motion feature vector with the reference feature vector to determine whether the similarity is lower than the motion threshold, it is helpful to efficiently determine whether the prisoner is a suspected prisoner.

[0146] Step 330: Issue a second warning based on the location information and movement characteristics of each suspicious criminal in a preset time period.

[0147] The preset period may refer to a current period including the current time point.

[0148] In some embodiments, the data processing module may issue a second warning in a variety of ways. For example, for each suspicious prisoner, based on the location information and motion characteristics of a preset time period, a vector is constructed, and information about the conflict event is determined through vector retrieval, and a second warning is issued (the second warning includes the number of the suspicious prisoner, information about the conflict event, etc.).

[0149] In some embodiments of the present specification, the motion characteristics of the prisoners are extracted when the motion data meets the conditions, thereby quickly and efficiently identifying suspicious prisoners, saving computing resources, and issuing warnings in a timely manner based on the location information and motion characteristics of each suspicious prisoner in a preset time period, which is conducive to improving supervision efficiency and capabilities.

[0150] In some embodiments, the data processing module can determine the target prisoner based on the location information of each suspicious prisoner in a preset time period; determine the severity of the conflict event based on the movement characteristics of the target prisoner; and issue a second warning in response to the severity of the conflict event meeting a third preset condition.

[0151] Target criminals can refer to suspicious persons who may be involved in conflict incidents.

[0152] In some embodiments, the data processing module can obtain the location information of all suspicious prisoners in the current period through the positioning module, and in response to the existence of at least two suspicious prisoners whose location distance is less than the distance threshold, determine the suspicious prisoners whose location distance is less than the distance threshold as the target prisoners. The distance threshold can be a preset extremely small value.

[0153] In some embodiments, the data processing module may obtain the similarities between the current motion feature vectors of multiple target prisoners and the reference feature vectors corresponding thereto, sum the multiple similarities, and determine the severity by looking up the table based on the sum of the similarities based on a sixth preset relationship table including the corresponding relationship between the sum of the similarities and the severity of the conflict event. For more information about the similarity between the current motion feature vector and the reference feature vector, see the relevant description of step 320.

[0154] In some embodiments, the greater the number of target prisoners, the greater the severity of the conflict event.

[0155] In some embodiments, the severity may be related to the difference between the current motion feature vectors and the reference feature vectors of the plurality of target prisoners.

[0156] In some embodiments, the data processing module can obtain the current motion feature vectors and reference feature vectors of multiple target prisoners, and for each target prisoner, calculate the difference between each motion feature in its current motion feature vector and the corresponding motion feature in the reference feature vector; for the differences in the same motion features of different target prisoners, weighted sum is performed according to the weights of different target prisoners, and the sum of the obtained differences is weighted summed again according to the preset weights of different motion features; based on the seventh preset relationship table including the corresponding relationship between the sum of the differences in the same motion features of different target prisoners and the severity of the conflict event, the severity is determined by looking up the table based on the sum of the differences in the motion features of different target prisoners. The data processing module can preset the weights of different target prisoners in advance.

[0157] For example, there are 2 target prisoners. For target prisoner 1, calculate E1=(e 11 , e 21 , e 31 , e 41 , e 51 ) and F1=(f 11 , f 21 , f 31 , f 41 , f 51 ) Differences in the characteristics of each movement: , , , ; For target prisoner 2, calculate E2=(e 12 , e 22 , e 32 , e 42 , e 52 ) and F2 = (f 12 , f 22 , f 32 , f42 , f 52 ) Differences in the characteristics of each movement: , , , , ; E, F represent the current motion feature vector and the reference feature vector respectively. The weight of target prisoner 1 is h1, the weight of target prisoner 2 is h2, and ; For the difference of the same motion features of target prisoners 1 and 2, the first weighted summation is performed according to the weights of target prisoners 1 and 2: , , , , .

[0158] The five different motion features corresponding to the elements at the same position of E and F are preset (such as speed range, number of speed direction changes, speed exceeding threshold time, acceleration duration, acceleration exceeding threshold time), and the corresponding weights are k1, k2, k3, k4, and k5. Based on this preset weight, the differences of different motion features are weighted summed for the second time: = the sum of the differences; based on the sum of the differences, the severity is determined by the seventh preset relationship table.

[0159] In some embodiments, the weight of the target prisoner may be related to the physiological data of the target prisoner. For more information about physiological data, see Figure 2 and its related description.

[0160] In some embodiments, weights are assigned according to the ratio of the physiological data differences of different target prisoners. The greater the difference in physiological data, the greater the weight of the target prisoner. The physiological data difference of the target prisoner may refer to the difference between the current physiological data of the target prisoner and the physiological data under normal historical conditions. For example, there are two target prisoners. The difference between the current physiological data of target prisoner 1 and the physiological data under normal historical conditions is p, and the difference between the current physiological data of target prisoner 2 and the physiological data under normal historical conditions is q. The ratio of the physiological data difference between target prisoner 1 and target prisoner 2 is p:q, then the weight of target prisoner 1 is , the weight of target prisoner 2 is .

[0161] In some embodiments of the present specification, weights are determined by differences in physiological data of target prisoners, so that the severity of the conflict event can be determined more accurately.

[0162] In some embodiments of the present specification, the severity can be determined more accurately by combining the differences between the current motion feature vectors and the reference feature vectors of multiple target prisoners.

[0163] In some embodiments, the severity of the conflict event may also be correlated to the physiological data of the target criminal.

[0164] In some embodiments, the data processing module can calculate the difference between the current physiological data of different target prisoners and the historical physiological data under normal historical conditions, determine the sum of the differences in the physiological data of different target prisoners; preset the weights corresponding to the motion characteristics and physiological data of different target prisoners; based on the preset weights, perform weighted summation on the differences in motion characteristics (the sum of the differences in motion characteristics of different target prisoners) and the differences in physiological data (the sum of the differences in physiological data of different target prisoners) to determine the sum of the differences. The seventh preset relationship table may include the corresponding relationship between the sum of the differences of different target prisoners and the severity of the conflict event. Based on the sum of the differences of different target prisoners, the severity of the conflict event is determined by looking up the table.

[0165] In some embodiments of the present specification, the severity of the conflict event is associated with the physiological data of the target prisoner, and judging the severity by the abnormality of the physiological data is more accurate and comprehensive.

[0166] The third preset condition may refer to the severity of the conflict event reaching the preset condition for issuing the second warning, for example, the severity of the conflict event is higher than the second preset threshold value.

[0167] In some embodiments, the data processing module may issue a second warning in response to the severity of the conflict event satisfying a third preset condition, where the second warning includes the target prisoner number, the severity of the conflict event, and the like.

[0168] In some embodiments of the present specification, the location information of each suspicious prisoner in a preset time period can be used to accurately identify the target prisoners who may be involved in the conflict event, and then determine the severity of the conflict event. When the severity reaches the conditions, an early warning is issued in a timely manner, which is conducive to accurate and efficient monitoring of prisoners.

[0169] One of one or more embodiments of the present specification provides a monitoring device for a special group, the device comprising at least one processor and at least one memory; the at least one memory is used to store computer instructions; and the at least one processor is used to execute at least part of the computer instructions to implement a monitoring method for a special group.

[0170] One of one or more embodiments of the present specification provides a computer-readable storage medium, which stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes a monitoring method for a special group.

[0171] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0172] At the same time, this specification uses specific words to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.

[0173] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0174] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A monitoring device for a special group, characterized in that: The device comprises: a motion module, a positioning module, a physiological module, a data transmission module, a data storage module, a data processing module and an alarm module which are in communication connection; The motion module is used to monitor the motion data of at least one prisoner and transmit the motion data to the data storage module through the data transmission module, wherein the motion data includes motion speed and acceleration; The positioning module is used to obtain the location information of the at least one prisoner, and transmit the location information to the data storage module through the data transmission module; The physiological module is used to monitor the physiological data of the at least one prisoner and transmit the physiological data to the data storage module through the data transmission module; The data processing module is used to determine warning information based on at least one of the motion data, the position information and the physiological data; the at least one prisoner includes at least one sick prisoner, the warning information includes a first warning, and the data processing module is further used to: Based on the location information of the at least one sick prisoner, determining whether the at least one sick prisoner is alone; Extracting the movement features of the at least one patient, wherein the movement features include solitary movement features and non-solitary movement features; Based on the motion characteristics, determining the degree of suspicion of the at least one criminal; the data processing module is further used for: Counting the solitary movement feature vector and the non-solitary movement feature vector of the at least one patient to determine a first difference; Extracting a reference feature vector of the at least one sick prisoner in a resting scene, and determining a second difference based on the reference feature vector and the solitary movement feature vector; Counting the physiological data of the at least one sick prisoner when alone and the historical normal physiological data to determine a third difference; determining the degree of suspicion based on the first difference, the second difference, and the third difference; In response to the suspicion level satisfying a first preset condition, issuing the first warning, wherein the first warning is related to malingering; The alarm module is used to receive the early warning information from the data processing module and alert the staff.

2. The monitoring device according to claim 1, characterized in that: The warning information also includes a second warning, and the data processing module is further used for: In response to the motion data satisfying a second preset condition, extracting a motion feature of the at least one prisoner based on the motion data; identifying a suspected criminal based on the movement characteristics; Based on the location information and the movement characteristics of each of the suspicious criminals in a preset time period, the second warning is issued, and the second warning is related to a conflict event.

3. The monitoring device according to claim 2, characterized in that: The data processing module is further used for: Determining a target prisoner based on the location information of each of the suspected prisoners during the preset time period; Determining the severity of the conflict event based on the movement characteristics of the target criminal; In response to the severity of the conflict event satisfying a third preset condition, the second warning is issued.

4. A monitoring method for a special group, characterized in that: The method comprises: monitoring movement data of at least one prisoner, the movement data including movement speed and acceleration; obtaining location information of the at least one prisoner; monitoring physiological data of the at least one inmate; Based on at least one of the motion data, the position information, and the physiological data, early warning information is determined; the at least one prisoner includes at least one sick prisoner, the early warning information includes a first early warning, and the early warning information is determined based on at least one of the motion data, the position information, and the physiological data, including: Based on the location information of the at least one sick prisoner, determining whether the at least one sick prisoner is alone; Extracting the movement features of the at least one patient, wherein the movement features include solitary movement features and non-solitary movement features; Determining the degree of suspicion of the at least one criminal based on the motion characteristics; determining the degree of suspicion of the at least one criminal based on the motion characteristics includes: Counting the solitary movement feature vector and the non-solitary movement feature vector of the at least one patient to determine a first difference; Extracting a reference feature vector of the at least one sick prisoner in a resting scene, and determining a second difference based on the reference feature vector and the solitary movement feature vector; Counting the physiological data of the at least one sick prisoner when alone and the historical normal physiological data to determine a third difference; determining the degree of suspicion based on the first difference, the second difference, and the third difference; In response to the suspicion level satisfying a first preset condition, issuing the first warning, wherein the first warning is related to malingering; Based on the early warning information, an alarm is alerted to the staff.

5. The monitoring method according to claim 4, characterized in that: The warning information further includes a second warning, and the determining of the warning information based on at least one of the motion data, the position information, and the physiological data includes: In response to the motion data satisfying a second preset condition, extracting a motion feature of the at least one prisoner based on the motion data; identifying a suspected criminal based on the movement characteristics; Based on the location information and the movement characteristics of each of the suspicious criminals in a preset time period, the second warning is issued, and the second warning is related to a conflict event.

6. The monitoring method according to claim 5, characterized in that: The issuing of the second warning based on the location information and the movement characteristics of each of the suspicious criminals in a preset time period includes: Determining a target prisoner based on the location information of each of the suspected prisoners during the preset time period; Determining the severity of the conflict event based on the movement characteristics of the target criminal; In response to the severity of the conflict event satisfying a third preset condition, the second warning is issued.

7. A monitoring device for a special group, characterized in that: The apparatus comprises at least one processor and at least one memory; The at least one memory is used to store computer instructions; The at least one processor is used to execute at least part of the computer instructions to implement the monitoring method described in any one of claims 4-6.

Images