Behavior monitoring method, device, electronic device and storage medium

Abstract

The present invention provides a behavior supervision method, device, electronic device and storage medium, the method comprising: determining the behavior state of the target person based on the object image of the target person's work object and / or the target person's voice; and issuing a prompt message based on the behavior state of the target person. The method, device, electronic device and storage medium provided by the present invention determine the behavior state of the target person by applying the object image of the target person's work object and / or the target person's voice, and give a reminder based on the behavior state, thereby realizing automatic behavior supervision of the target person, without the need for the supervisor to participate in the whole process, saving the supervisor's time, and increasing the time for the target person to focus on work / study, and improving the work / study efficiency and work / study quality of the target person.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a behavior monitoring method, device, electronic equipment and storage medium. Background Art

[0002] Primary school students have difficulty concentrating for long periods of time when studying, and often play with erasers or spin pens while doing their homework, which means that their homework usually takes a lot of time to complete.

[0003] At present, in order to enable primary school students to complete their homework better and faster, parents usually choose to supervise their children's study themselves. However, this method not only takes up a lot of parents' time, but primary school students will also deliberately chat with their parents to distract their attention from their studies. The efficiency of homework completion and learning efficiency has not been effectively improved. Summary of the invention

[0004] The present invention provides a behavior supervision method, device, electronic device and storage medium, which are used to solve the defect that the learning efficiency of students in the prior art cannot be effectively improved, and to improve the work / learning efficiency and work / learning quality of target personnel.

[0005] The present invention provides a behavior monitoring method, comprising:

[0006] Determining the behavior state of the target person based on the object image of the target person's work object and / or the target person's voice;

[0007] Based on the behavior status of the target person, a prompt message is issued.

[0008] According to a behavior monitoring method provided by the present invention, the behavior state of the target person is determined based on the object image of the target person's work object and / or the target person's voice, including:

[0009] Performing operation object recognition on the object image to obtain current operation object content;

[0010] Based on the current operation object content and the previous operation object content, the behavior state of the target person is determined, and the previous operation object content is the operation object content before the current operation object content.

[0011] According to a behavior monitoring method provided by the present invention, the behavior state of the target person is determined based on the object image of the target person's work object and / or the target person's voice, including:

[0012] Performing voice classification on the speech of the person to obtain a voice classification result of the target person;

[0013] Based on the speech classification result of the target person, the behavior state of the target person is determined.

[0014] According to a behavior supervision method provided by the present invention, the voice classification of the person's voice to obtain the voice classification result of the target person includes:

[0015] Performing speech recognition on the person's speech to obtain a speech recognition text of the person's speech;

[0016] The speech recognition text is subjected to text classification to obtain a speech classification result of the target person.

[0017] According to a behavior monitoring method provided by the present invention, the behavior state of the target person is determined based on the object image of the target person's work object and / or the target person's voice, including:

[0018] Determine the current behavior of the target person based on the object image and / or the person's voice, and the person image of the target person;

[0019] Based on the current behavior of the target person, the behavior state of the target person is determined.

[0020] According to a behavior monitoring method provided by the present invention, the behavior state of the target person is determined based on the object image of the target person's work object and / or the target person's voice, including:

[0021] Determining a target behavior of the target person based on the historical object image and the historical person voice;

[0022] Based on the target behavior of the target person and the object image or the person's voice, the behavior state of the target person is determined.

[0023] According to a behavior monitoring method provided by the present invention, the step of issuing a prompt message based on the behavior state of the target person includes:

[0024] If the number of times that the target person's behavior status is abnormal within the preset time period exceeds the number threshold, and / or the cumulative duration that the target person's behavior status is abnormal within the preset time period exceeds the duration threshold, the prompt information is issued.

[0025] The present invention also provides a behavior monitoring device, comprising:

[0026] A determination module, configured to determine the behavior state of the target person based on an object image of the target person's work object and / or the target person's voice;

[0027] The prompt module is used to issue prompt information based on the behavior status of the target person.

[0028] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of any of the above-mentioned behavior monitoring methods are implemented.

[0029] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of any of the above-mentioned behavior monitoring methods are implemented.

[0030] The behavior supervision method, device, electronic device and storage medium provided by the present invention determine the behavior status of the target person by applying the object image of the target person's work object and / or the target person's voice, and provide reminders based on the behavior status, thereby realizing automatic behavior supervision of the target person. The supervisor does not need to participate in the whole process, saving the supervisor's time, and increasing the time that the target person can focus on work / study, thereby improving the target person's work / study efficiency and work / study quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0032] Figure 1 It is a flow chart of the behavior monitoring method provided by the present invention;

[0033] Figure 2 It is one of the flow charts of the behavior state determination method provided by the present invention;

[0034] Figure 3 This is the second flow chart of the behavior state determination method provided by the present invention;

[0035] Figure 4 It is a flow chart of the speech classification method provided by the present invention;

[0036] Figure 5 This is the third flow chart of the behavior state determination method provided by the present invention;

[0037] Figure 6 This is the fourth flow chart of the behavior state determination method provided by the present invention;

[0038] Figure 7 It is a structural schematic diagram of the behavior monitoring device provided by the present invention;

[0039] Figure 8 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0040] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0041] An embodiment of the present invention provides a behavior monitoring method. Figure 1 It is one of the flow charts of the behavior supervision method provided by the present invention, such as Figure 1 As shown, the method includes:

[0042] Step 110, determining the behavior state of the target person based on the object image of the target person's work object and / or the target person's voice;

[0043] Step 120: Send a prompt message based on the behavior status of the target person.

[0044] Specifically, the target person is the person who needs to be supervised, such as students, employees, etc. The target person's work object is the object operated by the target person to complete the established tasks in production, learning, etc. For example, if the target person is a student, the work object can be a workbook. For another example, if the target person is an employee, the work object can be a computer document. The object image is an image containing the target person's work object. The image can be an image of the work object directly collected by a camera, scanner or other image acquisition device with a camera function, or it can be an image of the work object after image preprocessing. The embodiment of the present invention does not make specific limitations on this. Personnel voice is the voice data emitted by the target person. The voice data can be obtained through a sound pickup device. The sound pickup device here can be a smart phone, a tablet computer, etc., or a smart appliance such as a speaker, a smart clock, etc. After the sound pickup device obtains the voice data through the microphone array, it can also amplify and reduce the noise of the voice data. The embodiment of the present invention does not make specific limitations on this.

[0045] In order to supervise the work or study of the target person and increase the time that the target person can focus on work or study, the embodiment of the present invention determines the behavior state of the target person according to the object image of the target person's work object, or according to the target person's voice, or according to the object image of the target person's work object and the target person's voice. Here, the behavior state of the target person is used to characterize whether the target person is in a normal working or learning state. For example, if it is determined according to the object image of the target person's work object that the work object of the target person has not changed, it can be determined that the target person is dozing off, distracted, etc., and the behavior state of the target person is abnormal. For another example, if it is determined according to the target person's voice that the target person is chatting, it can be determined that the behavior state of the target person is also abnormal.

[0046] When an object image is applied, the current behavior of the target person may be determined based on the correspondence between the sample object image and each candidate behavior and the object image, and then the behavior state of the target person may be determined based on the current behavior. Alternatively, image recognition may be performed on the object image, and then the behavior state of the target person may be determined based on the recognition result. The embodiment of the present invention does not specifically limit this. When a person's voice is applied, voice recognition may be performed on the person's voice, and then the behavior state of the target person may be determined based on the recognition result.

[0047] After obtaining the behavior state of the target person, if the behavior state of the target person is abnormal, that is, it can be determined that the target person is not currently concentrating on work or study, then a prompt message can be directly sent to the target person to remind the target person to concentrate on work or study, and a prompt message can also be sent to the supervisor of the target person to remind the supervisor to urge the target person to concentrate on work or study. The prompt message can also be temporarily not sent. When it is determined that the number of times or the cumulative duration that the target person has not concentrated on work or study for a period of time exceeds a certain threshold, the sending of the prompt message is triggered. The embodiment of the present invention does not specifically limit this. It is understandable that if the target person is a student, the supervisor of the target person can be a parent, and if the target person is an employee, the supervisor of the target person can be a leader.

[0048] The method provided by the embodiment of the present invention determines the behavior status of the target person by applying the object image of the target person's work object and / or the target person's voice, and provides reminders based on the behavior status, thereby realizing automatic behavior supervision of the target person. This does not require the full participation of the supervisor, saves the supervisor's time, and increases the time that the target person can focus on work / study, thereby improving the target person's work / study efficiency and work / study quality.

[0049] Based on any of the above embodiments, Figure 2is one of the flow charts of the behavior state determination method provided by the present invention, such as Figure 2 As shown, the method includes:

[0050] Step 111, performing operation object recognition on the object image to obtain the current operation object content;

[0051] Step 112, based on the current operation object content and the previous operation object content, determine the behavior state of the target person, the previous operation object content is the operation object content before the current operation object content.

[0052] Specifically, considering that the work content or learning content of the target person usually needs to revolve around the homework object, for example, the learning content of students is usually to do homework, therefore, the embodiment of the present invention determines the behavior state of the target person based on the object image of the target person's homework object: first, the object image of the target person's homework object is collected, and the object image is subjected to homework object recognition to obtain the current homework object content, and then the current homework object content can be compared with the previous homework object content to obtain the comparison result. If the comparison result shows that there is a change, it can be said that the target person is working or studying, and at this time, it can be determined that the behavior state of the target person is normal. Here, the previous homework object content is the homework object content before the current homework object content.

[0053] Furthermore, it is possible to set the object image of the target person's work object to be collected at a preset time interval. For the currently collected object image, the object image obtained by the last collection is the previous object image, and the work object recognition of the previous object image can obtain the content of the previous work object. Preferably, in order to ensure the effect of behavior supervision, the preset time interval can be set to a shorter duration.

[0054] Based on any of the above embodiments, Figure 3 FIG. 2 is a flow chart of the method for determining the behavior state provided by the present invention. Figure 3 As shown, the method includes:

[0055] Step 113, performing voice classification on the person's voice to obtain a voice classification result of the target person;

[0056] Step 114, determining the behavior state of the target person based on the speech classification result of the target person.

[0057] Specifically, considering that the work content or learning content of the target person may be related to voice data, for example, the learning content of students is reading texts, and the work content of employees is giving speeches. If the target person is talking or chatting, voice data will also be emitted. Therefore, in order to determine the target person's behavioral state based on the target person's voice, the embodiment of the present invention can perform voice classification on the target person's voice after obtaining the target person's voice through a sound pickup device, thereby obtaining the voice classification result of the target person. On this basis, the target person's behavioral state can be determined according to the voice classification result of the target person.

[0058] Here, the speech classification result is used to characterize whether there is speech content in the person's speech. If so, it is also used to characterize whether the speech content is related to work or learning content. For example, if the target person is a student, if the speech classification result of the target person is a text, that is, the speech content of the person's speech is related to the learning content, then it can be determined based on the speech classification result that the target person is in a normal learning state, that is, the target person's behavior state is determined to be normal.

[0059] Based on any of the above embodiments, Figure 4 It is a flow chart of the speech classification method provided by the present invention, such as Figure 4 As shown, the method includes:

[0060] Step 1130, performing speech recognition on the person's speech to obtain a speech recognition text of the person's speech;

[0061] Step 1131, perform text classification on the speech recognition text to obtain the speech classification result of the target person.

[0062] Specifically, the speech classification result of the target person can be obtained in the following manner: first, the speech of the target person is recognized, so that the speech can be transcribed into speech recognition text, that is, the text content covered by the speech of the person is obtained, and then the speech recognition text of the speech of the person is classified to obtain the speech classification result of the target person, thereby determining whether the speech content of the speech of the person is related to work or study content. Here, the embodiment of the present invention does not specifically limit the method of speech recognition and text classification, for example, it can be implemented by using a speech recognition model and a text classification model.

[0063] Based on any of the above embodiments, Figure 5 FIG. 3 is a flow chart of the method for determining the behavior state provided by the present invention. Figure 5 As shown, the method includes:

[0064] Step 115, determining the current behavior of the target person based on the object image and / or the person's voice, and the person image of the target person;

[0065] Step 116, determining the behavior state of the target person based on the current behavior of the target person.

[0066] Specifically, in order to supervise the work or study of the target person and increase the time the target person can focus on work or study, the embodiment of the present invention determines the current behavior of the target person based on the object image of the current target person's work object and the person image of the target person, or based on the person voice and person image of the current target person, or based on the object image of the current target person's work object and the person voice and person image of the target person, where the current behavior is used to characterize the action currently performed by the target person, and on this basis, the behavior state of the target person is determined based on the current behavior of the target person. Here, the person image includes an image of the upper body of the target person.

[0067] For example, the target person is a student, and behavior recognition is performed on the target person's image to learn that the student is holding a pen, and homework object recognition is performed on the object image. The current homework object content is compared with the previous homework object content, and it is found that the content of the homework book has not changed. It can be determined that the current behavior of the target person is holding a pen but not writing, which means that the target person may be dozing off, distracted, or deliberately pretending. According to the current behavior of the target person, the behavior state of the target person can be determined as abnormal; for another example, behavior recognition is performed on the target person's image to learn that the student is holding a textbook, and voice recognition is performed on the person's voice to learn that the person's voice has no voice content, then it can be determined that the current behavior of the target person is reading aloud without sound. According to the current behavior of the target person, the behavior state of the target person can be determined as abnormal.

[0068] In particular, the current behavior of the target person can also be determined based only on the person image of the target person, and then the behavior state of the target person can be determined based on the current behavior of the target person. For example, by performing behavior recognition on the person image of the target person, it is known that the target person is currently playing with items that are not related to work or study, such as erasers, toys, Rubik's cubes, etc., and the behavior state of the target person can be determined to be abnormal based on the behavior; for another example, by performing face detection on the person image of the target person, and performing expression recognition based on the face area, it is known that the target person is currently dozing off, and the behavior state of the target person can be determined to be abnormal based on the behavior; for another example, by performing sitting posture detection on the person image of the target person, it is known that the target person is currently lying on the table, and the behavior state of the target person can also be determined to be abnormal based on the behavior.

[0069] Based on any of the above embodiments, Figure 6 FIG. 4 is a flow chart of the method for determining the behavior state provided by the present invention. Figure 6 As shown, the method includes:

[0070] Step 117, determining the target behavior of the target person based on the historical object image and the historical person voice;

[0071] Step 118, determining the behavior state of the target person based on the target behavior of the target person, and the object image or the person's voice.

[0072] Specifically, considering that if the target person's behavioral state is judged only based on the object image of the target person's homework object or the target person's personal voice, there may be judgment errors. For example, the target person is a student, and when the student's learning content is reading aloud, since the student does not need to do homework at this time, the content of the homework object will not change. If the target person's behavioral state is judged only based on the object image of the homework object, the result will be that the student's behavioral state is abnormal.

[0073] In view of this problem, the embodiment of the present invention pre-collects a section of data, namely, historical object images and historical personnel voices, and pre-judges the target behavior of the target person based on these data, namely, the specific work or learning content of the target person. On this basis, the target behavior of the target person, as well as the object image of the current target person's work object or the personnel voice of the current target person, can accurately determine the behavior state of the target person. For example, based on the historical object image and the historical personnel voice, it is determined that the target behavior of the target person is to do homework. At this time, the behavior state of the target person can be determined only based on the object image of the target person's work object. The specific process is: perform work object recognition on the object image of the target person's work object, and then compare the current work object content obtained with the previous work object content. If no change is found, the behavior state of the target person can be directly determined to be abnormal. If a change is found, the behavior state of the target person can also be directly determined to be normal.

[0074] Here, the specific target behavior can be pre-judged in a method of determining the target behavior of the target person based on the correspondence between the sample object image and the sample person voice and each candidate target behavior, as well as the historical object image and the historical person voice, or it can be pre-judged in a method of performing image recognition and voice recognition on the historical object image and the historical person voice, respectively, and determining the target behavior of the target person based on the recognition results. The embodiment of the present invention does not make any specific limitation on this.

[0075] Based on any of the above embodiments, step 120 includes:

[0076] If the number of times the target person's behavior status is abnormal within the preset time period exceeds the number threshold, and / or the cumulative duration of the target person's behavior status being abnormal within the preset time period exceeds the duration threshold, a prompt message is issued.

[0077] Specifically, considering that a short rest or distraction can reduce fatigue caused by work or study for the target person, it will have a positive effect on the subsequent work or study efficiency. In this regard, the embodiment of the present invention counts the behavior status of the target person within a period of time, i.e., a preset time period. If it is determined that the number of times the target person's behavior status is abnormal within the preset time period exceeds the number threshold, and / or the cumulative duration of the target person's behavior status being abnormal within the preset time period exceeds the duration threshold, then a prompt message can be initiated to remind the target person to concentrate on work or study, or to remind the target person's supervisor to urge the target person to concentrate on work or study.

[0078] Here, the preset time period can be preset according to actual needs or can be set according to experience. The unit of the preset time period can be days, hours, etc., which is not specifically limited in the embodiment of the present invention. The number threshold and the duration threshold are both used as comparison parameters to determine whether to trigger the conditions for issuing a prompt message. The number threshold and the duration threshold can be preset without specific numerical limitations. Specific ways of issuing prompt messages include but are not limited to desktop lifting reminders, voice broadcast reminders, and indicator light prompts.

[0079] Based on any of the above embodiments, taking students as an example, the embodiment of the present invention provides a student learning supervision method to increase students' focused learning time, improve students' learning efficiency and learning quality. The specific process of the method is as follows:

[0080] S1) Obtain the learning status of students in the current time period;

[0081] The current time period is a time period [for the last collection time of the student, for the current collection time of the student]; the specific duration of the current time period is not limited and can be preset; the specific method of obtaining the learning status is not limited, for example, using an AI (artificial intelligence) camera to collect images, and then identifying the learning status based on the images;

[0082] The learning status may include learning and non-learning. The non-learning status of students includes but is not limited to the following situations: not moving the pen, reading aloud without sound, playing with erasers, spinning pens, playing with toys, chatting, and no update on the homework book, etc. Among them, the fact that the content on the homework book has not been updated can be judged by regularly collecting the content on the homework book, comparing the results of two consecutive collections, and if it is found that there is no obvious change in the content on the homework book, it means that the content on the homework book has not been updated;

[0083] S2) counting the cumulative duration of the student's non-learning learning status during the current time period;

[0084] The current time period is composed of N time points (N≧1, N is a positive integer). When the student's learning state starts to be non-learning at the i-th time point and ends at the j-th time point, a non-learning dynamic event occurs in the corresponding period of the i-th time point. In this non-learning dynamic event, the student's learning state is non-learning for a duration of t i = ji, (i≦j≦N, i and j are both positive integers); sum the durations of all non-learning dynamic events that occur in the current time period, that is, t = ∑t i , we can determine the cumulative duration t of the student’s non-learning state in the current time period;

[0085] S3) determining whether the cumulative duration of the learning state being non-learning meets a first preset condition, and if so, issuing a prompt message in a preset manner;

[0086] Judgment example: The first preset condition can be set as the proportion of the cumulative duration in the current time period exceeds the proportion threshold, the cumulative duration of the student's non-learning state is t, the current time period is T, and the proportion of the cumulative duration in the current time period is γ=t / T. When the cumulative duration meets the first preset condition, that is, γ exceeds the proportion threshold, it means that the student's learning attention is not focused and needs to be reminded to pay attention to learning in order to improve the student's learning efficiency; wherein, the proportion threshold is used as a comparison parameter to determine whether the conditions for reminding students to study are triggered, and the proportion threshold can be preset. The preset methods include but are not limited to desktop lifting reminders, voice broadcast reminders, and indicator light prompts.

[0087] In order to accurately supervise students to study hard, the following steps can be added on the basis of S1 to S3 above:

[0088] S4) counting the number of times the student's learning status is non-learning in the current time period;

[0089] The current time period is composed of N time points (N≧1, N is a positive integer). When the student's learning state starts to be non-learning at the i-th time point and ends this state at the j-th time point, the count is 1. i , indicating that a non-learning dynamic event occurs in the corresponding period at the i-th time point, (i≦j≦N, i and j are both positive integers); the 1 corresponding to all non-learning dynamic events that occur in the current time period i Perform cumulative summation, that is, h = ∑1 i , we can determine the number of times the student’s learning status is non-learning in the current time period h;

[0090] S5) determining whether the number of times the learning state is non-learning satisfies a second preset condition, and if so, issuing a prompt message in a preset manner;

[0091] Judgment example: The second preset condition can be set as the frequency of occurrence in the current time period exceeds the frequency threshold, the number of times the student's learning status is non-learning is h, the current time period is T, and the proportion of the number in the current time period is α=h / T. When the number meets the second preset condition, that is, α exceeds the frequency threshold, it means that the student is not paying attention to learning and needs to be reminded to pay attention to learning in order to improve the student's learning efficiency; among them, the frequency threshold can be set in advance without specific numerical limitation.

[0092] The behavior monitoring device provided by the present invention is described below. The behavior monitoring device described below and the behavior monitoring method described above can be referenced to each other.

[0093] Based on any of the above embodiments, an embodiment of the present invention provides a behavior monitoring device. Figure 7 is a schematic diagram of the structure of the behavior monitoring device provided by the present invention, such as Figure 7 As shown, the device comprises:

[0094] A determination module 710, configured to determine the behavior state of the target person based on the object image of the target person's work object and / or the target person's voice;

[0095] The prompt module 720 is used to issue prompt information based on the behavior status of the target person.

[0096] The device provided by the embodiment of the present invention determines the behavior status of the target person by applying the object image of the target person's work object and / or the target person's voice, and provides reminders based on the behavior status, thereby realizing automatic behavior supervision of the target person. The supervisor does not need to participate in the whole process, thus saving the supervisor's time, and increasing the time that the target person can focus on work / study, thereby improving the target person's work / study efficiency and work / study quality.

[0097] Based on any of the above embodiments, the determination module 710 includes:

[0098] The operation object recognition unit is used to perform operation object recognition on the object image to obtain the current operation object content;

[0099] The first behavior state determination unit is used to determine the behavior state of the target person based on the current operation object content and the previous operation object content, where the previous operation object content is the operation object content before the current operation object content.

[0100] Based on any of the above embodiments, the determination module 710 includes:

[0101] A speech classification unit is used to classify the speech of a person and obtain a speech classification result of the target person;

[0102] The second behavior state determination unit is used to determine the behavior state of the target person based on the speech classification result of the target person.

[0103] Based on any of the above embodiments, the speech classification unit includes:

[0104] A speech recognition unit, used to perform speech recognition on a person's speech and obtain a speech recognition text of the person's speech;

[0105] The text classification unit is used to perform text classification on the speech recognition text to obtain the speech classification result of the target person.

[0106] Based on any of the above embodiments, the determination module 710 includes:

[0107] A current behavior determination unit, configured to determine the current behavior of the target person based on the object image and / or the person's voice, and the person image of the target person;

[0108] The third behavior state determination unit is used to determine the behavior state of the target person based on the current behavior of the target person.

[0109] Based on any of the above embodiments, the determination module 710 includes:

[0110] A target behavior determination unit, used for determining a target behavior of a target person based on the historical object image and the historical person voice;

[0111] The fourth behavior state determination unit is used to determine the behavior state of the target person based on the target behavior of the target person and the object image or the person's voice.

[0112] Based on any of the above embodiments, the prompt module 720 includes:

[0113] If the number of times the target person's behavior status is abnormal within the preset time period exceeds the number threshold, and / or the cumulative duration of the target person's behavior status being abnormal within the preset time period exceeds the duration threshold, a prompt message is issued.

[0114] Figure 8 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 8As shown, the electronic device may include: a processor 810, a communication interface 820, a memory 830 and a communication bus 840, wherein the processor 810, the communication interface 820 and the memory 830 communicate with each other through the communication bus 840. The processor 810 may call the logic instructions in the memory 830 to execute the behavior supervision method, which includes: determining the behavior state of the target person based on the object image of the target person's work object and / or the target person's voice; and issuing prompt information based on the behavior state of the target person.

[0115] In addition, the logic instructions in the above-mentioned memory 830 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0116] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the behavior supervision method provided by the above-mentioned methods. The method includes: determining the behavior status of the target person based on the object image of the target person's work object and / or the target person's voice; and issuing prompt information based on the behavior status of the target person.

[0117] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, it is implemented to execute the behavior supervision method provided by the above-mentioned methods. The method includes: determining the behavior state of the target person based on the object image of the target person's work object and / or the target person's voice; and issuing a prompt message based on the behavior state of the target person.

[0118] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0119] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0120] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A behavior supervision method, characterized in that: include: Determining the behavior state of the target person based on the object image of the target person's work object and / or the target person's voice; Based on the behavior status of the target person, a prompt message is issued; The determining of the behavior state of the target person based on the object image of the target person's work object and / or the target person's voice includes: Determine the target behavior of the target person based on the historical object image and the historical person voice; the historical object image and the historical person voice are pre-collected images of the target person's work object and the voice data of the target person, respectively, and the target behavior is used to represent the work or study content of the target person; Based on the target behavior of the target person and the object image or the person's voice, the behavior state of the target person is determined.

2. The behavior supervision method according to claim 1, characterized in that: The determining of the behavior state of the target person based on the object image of the target person's work object and / or the target person's voice includes: Performing operation object recognition on the object image to obtain current operation object content; Based on the current operation object content and the previous operation object content, the behavior state of the target person is determined, and the previous operation object content is the operation object content before the current operation object content.

3. The behavior monitoring method according to claim 1, characterized in that: The determining of the behavior state of the target person based on the object image of the target person's work object and / or the target person's voice includes: Performing voice classification on the speech of the person to obtain a voice classification result of the target person; Based on the speech classification result of the target person, the behavior state of the target person is determined.

4. The behavior supervision method according to claim 3, characterized in that: The performing voice classification on the speech of the person to obtain the speech classification result of the target person includes: Performing speech recognition on the person's speech to obtain a speech recognition text of the person's speech; The speech recognition text is subjected to text classification to obtain a speech classification result of the target person.

5. The behavior monitoring method according to claim 1, characterized in that: The determining of the behavior state of the target person based on the object image of the target person's work object and / or the target person's voice includes: Determine the current behavior of the target person based on the object image and / or the person's voice, and the person image of the target person; Based on the current behavior of the target person, the behavior state of the target person is determined.

6. The behavior supervision method according to any one of claims 1 to 5, characterized in that: The issuing of prompt information based on the behavior status of the target person includes: If the number of times that the target person's behavior status is abnormal within the preset time period exceeds the number threshold, and / or the cumulative duration that the target person's behavior status is abnormal within the preset time period exceeds the duration threshold, the prompt information is issued.

7. A behavior monitoring device, characterized in that: include: A determination module, configured to determine the behavior state of the target person based on an object image of the target person's work object and / or the target person's voice; A prompt module, used for issuing prompt information based on the behavior status of the target person; The determination module comprises: a target behavior determination unit, for determining the target behavior of the target person based on the historical object image and the historical person voice; the historical object image and the historical person voice are pre-collected images of the target person's work object and the voice data of the target person, respectively, and the target behavior is used to represent the work or study content of the target person; The fourth behavior state determination unit is used to determine the behavior state of the target person based on the target behavior of the target person and the object image or the person's voice.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the behavior monitoring method according to any one of claims 1 to 6 are implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the behavior monitoring method according to any one of claims 1 to 6 are implemented.

Images