A computer information processing method and a computer system

Abstract

The present invention provides a computer information processing method and a computer system, and relates to the technical field of computer information processing. The method comprises: receiving multiple recorded video information sent by a network transmission device in real time, and classifying the multiple recorded video information based on the video scene or the video sending address in the recorded video information; periodically compressing the multiple historical record video information according to the classified multiple historical record video information and a preset compression sorting time to generate initial compressed data; periodically performing video data reduction and clearing processing on the historical record video information of the same segment in the initial compressed data according to a preset re-cleaning time, and performing data re-compression processing to generate re-compressed data. The present application reduces the storage pressure of the computer by compressing multiple videos and reducing and clearing the video data of the same segment.

Description

Technical Field

[0001] The present invention relates to the technical field of computer information processing, and in particular to a computer information processing method and a computer system. Background Art

[0002] With the rapid development of Internet computer technology, the Internet has become an indispensable part of people's life. The collection and organization of big data based on the Internet, the sharing of information among multiple parties, etc., have greatly reduced the difficulty of information collection and processing for computer systems and users.

[0003] But at the same time, due to the strong openness of the Internet, the difficulty of information collection and processing has been greatly reduced, the collection and processing of big data has grown explosively, and the flood of information has increased the pressure on computers for data processing and data storage.

[0004] Among them, in the real-time process of monitoring video, due to the limited storage space of the computer system, the only way to reduce storage pressure is to clear the video regularly. When historical monitoring video needs to be retrieved, the regular clearing of the video will undoubtedly lead to a large amount of information loss. Summary of the invention

[0005] In order to reduce the information storage pressure of a computer system, the present application provides a computer information processing method and a computer system.

[0006] In a first aspect, the present application provides a computer information processing method, which adopts the following technical solution:

[0007] A computer information processing method, the method comprising:

[0008] Receiving multiple recorded video information sent by a network transmission device in real time, and classifying the multiple recorded video information based on video scenes or video sending addresses in the recorded video information;

[0009] According to the classified multiple historical record video information and the preset compression and sorting time, periodically compressing the multiple historical record video information to generate initial compressed data;

[0010] According to the preset re-cleaning time, the historical record video information of the same segment in the initially compressed data is periodically subjected to video data reduction and clearing processing, and is subjected to re-data compression processing to generate re-compressed data.

[0011] Optionally, the method further includes:

[0012] receiving a plurality of reference video information input by a user, wherein a one-to-one mapping relationship exists between the plurality of reference video information and the categories into which the plurality of recorded video information are classified;

[0013] According to the plurality of reference video information, status recognition processing is performed on the plurality of recorded video information currently received and classified, and corresponding status identifiers are added.

[0014] Optionally, the performing status recognition processing on the multiple recorded video information currently received and classified according to the multiple reference video information, and adding corresponding status identifiers, includes:

[0015] Compare the target control video information with the target recorded video information received within a preset unit time length before the current moment;

[0016] If there is a static difference region of static matter between the target control video information and the target recorded video information, and according to the static difference region and the static change information corresponding to the target control video information input by the user, a static object state identifier corresponding to the target recorded video information is generated;

[0017] If there is a dynamic difference region of dynamic matter between the target control video information and the target recorded video information, and according to the dynamic difference region and a preset dynamic offset threshold, a dynamic object state identifier corresponding to the target recorded video information is generated.

[0018] Optionally, comparing the target reference video information with the target recorded video information received within a preset unit time length before the current moment includes:

[0019] Capturing reference static object information and reference dynamic object information from the target reference video information, wherein the reference static object information includes the areas where reference building objects and reference fixed equipment objects are located, and the reference dynamic object information includes the moving areas of reference people and reference dynamic objects;

[0020] Capturing current static object information and current dynamic object information from the target recorded video information, wherein the current static object information includes the area where the current building object and the current fixed equipment object are located, and the current dynamic object information includes the moving area of ​​the current person and the current dynamic object;

[0021] The current static object information is compared with the reference static object information, and the current dynamic object information is compared with the reference dynamic object information.

[0022] Optionally, generating a static object state identifier corresponding to the target recorded video information according to the static difference area and the static change information corresponding to the target reference video information input by the user includes:

[0023] Generate estimated static increase and decrease information for the unit time length before the current moment according to the static change information input by the user and the target recorded video information corresponding to multiple target historical record video information of the same shooting area, wherein the estimated static increase and decrease information includes a static change area and a static material change amount;

[0024] If the static difference area corresponding to the target recorded video information is within the estimated static increase or decrease information, a static object state identifier carrying a normal label is generated;

[0025] If the static difference area corresponding to the target recorded video information is not within the estimated static increase or decrease information, a static object state identifier carrying an abnormal label is generated.

[0026] Optionally, generating a dynamic object state identifier corresponding to the target recorded video information according to the dynamic difference area and a preset dynamic offset threshold includes:

[0027] Based on the target history record video information, capturing the historical movement range of the person, the historical on-the-job time habits of the person, and the historical movement range of the dynamic object;

[0028] Based on the historical movement range of the person, the historical movement range of the dynamic object and a preset dynamic offset threshold, dividing the target recorded video information into an estimated person dynamic movement area and an estimated dynamic object movement area;

[0029] If the shooting time corresponding to the target recorded video is within the time of the historical on-duty time habit of the person, then according to the moving areas of the current person and the current dynamic object in the current dynamic object information, as well as the estimated dynamic moving area of ​​the person and the estimated moving area of ​​the dynamic object, the dynamic object state identifier carrying a normal label or an abnormal label is generated;

[0030] If the corresponding time in the target recorded video is not within the historical on-the-job time habits of the person, the dynamic object state identifier carrying a normal label or an abnormal label is generated based on the moving area of ​​the current dynamic object in the current dynamic object information and the estimated moving area of ​​the dynamic object.

[0031] Optionally, the method further includes:

[0032] Receive tag verification information input by the user;

[0033] The status identifiers of the plurality of corresponding historical record video information carrying abnormal labels are updated according to the label verification information.

[0034] In a second aspect, the present application provides a computer system, which adopts the following technical solution;

[0035] A computer system, comprising:

[0036] The classification module 801 is used to receive multiple recorded video information sent by the network transmission device in real time, and classify the multiple recorded video information based on the video scene or the video sending address in the recorded video information;

[0037] The information compression module 802 is used to periodically compress the multiple historical record video information to generate initial compressed data according to the classified multiple historical record video information and the preset compression and sorting time;

[0038] According to the preset re-cleaning time, the historical record video information of the same segment in the initially compressed data is periodically subjected to video data reduction and clearing processing, and is subjected to re-data compression processing to generate re-compressed data.

[0039] In a third aspect, the present application provides a smart terminal, which adopts the following technical solution:

[0040] A smart terminal comprises a processor and a memory, wherein the memory stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by the processor to implement the computer information processing method as described in the first aspect.

[0041] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution:

[0042] A computer-readable storage medium, wherein at least one instruction, at least one program, a code set or an instruction set is stored in the storage medium, and the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by a processor to implement the computer information processing method as described in the first aspect.

[0043] In summary, the present application includes at least one of the following beneficial technical effects:

[0044] 1. In the process of the computer system acquiring the recorded video information in real time, in order to reduce the storage pressure of the computer system and the pressure of the user to screen the video, the computer system first classifies the multiple recorded video information so that the same area is shot and classified into the same type of recorded video information; then the computer system periodically compresses the recorded video information, thereby reducing the storage pressure of the computer system; further, the computer system reduces and clears the video data of the same segment in the historical record video information, and compresses it again, thereby further reducing the storage pressure of the computer;

[0045] 2. The computer system adds different status identifiers to the recorded video information to reduce the difficulty of manually identifying videos shot in abnormal states. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0047] Figure 1 It is a flowchart of a computer information processing method provided in an embodiment of the present application.

[0048] Figure 2 It is a flowchart of adding a status identifier provided in an embodiment of the present application.

[0049] Figure 3 It is a flow chart of adding static object status identification and dynamic object status identification provided in an embodiment of the present application.

[0050] Figure 4 It is a flow chart of comparing target control video information with target recorded video information provided in an embodiment of the present application.

[0051] Figure 5 It is a schematic diagram of a process for generating a static object state identification provided in an embodiment of the present application.

[0052] Figure 6 It is a schematic diagram of a process for generating a dynamic object state identification provided in an embodiment of the present application.

[0053] Figure 7 It is a flow chart of an update status identification provided in an embodiment of the present application.

[0054] Figure 8 It is a system block diagram of a computer system provided in an embodiment of the present application.

[0055] Explanation of the accompanying drawings: 801, classification module; 802, information compression module; 803, information receiving module; 804, identification adding module; 805, comparison module; 806, information capturing module; 807, state estimation module; 808, updating module. DETAILED DESCRIPTION

[0056] In order to make the objectives, technical solutions and advantages of the present invention more clear, the embodiments of the present invention will be further described in detail below in conjunction with the accompanying drawings 1-8.

[0057] The embodiment of the present application provides a computer information processing method, which can be applied to a computer system. The embodiment of the present application takes the computer system receiving monitoring videos of industrial construction or factory production as an example for explanation, and other situations such as street monitoring videos, equipment management monitoring video processing, etc. are not described one by one.

[0058] The following will be combined with specific implementation methods. Figure 1 The processing flow shown is described in detail, and the content can be as follows:

[0059] S101, receiving a plurality of recorded video information sent by a network transmission device in real time, and classifying the plurality of recorded video information based on video scenes or video sending addresses in the recorded video information.

[0060] During implementation, a computer system receives multiple recorded video information sent by a network transmission device or directly sent by a video surveillance device. Before the computer system stores the received recorded video information in a memory, the computer system first classifies the multiple recorded video information according to the video scene and the initial video shooting address of each recorded video information, so as to classify multiple recorded video information shot at the same location into the same category, thereby reducing the pressure on the computer system to manage video information.

[0061] The recorded video information here can be connected and transmitted in real time, or it can be transmitted after being filmed in stages. At the same time, the video shot for a long time is divided here to facilitate the accurate positioning of the abnormal time period in the video later. When dividing the video shot for a long time, the same continuous video is usually divided into multiple recorded video information based on the time axis, for example, the divided time is 1 hour, 2 hours, 1 day, etc.

[0062] S102, periodically compressing the plurality of historical record video information according to the classified plurality of historical record video information and the preset compression and sorting time to generate initial compression data.

[0063] In practice, the recorded video information stored in the computer system for a certain period of time is called historical record video information, where the certain period of time can be a day or a week, etc., which is manually defined. The computer system compresses the same type of historical record video information according to a preset compression and sorting period to generate primary compressed data.

[0064] S103, according to the preset re-cleaning time, periodically perform video data reduction and clearing processing on the historical record video information of the same segment in the initially compressed data, and perform re-data compression processing to generate re-compressed data.

[0065] In implementation, in order to facilitate further processing of the initially compressed data stored in the computer system and reduce the storage pressure of the computer system, the computer system periodically processes the initially compressed data of the same category with the re-cleaning time as the period. Specifically, in the process of processing the initially compressed video, if it is identified that the historical record video information in the initially compressed video contains continuous and identical segments, the identical segments are cleared, and only one screenshot in the video is recorded, and the repetition time is recorded. After the video data reduction and clearing processing is performed on the historical record video information in the initially compressed video, the computer system again performs data compression processing on the processed historical record video information to generate re-compressed data, thereby further reducing the information storage pressure of the computer system.

[0066] Optionally, in this application, there is also Figure 2 The specific operation method is as follows:

[0067] S201, receiving a plurality of reference video information input by a user, wherein a one-to-one mapping relationship exists between the plurality of reference video information and the categories for classifying the plurality of recorded video information.

[0068] In practice, in order to facilitate the identification of anomalies in recorded video information, the computer system receives multiple reference video information input by the user, where the anomalies include the position of static materials and the moving range of dynamic materials in the video, such as the position movement of factory fixed equipment, the moving range of factory operators exceeding the normal moving range, etc. At the same time, there is a one-to-one mapping relationship between the reference video information and the categories of the multiple recorded videos.

[0069] S202, performing status recognition processing on the multiple recorded video information currently received and classified according to the multiple reference video information, and adding corresponding status identifiers.

[0070] In implementation, in order to facilitate status identification of the classified multiple recorded video information, so that the user can promptly process the abnormal recorded video information and enhance the efficiency of the information processing process, the computer system compares the control video with the multiple recorded video information before data compression after classification, and adds a status mark according to the comparison result.

[0071] Optionally, in step S202, there is also Figure 3 The specific operations are as follows:

[0072] S301, comparing the target comparison video information with the target recorded video information received within a preset unit time before the current moment.

[0073] In implementation, the computer system processes multiple recorded video information and multiple reference video information, one of which is selected for illustration, and the selected recorded video information is referred to as target recorded video information, and the reference video information is referred to as target reference video information.

[0074] The computer system selects the target recorded video information received within a preset unit time before the current moment, and compares the target recorded video information with the corresponding target reference video. The specific comparison results are as follows.

[0075] S302: If there is a static difference region of static material between the target reference video information and the target recorded video information, a static object state identifier corresponding to the target recorded video information is generated according to the static difference region and the static change information corresponding to the target reference video information input by the user.

[0076] During implementation, when the computer system compares the target recorded video information with the target control video information, if there is a static difference area between the static materials between the target control video information and the target recorded video information, the computer system further estimates the area where the static object of the target recorded video information is located based on the static change information, which is referred to as the static object estimation area.

[0077] Then, if the computer system identifies that the static difference region is within the static object estimation region, a static object state identifier carrying a normal label is generated. If the computer system identifies that the static difference region is not within the static object estimation region, a static object state identifier carrying an abnormal label is generated.

[0078] S303: If there is a dynamic difference region of dynamic matter between the target control video information and the target recorded video information, a dynamic object state identifier corresponding to the target recorded video information is generated according to the dynamic difference region and a preset dynamic offset threshold.

[0079] In implementation, when a computer system compares target recorded video information with target control video information, if there is a dynamic difference region of dynamic matter between the target control video information and the target recorded video information, the computer combines the dynamic difference region with the dynamic offset threshold to generate a dynamic object state identification carrying an abnormal label or a normal label.

[0080] Optionally, in step 301, there is also Figure 4 The specific operations are as follows:

[0081] S401, capturing control static object information and control dynamic object information from the target control video information, wherein the control static object information includes the areas where control building objects and control fixed equipment objects are located, and the control dynamic object information includes the moving areas of control persons and control dynamic objects.

[0082] During implementation, before comparing the target control video information with the target recorded video information, the computer system first captures the static object information and dynamic object information in the video from the target control video information. The static object information here includes the areas where the control buildings and control fixed equipment objects are located in the target control video information, and the control dynamic object information includes the moving areas of the control people and control dynamic objects.

[0083] S402, capturing current static object information and current dynamic object information from the target recorded video information, wherein the current static object information includes the area where the current building object and the current fixed equipment object are located, and the current dynamic object information includes the moving area of ​​the current person and the current dynamic object.

[0084] During implementation, before comparing the target control video information with the target recorded video information, the computer system also captures the current static object information and the current dynamic object information in the video from the target recorded video information, where the current static object information includes the area where the current building and the current fixed equipment object in the target recorded video information are located, and the current dynamic object information includes the moving area of ​​the current person and the current dynamic object.

[0085] S403, comparing the current static object information with the reference static object information, and comparing the current dynamic object information with the reference dynamic object information.

[0086] During implementation, the computer system compares the areas where the current building object and the current fixed equipment object in the current static object information are located with the areas where the control building object and the control fixed equipment object are located in the control static object information, and at the same time compares the moving areas of the current person and the current dynamic object in the current dynamic object information with the moving areas of the control person and the control dynamic object in the control dynamic object information, respectively. The specific comparison results are as follows.

[0087] Optionally, in step 302, there is also Figure 5 The specific operations are as follows:

[0088] S501, based on the static change information input by the user and the target recorded video information corresponding to multiple target historical recorded video information in the same shooting area, generate the estimated static increase and decrease information in unit time before the current moment, the estimated static increase and decrease information includes the estimated static change area and the estimated static material change amount.

[0089] During implementation, the computer system receives static change information input by the user, where the static change information is used to reflect the process of changes in the control video information compared with the standard conditions of the building, the time required for the change of the building, the process of moving the fixed equipment, and the time required to move the solid equipment.

[0090] The computer system first retrieves from the memory according to the target recorded video information, corresponding to a plurality of historical recorded video information of the same shooting area, where the historical recorded video information is referred to as the target historical recorded video information.

[0091] The computer system then generates, from multiple target historical record video information, the construction progress of the building object or the movement progress of the fixed equipment before the current target record video information was shot, as well as the construction rate ratio information of the building object's construction process relative to the standard construction time, and the movement rate ratio information of the fixed equipment's movement process relative to the standard movement time.

[0092] The computer then calculates the estimated construction volume of the building object and the estimated movement volume of the fixed equipment in the current recorded video information based on the construction process, movement process, construction rate ratio information and movement rate ratio information.

[0093] Furthermore, the computer system divides the estimated static object movement area from the target recorded video based on the estimated construction volume of the building object and the estimated movement volume of the fixed equipment; next, the computer system superimposes the estimated construction volume and the estimated movement volume of the fixed equipment with the static object change threshold to generate an estimated static material change, and superimposes the estimated static object movement area with the static change threshold area to generate an estimated static change area, where the estimated static material change amount and the estimated static change area are referred to as estimated static increase and decrease information.

[0094] S502: If the static difference area corresponding to the target recorded video information is within the estimated static increase or decrease information, a static object state identifier carrying a normal label is generated.

[0095] In implementation, the computer system compares the static difference area in the target recorded video information with the estimated static change area in the estimated static increase and decrease information, and generates a static object state identifier carrying a normal label if the static difference area is within the estimated static change area.

[0096] S503: If the static difference area corresponding to the target recorded video information is not within the estimated static increase or decrease information, a static object state identifier carrying an abnormal label is generated.

[0097] During implementation, the computer system compares the static difference area in the target recorded video information with the estimated static change area in the estimated static increase and decrease information. If the static difference area corresponding to the target recorded video information is not within the estimated static change area, a static object state identifier carrying an abnormal label is generated.

[0098] Optionally, in step 303, there is also Figure 6 The specific operations are as follows:

[0099] S601, based on the historical record video information of multiple targets, capturing the historical movement range of the person, the historical on-the-job time habits of the person, and the historical movement range of the dynamic object.

[0100] In implementation, the computer system captures the historical movement range of the person and the historical movement range of the dynamic object in the target historical record video information based on multiple target historical record video information, and further generates the person's historical on-the-job time habits based on the person's historical on-the-job time and the proportion of on-the-job time at different times. For example, it is concluded that the person always stays on the job from 9 am to 5 pm on weekdays.

[0101] S602: based on the historical movement range of the person, the historical movement range of the dynamic object and a preset dynamic offset threshold, the target recorded video information is divided into an estimated person dynamic movement area and an estimated dynamic object movement area.

[0102] During implementation, the computer system superimposes the historical movement range of the person and the preset dynamic offset threshold to divide the estimated dynamic movement area of ​​the person in the target recorded video information. The computer system then superimposes the historical dynamic object movement range and the preset dynamic offset threshold to divide the estimated dynamic object movement area in the target recorded video information.

[0103] S603, if the shooting time corresponding to the target recorded video is within the time of the person's historical on-the-job time habits, then a dynamic object state identification carrying a normal label or an abnormal label is generated based on the moving areas of the current person and the current dynamic object in the current dynamic object information, as well as the estimated dynamic moving area of ​​the person and the estimated moving area of ​​the dynamic object.

[0104] During implementation, the computer system first identifies whether the shooting time corresponding to the current target recorded video is within the time of the person's historical on-the-job time habits.

[0105] If the shooting time corresponding to the target recorded video is within the historical on-duty time of the person, then the moving areas of the current person and the current dynamic object in the current dynamic object information are compared with the estimated dynamic moving area of ​​the person and the estimated dynamic object moving area, respectively. The comparison results are as follows:

[0106] Case 1: The moving areas of the current person and the current dynamic object are both located in the estimated person dynamic moving area and the estimated dynamic object moving area respectively, then a dynamic object state identifier carrying a normal label is generated;

[0107] Case 2: If the current moving area of ​​the person is not within the estimated dynamic moving area of ​​the person, and / or the current moving area of ​​the dynamic object is not within the estimated dynamic object moving area, a dynamic object state identifier carrying an abnormal label is generated.

[0108] S604, if the corresponding time in the target recorded video is not within the person's historical on-the-job time habits, a dynamic object state identifier carrying a normal label or an abnormal label is generated based on the moving area of ​​the current dynamic object in the current dynamic object information and the estimated moving area of ​​the dynamic object.

[0109] In implementation, if the shooting time corresponding to the target recorded video is not within the historical on-duty time of the person, it is only necessary to compare the moving area of ​​the current dynamic object in the current dynamic object information with the estimated moving area of ​​the dynamic object. The comparison is as follows:

[0110] Case 1: If the moving area of ​​the current dynamic object is within the estimated moving area of ​​the dynamic object, a dynamic object state identifier with a normal label is generated;

[0111] Case 2: If the moving area of ​​the current dynamic object is not within the estimated moving area of ​​the dynamic object, a dynamic object state identifier carrying an abnormal label is generated.

[0112] Optionally, in the embodiments of the present application, there is also Figure 7 The specific operations are as follows:

[0113] S701, receiving tag verification information input by a user.

[0114] In implementation, the computer system receives the tag verification information input by the user. The tag verification information here can be the verification process performed by the user on the status identifier carrying the abnormal tag through the terminal after the computer system feeds back the status identifier carrying the abnormal tag to the user's terminal.

[0115] S702: Update the status flags of the plurality of corresponding historical record video information that carry abnormal tags according to the tag verification information.

[0116] During implementation, the computer system verifies the information based on the tags and updates the status identification of the abnormal tags carried in the multiple historical information.

[0117] It should be noted that in order to ensure the accuracy of the target historical record video information used above, the status identifier corresponding to the target historical record video information here should carry a normal label. After the computer system updates the status identifier carrying the abnormal label, the number of target historical record video information may also change with the change in the number of abnormal labels.

[0118] like Figure 8 As shown, the embodiment of the present application further discloses a computer system, characterized in that the computer system includes:

[0119] The classification module 801 is used to receive multiple recorded video information sent by the network transmission device in real time, and classify the multiple recorded video information based on the video scene or the video sending address in the recorded video information;

[0120] The information compression module 802 is used to periodically compress the multiple historical record video information to generate initial compressed data according to the classified multiple historical record video information and the preset compression and sorting time;

[0121] According to the preset re-cleaning time, the historical record video information of the same segment in the initially compressed data is periodically subjected to video data reduction and clearing processing, and the data is compressed again to generate re-compressed data.

[0122] Optionally, the computer system may also be used to:

[0123] The information receiving module 803 is used to receive a plurality of reference video information input by a user, and there is a one-to-one mapping relationship between the plurality of reference video information and the categories for classifying the plurality of recorded video information;

[0124] The identification adding module 804 is used to perform status identification processing on the multiple recorded video information currently received and classified according to the multiple reference video information, and add corresponding status identification.

[0125] Optionally, the computer system may also be used to:

[0126] The comparison module 805 is used to compare the target control video information with the target recorded video information received within a preset unit time before the current moment;

[0127] If there is a static difference region of static matter between the target control video information and the target recorded video information, and according to the static difference region and the static change information corresponding to the target control video information input by the user, a static object state identifier corresponding to the target recorded video information is generated;

[0128] If there is a dynamic difference region of dynamic matter between the target control video information and the target recorded video information, and according to the dynamic difference region and a preset dynamic offset threshold, a dynamic object state identifier corresponding to the target recorded video information is generated.

[0129] Optionally, the computer system may also be used to:

[0130] An information capturing module 806 is used to capture the reference static object information and the reference dynamic object information from the target reference video information, wherein the reference static object information includes the location of the reference building object and the reference fixed equipment object, and the reference dynamic object information includes the moving area of ​​the reference person and the reference dynamic object;

[0131] The information capturing module 806 is used to capture the current static object information and the current dynamic object information from the target recorded video information, wherein the current static object information includes the area where the current building object and the current fixed equipment object are located, and the current dynamic object information includes the moving area of ​​the current person and the current dynamic object;

[0132] The comparison module 805 is used to compare the current static object information with the reference static object information, and to compare the current dynamic object information with the reference dynamic object information.

[0133] Optionally, the computer system may also be used to:

[0134] The state estimation module 807 is used to generate estimated static increase and decrease information per unit time before the current moment according to the static change information input by the user and the target recorded video information corresponding to multiple target historical record video information of the same shooting area, and the estimated static increase and decrease information includes the static change area and the static material change amount;

[0135] If the static difference area corresponding to the target recorded video information is within the estimated static increase or decrease information, a static object state identifier carrying a normal label is generated;

[0136] If the static difference area corresponding to the target recorded video information is not within the estimated static increase or decrease information, a static object state identifier carrying an abnormal label is generated.

[0137] Optionally, the computer system may also be used to:

[0138] The information capture module 806 captures the historical movement range of the person, the historical on-the-job time habits of the person, and the historical movement range of the dynamic object based on the multiple target historical record video information;

[0139] The state estimation module 807 divides the target recorded video information into an estimated human dynamic movement area and an estimated dynamic object movement area based on the historical human movement range, the historical dynamic object movement range and a preset dynamic offset threshold;

[0140] If the shooting time corresponding to the target recorded video is within the time of the person's historical on-the-job time habits, a dynamic object state identifier carrying a normal label or an abnormal label is generated according to the moving areas of the current person and the current dynamic object in the current dynamic object information, as well as the estimated dynamic moving area of ​​the person and the estimated moving area of ​​the dynamic object;

[0141] If the corresponding time in the target recorded video is not within the person's historical on-the-job time habits, a dynamic object state identifier carrying a normal label or an abnormal label is generated based on the moving area of ​​the current dynamic object in the current dynamic object information and the estimated moving area of ​​the dynamic object.

[0142] Optionally, the computer system may also be used to:

[0143] The information receiving module 803 is used to receive the label verification information input by the user;

[0144] The updating module 808 is used to update the status identification of the abnormal labels carried by the plurality of corresponding historical record video information according to the label verification information.

[0145] In an embodiment of the present application, a smart terminal is provided. The smart terminal may have relatively large differences due to different configurations or performances, and may include one or more central processors (for example, one or more processors) and memories, and one or more storage media (for example, one or more mass storage devices) for storing applications or data. Among them, the memory and storage medium may be short-term storage or permanent storage. The program stored in the storage medium may include one or more modules (not shown in the figure), and each module may include a series of instruction operations in the smart terminal.

[0146] The intelligent terminal may also include one or more power supplies, one or more wired or wireless network interfaces, one or more input and output interfaces, one or more keyboards, and / or one or more operating systems.

[0147] The intelligent terminal may include a memory and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by one or more processors to perform the above-mentioned computer information processing method.

[0148] A person skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware or by instructing related hardware through a program. The program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, etc.

[0149] The above are all preferred embodiments of the present application, and the protection scope of the present application is not limited thereto. Therefore, any equivalent changes made according to the structure, shape, and principle of the present application should be included in the protection scope of the present application.

[0150] Although the present invention is disclosed as above, the protection scope of the present invention is not limited thereto. Those skilled in the art may make various changes and modifications without departing from the spirit and scope of the present invention, and these changes and modifications will fall within the protection scope of the present invention.

Claims

1. A computer information processing method, characterized in that: The method comprises: Receiving multiple recorded video information sent by a network transmission device in real time, and classifying the multiple recorded video information based on video scenes or video sending addresses in the recorded video information; According to the classified multiple historical record video information and the preset compression and sorting time, periodically compressing the multiple historical record video information to generate initial compressed data; According to a preset re-cleaning time, periodically perform video data reduction and clearing processing on the historical record video information of the same segment in the initially compressed data, and perform re-data compression processing to generate re-compressed data; The method further comprises: receiving a plurality of reference video information input by a user, wherein a one-to-one mapping relationship exists between the plurality of reference video information and the categories into which the plurality of recorded video information are classified; According to the plurality of reference video information, status recognition processing is performed on the plurality of recorded video information currently received and classified, and corresponding status identifiers are added; The step of performing status recognition processing on the multiple recorded video information currently received and classified according to the multiple reference video information and adding corresponding status identifiers includes: Compare the target control video information with the target recorded video information received within a preset unit time length before the current moment; If there is a static difference region of static matter between the target control video information and the target recorded video information, and according to the static difference region and the static change information corresponding to the target control video information input by the user, a static object state identifier corresponding to the target recorded video information is generated; If there is a dynamic difference region of dynamic matter between the target control video information and the target recorded video information, and according to the dynamic difference region and a preset dynamic offset threshold, a dynamic object state identifier corresponding to the target recorded video information is generated.

2. The method according to claim 1, characterized in that The step of comparing the target reference video information with the target recorded video information received within a preset unit time length before the current moment includes: Capturing reference static object information and reference dynamic object information from the target reference video information, wherein the reference static object information includes the areas where reference building objects and reference fixed equipment objects are located, and the reference dynamic object information includes the moving areas of reference people and reference dynamic objects; Capturing current static object information and current dynamic object information from the target recorded video information, wherein the current static object information includes the area where the current building object and the current fixed equipment object are located, and the current dynamic object information includes the moving area of ​​the current person and the current dynamic object; The current static object information is compared with the reference static object information, and the current dynamic object information is compared with the reference dynamic object information.

3. The method according to claim 2, characterized in that The step of generating a static object state identifier corresponding to the target recorded video information according to the static difference area and the static change information corresponding to the target reference video information input by the user comprises: Generate estimated static increase and decrease information for the unit time length before the current moment according to the static change information input by the user and the target recorded video information corresponding to multiple target historical record video information of the same shooting area, wherein the estimated static increase and decrease information includes a static change area and a static material change amount; If the static difference area corresponding to the target recorded video information is within the estimated static increase or decrease information, a static object state identifier carrying a normal label is generated; If the static difference area corresponding to the target recorded video information is not within the estimated static increase or decrease information, a static object state identifier carrying an abnormal label is generated.

4. The method according to claim 3, characterized in that The step of generating a dynamic object state identifier corresponding to the target recorded video information according to the dynamic difference area and a preset dynamic offset threshold comprises: Based on the target history record video information, capturing the historical movement range of the person, the historical on-the-job time habits of the person, and the historical movement range of dynamic objects; Based on the historical movement range of the person, the historical movement range of the dynamic object and a preset dynamic offset threshold, dividing the target recorded video information into an estimated person dynamic movement area and an estimated dynamic object movement area; If the shooting time corresponding to the target recorded video is within the time of the historical on-duty time habit of the person, then according to the moving areas of the current person and the current dynamic object in the current dynamic object information, as well as the estimated dynamic moving area of ​​the person and the estimated moving area of ​​the dynamic object, the dynamic object state identifier carrying a normal label or an abnormal label is generated; If the corresponding time in the target recorded video is not within the historical on-the-job time habits of the person, the dynamic object state identifier carrying a normal label or an abnormal label is generated based on the moving area of ​​the current dynamic object in the current dynamic object information and the estimated moving area of ​​the dynamic object.

5. The method according to claim 4, characterized in that The method further comprises: Receive tag verification information input by the user; The status identifiers of the plurality of corresponding historical record video information carrying abnormal labels are updated according to the label verification information.

6. A computer system, characterized in that: The computer system comprises: A classification module (801) is used to receive in real time a plurality of recorded video information sent by a network transmission device, and classify the plurality of recorded video information based on a video scene or a video sending address in the recorded video information; An information compression module (802) is used to periodically compress the plurality of historical record video information to generate initial compressed data according to the classified plurality of historical record video information and a preset compression and sorting time; According to a preset re-cleaning time, periodically perform video data reduction and clearing processing on the historical record video information of the same segment in the initially compressed data, and perform re-data compression processing to generate re-compressed data; An information receiving module (803) is used to receive a plurality of reference video information input by a user, wherein there is a one-to-one mapping relationship between the plurality of reference video information and the categories for classifying the plurality of recorded video information; The identification adding module (804) is used to perform status identification processing on the multiple recorded video information currently received and classified according to the multiple reference video information, and add corresponding status identification; A comparison module (805) is used to compare the target control video information with the target recorded video information received within a preset unit time before the current moment; If there is a static difference region of static matter between the target control video information and the target recorded video information, and according to the static difference region and the static change information corresponding to the target control video information input by the user, a static object state identifier corresponding to the target recorded video information is generated; If there is a dynamic difference region of dynamic matter between the target control video information and the target recorded video information, and according to the dynamic difference region and a preset dynamic offset threshold, a dynamic object state identifier corresponding to the target recorded video information is generated.

7. An intelligent terminal, characterized in that: The intelligent terminal includes a processor and a memory, wherein the memory stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by the processor to implement the computer information processing method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: The storage medium stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by the processor to implement the computer information processing method as described in any one of claims 1 to 5.

Images