Laboratory monitoring method, apparatus, electronic device, and storage medium

Abstract

The present application relates to a kind of laboratory monitoring method, device, electronic equipment and storage medium, the method comprises: obtaining first vector and second vector, second vector is the vector obtained according to current time user experiment action, first vector is the vector obtained according to previous time user experiment action;The similarity of both is obtained based on first vector and second vector, and the similarity is compared with baseline threshold to judge whether abnormal action is produced, baseline threshold is preset abnormal action judging standard;When judging abnormal action occurs, alarm is carried out.The laboratory monitoring method, device, electronic equipment and storage medium described above, according to the comparison of the similarity obtained and limit threshold, whether abnormal action can be judged.The method can judge the abnormal behavior of personnel in laboratory according to preset personnel operation requirement, so as to achieve better monitoring effect, avoid the situation that does not meet the operation requirement appears in experiment process, and safety is better.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of monitoring, in particular to a laboratory monitoring method and device, electronic equipment and storage medium. BACKGROUND

[0002] The existing laboratory safety management system has a monitoring system for external elements such as environmental instruments, but lacks monitoring of human behavior factors, and different behavior white lists and black lists are required for different scenarios, so it is difficult to monitor human behavior factors.

[0003] Taking a PCR laboratory as an example, a PCR laboratory is also known as a gene amplification laboratory. In recent years, with the application of analytical biology in the medical field gradually occupying a dominant position, more and more medical institutions are building PCR laboratories. Compared with conventional laboratories, PCR laboratories have higher requirements, including, for example, the need to have a standard PCR fluorescence laboratory, detection equipment must meet the standard PCR fluorescence laboratory setting requirements, must pass the acceptance of the national clinical test center, detection personnel must pass the business training of the clinical test center and obtain a qualified certificate, and must be operated correctly in a sterile and dust-free environment. Among the above requirements, the monitoring of the operation steps of the detection personnel is more difficult. SUMMARY

[0004] Therefore, it is necessary to provide a laboratory monitoring method, device, electronic equipment and storage medium to solve the above technical problems, which can judge the abnormal behavior of personnel in the laboratory according to the preset personnel operation requirements, so as to achieve better monitoring effect and avoid the occurrence of operation requirements in the experiment process. It is safer.

[0005] In a first aspect, the present application provides a laboratory monitoring method, the method comprising:

[0006] obtaining a first vector and a second vector, the second vector being a vector obtained according to the user's experimental action at the current time, and the first vector being a vector obtained according to the user's experimental action at the previous time;

[0007] obtaining the similarity of the first vector and the second vector, and comparing the similarity with a baseline threshold to determine whether an abnormal action occurs, the baseline threshold being a preset abnormal action judgment standard;

[0008] When it is determined that the abnormal action occurs, an alarm is given.

[0009] In one embodiment, the method further comprises:

[0010] Obtaining a laboratory base model according to a point cloud image of an internal space of a laboratory having preset positioning points.

[0011] In one of the embodiments, the method further comprises:

[0012] Based on the number of the first vectors obtained at a previous time, the first vector farthest from the current time is removed.

[0013] In one of the embodiments, the obtaining of the similarity between the first vector and the second vector further comprises:

[0014] Based on the preset scores of the first vectors, the expected scores of the first vectors are obtained.

[0015] Based on the acquisition time and the number of the first vectors, the expected scores of the first vectors are weighted to obtain the actual scores of the first vectors.

[0016] In one of the embodiments, the obtaining of the similarity between the first vector and the second vector comprises:

[0017] Based on the actual scores of the first vectors, the average value of the actual scores of the first vectors is obtained.

[0018] Based on the average value of the actual scores, the similarity between the second vector and the first vector is obtained.

[0019] In one of the embodiments, the comparison of the similarity with the baseline threshold to determine whether an abnormal action occurs comprises:

[0020] The similarity between the first vector and the second vector is arranged linearly to obtain a similarity line.

[0021] Based on the intersection position of the baseline threshold and the similarity line, it is determined that the abnormal action exists on both sides of the intersection position.

[0022] In one of the embodiments, the comparison of the similarity with the baseline threshold to determine whether an abnormal action occurs further comprises:

[0023] When the intersection angle of the baseline threshold and the similarity line is greater than a first set angle value, it is determined that the abnormal action may exist;

[0024] When the intersection angle of the baseline threshold and the similarity line is greater than a second set angle value, it is determined that the abnormal action exists, and the second set angle value is greater than the first set angle value.

[0025] In a second aspect, the present application further provides a laboratory monitoring device, the device comprising:

[0026] an acquisition module configured to acquire a first vector and a second vector, the second vector being a vector obtained according to a user's experimental action at a current time, and the first vector being a vector obtained according to a user's experimental action at a previous time;

[0027] a first calculation module configured to obtain a similarity between the first vector and the second vector, and compare the similarity with a baseline threshold to determine whether an abnormal action occurs, the baseline threshold being a preset abnormal action determination criterion;

[0028] an alarm module configured to alarm when the abnormal action is determined to occur.

[0029] In a third aspect, the present application further provides an electronic device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the laboratory monitoring method according to any one of the above aspects when executing the computer program.

[0030] In a fourth aspect, the present application further provides a computer storage medium storing a computer program, the computer program being executed by a processor to implement the laboratory monitoring method according to any one of the above aspects.

[0031] In a fifth aspect, the present application further provides a computer program product comprising a computer program, the computer program being executed by a processor to implement the laboratory monitoring method according to any one of the above aspects.

[0032] The laboratory monitoring method, device, electronic device and storage medium described above can compare the second vector obtained according to a user's experimental action at a current time with the first vector obtained according to a user's experimental action at a previous time, since both are vectors, the difference between the vectors can be calculated to obtain the similarity between the first vector and the second vector, and then the obtained similarity is compared with a limit threshold, so that it can be determined whether there is an abnormal action in the operation steps of the experimental personnel. This method can determine the abnormal behavior of the personnel in the laboratory according to the preset personnel operation requirements, so as to achieve better monitoring effect, avoid the situation that the experimental process does not meet the operation requirements, and improve the safety. BRIEF DESCRIPTION OF DRAWINGS

[0033] In order to more clearly illustrate the technical solutions in the present application or the prior art, the following will briefly introduce the drawings needed in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor.

[0034] Figure 1 Figure 1 is a flow chart of a laboratory monitoring method according to an embodiment of the present application;

[0035] Figure 2 Figure 2 is a flow chart of a laboratory monitoring method according to another embodiment of the present application;

[0036] Figure 3 Figure 3 is a flow chart of a laboratory monitoring method according to another embodiment of the present application;

[0037] Figure 4 Figure 4 is a flow chart of a laboratory monitoring method according to another embodiment of the present application;

[0038] Figure 5 Figure 5 is a flow chart of a laboratory monitoring method according to another embodiment of the present application;

[0039] Figure 6 Figure 6 is a block diagram of a laboratory monitoring device according to an embodiment of the present application;

[0040] Figure 7 Figure 7 is a schematic diagram of a laboratory base model according to an embodiment of the present application;

[0041] Figure 8 Figure 8 is a schematic diagram of an abnormal action determination according to an embodiment of the present application;

[0042] Figure 9 Figure 9 is a block diagram of the internal structure of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0043] In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings of the embodiments of the present application. Obviously, the described embodiments are some but not all of the embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of the present application.

[0044] The embodiments of the present application will be described below with reference to the drawings. Figures 1-9 The laboratory monitoring method, device, electronic device and storage medium of the present application are described.

[0045] As shown in FIG. 1, in one embodiment, a laboratory monitoring method includes the following steps: Figure 1

[0046] In step S110, a first vector and a second vector are obtained. The second vector is a vector obtained according to the user's experimental action at the current time, and the first vector is a vector obtained according to the user's experimental action at the previous time.

[0047] ​Specifically, during the process of an experiment, the experimenter will perform a plurality of continuous operations. Assuming that when performing an experiment, the experimenter needs to perform 1 to 6 steps of operation in sequence, and by combining the 6 steps and taking an absolute coordinate origin as the calculation reference of the step vector, the vector of the experimenter's operation steps can be obtained.

[0048] In step S120, the similarity of the first vector and the second vector is obtained, and the similarity is compared with a baseline threshold to determine whether an abnormal action occurs. The baseline threshold is a preset abnormal action judgment standard.

[0049] Specifically, since the first vector and the second vector are the same in the operation steps, the difference between them is only the difference in the acquisition time, so the first vector can be regarded as the reference of the second vector. Since the experimenter's action may differ when performing the operation steps, the difference between the first vector and the second vector needs to be calculated by combining the numerical value of the vector, so as to judge the similarity of the two. Specifically, the cosine similarity can be used for similarity calculation. Then, according to the set baseline threshold, the similarity is compared, and it can be judged whether an abnormal action occurs. The baseline threshold is a reference threshold for judging whether an abnormal action exists.

[0050] In step S130, when it is judged that an abnormal action occurs, an alarm is given.

[0051] The above laboratory monitoring method compares the second vector obtained according to the current time user experiment action with the first vector obtained according to the previous time user experiment work. Since both are vectors, the difference between the vectors can be calculated to obtain the similarity between the first vector and the second vector. Then, according to the obtained similarity and the limit threshold, it can be judged whether there is an abnormal action in the operation steps of the experimenter. This method can judge the abnormal behavior of the personnel in the laboratory according to the preset personnel operation requirements, so as to achieve better monitoring effect, avoid the situation that the experiment process does not meet the operation requirements, and better safety.

[0052] In one embodiment, the first vector and the second vector are obtained, and the previous steps further include the following steps:

[0053] The laboratory basic model is obtained according to the point cloud image of the internal space of the laboratory with the preset positioning point.

[0054] Specifically, before the point cloud is acquired, the auxiliary guide wire is arranged to pass through the laboratory space, and the two ends of the auxiliary guide wire are located outside the laboratory space. Then, a positioning point is determined on the auxiliary guide wire, and the positioning point is located between the two ends of the auxiliary guide wire and in the laboratory space. The absolute position coordinates of the positioning point can be determined according to the absolute position coordinates of the two end points of the auxiliary guide wire. Since the absolute position coordinates of the positioning point are determined, the reference coordinate system can be determined according to the absolute position coordinates of the positioning point. Then, the position coordinates of each position in the laboratory can be calculated according to the reference coordinate system, so as to create a basic model of the laboratory. The basic model of the laboratory created is shown in FIG. 1. The process of creating the basic model includes determining the point cloud coordinates of the laboratory space, then importing the coordinate data into 3D max for modeling to obtain the basic model of the laboratory. In order to make the basic model of the laboratory created more similar to the real laboratory, the texture pictures of the internal space of the laboratory need to be acquired, and then the acquired texture pictures are attached to the surface of the basic model of the laboratory, so as to form the same laboratory model as the real laboratory. Figure 7

[0055] In one embodiment, the method further includes the following steps:

[0056] Based on the number of the plurality of first vectors obtained at the previous time, the first vector farthest from the current time is removed.

[0057] Specifically, it is assumed that the vectors are recorded from the initial operation of the experimental personnel. As the number of experiments of the experimental personnel increases, the proficiency and operation standardization will be stronger, so the first vector farthest from the current time can be defaulted as the operation step with poor reference. By removing the operation step with poor reference, the accuracy of the subsequent operation step comparison for abnormal motion judgment can be ensured. Specifically, a sliding window can be set to remove the vectors beyond the time range.

[0058] As shown in FIG. 2, in one embodiment, the similarity of the first vector and the second vector is obtained, and the method further includes the following steps: Figure 2

[0059] Step S210, obtaining the predicted score of each first vector based on the preset score of the plurality of first vectors.

[0060] Specifically, as shown in FIG. 3, the abscissa in the figure represents a plurality of vectors of a certain step. Since the importance of different vectors in different operations is different, the score of each vector can be set according to the importance. Figure 8

[0061] Step S220, performing weighted calculation on the predicted score of the first vector based on the acquisition time and the acquisition number of the first vector to obtain the actual score of the first vector. ​​​

[0062] Specifically, assuming vectors are recorded starting from the experimenter's initial operation, as the number of experiments increases, their proficiency and operational standardization will also improve. Therefore, the first vector furthest from the current time can be considered a less reliable operational step. Since vector similarity comparison involves comparing the current second vector with multiple previous first vectors, assigning the highest weight to the first vector closest to the current time and the lowest weight to the first vector furthest from the current time ensures the accuracy of identifying abnormal actions during subsequent comparisons of operational steps.

[0063] like Figure 3 As shown, in one embodiment, the similarity between the two vectors is obtained based on the first vector and the second vector, including the following steps:

[0064] Step S 310: Calculate the average of the actual scores of the first vectors based on the actual scores of the multiple first vectors.

[0065] Specifically, since each step has a set score, the scores of the same steps are added together and then averaged, which can be used for comparison of the second vector.

[0066] Step S320: Calculate the similarity between the second vector and the first vector based on the average of the actual scores.

[0067] like Figure 4 As shown, in one embodiment, comparing the similarity with a baseline threshold to determine whether an abnormal action has occurred includes the following steps:

[0068] Step S 410: Arrange the similarity of the first vector and the second vector in a linear fashion to obtain a similarity line.

[0069] Specifically, such as Figure 8 As shown, the operation consists of 6 steps, and the similarity between the second vector and the first vector in the 6 steps are 90%, 80%, 100%, 80%, and 90%, respectively. It should be noted that since vector differences can be positive or negative, although there are two 80% similarity values ​​in this figure, these two points represent different meanings.

[0070] Step S 420: Determine whether the abnormal action exists on both sides of the intersection position based on the intersection position of the baseline threshold and the similarity line.

[0071] Specifically, when the similarity line intersects with the baseline threshold, abnormal actions may occur in the two adjacent steps centered on that intersection point.

[0072] like Figure 5As shown, in one embodiment, the similarity is compared with the baseline threshold to determine whether an abnormal action is generated, and further includes the following steps:

[0073] Step S 510, when the intersection angle between the baseline threshold and the similarity line is greater than a first set angle value, it is determined that there may be an abnormal action.

[0074] Step S 520, when the intersection angle between the baseline threshold and the similarity line is greater than a second set angle value, it is determined that there is an abnormal action, and the second set angle value is greater than the first set angle value.

[0075] Specifically, as shown, Figure 8 The line with a vertical coordinate of 100% represents the baseline threshold. Since the intersection point of the similarity line and the baseline threshold can preliminarily determine the step in which the abnormal action is located, and then the inclination angle of the similarity line can determine the degree of similarity change in the step, if the degree of change is too large, the step is likely to have an abnormal action. The first set angle value can be set to 30 degrees, the second set angle value can be set to 60 degrees, and the baseline threshold can be represented by a neural network receiving similarity as input.

[0076] It should be noted that the partitioning of the clinical PCR laboratory and the configuration of the equipment are clearly specified in the "Provisional Measures for the Management of Clinical Gene Amplification Test Laboratories", "Measures for the Management of Clinical Gene Amplification Laboratories in Medical Institutions", and "Guidelines for the Work of Clinical Gene Amplification Laboratories in Medical Institutions" issued by the Ministry of Health. The functions and precautions of each zone are also described. In this embodiment, the laboratory is constructed in accordance with the corresponding regulations, in order to better monitor the workflow and overall work requirements of each zone in the laboratory, three abnormality recognition methods for instrument abnormalities, personnel abnormalities, and environmental abnormalities are designed. Among them:

[0077] Instrument abnormalities include:

[0078] 1. Instrument automatic early warning: mark the instrument in the laboratory modeling coordinates. If the instrument automatically warns, the signal converter automatically converts the instrument warning into a system warning. According to the coordinates, the position of the instrument is identified, and the laboratory personnel and responsible personnel are notified to handle.

[0079] 2. Use error warning: image recognition monitoring within the range established according to the modeling coordinates, including but not limited to: reagent dispensing error, use of extraction instrument error, use of amplification instrument error.

[0080] Personnel abnormalities include:

[0081] 1. Pre-experimental behavior abnormalities:

[0082] According to the experimental preparation of entering the coordinate point, the specific position monitoring is carried out, including but not limited to: abnormal entry path, that is, the establishment of entrance and exit reference coordinates, the identification of face orientation by image recognition system and the monitoring of coordinate movement position by positioning system, the path of personnel and articles can only be from the entrance coordinate to the exit coordinate direction, and cannot return.

[0083] Abnormal dress, specify the color of clothes in the coordinate range, identify the color of clothes through image recognition and coordinate positioning.

[0084] Abnormal protection specification, whether to wear a medical mask, cap, detect the identity information of abnormal behavior through face recognition, trigger signal to the corresponding locator, and the locator sends information to the monitoring platform.

[0085] 2, abnormal behavior in the laboratory:

[0086] Experimental action abnormality: determine the coordinate positioning of the first vector action in the experiment (according to the project setting, add sample, select the corresponding extraction program, take the corresponding project reaction liquid, set the sample amount specified by the project, add the extracted sample to the prepared reaction liquid, shake and mix, observe whether there are bubbles, and put the sample into the delivery window for machine amplification. According to the formula

[0087]

[0088] Calculate the similarity of action and first vector in the experiment, and trigger a warning when the similarity is less than 50%. Wherein A and B are two coordinates of the vector.

[0089] Abnormality of delivery path: determine that the delivery path of the article can only be from the reagent preparation area delivery window-sample preparation area delivery window-product amplification analysis area delivery window, monitor the delivery path with image monitoring device; Install the locator (pipette, sharp box, EP tube plate, 96-hole yellow plate, garbage can, mop) for non-movable articles, and trigger an alarm when the coordinates move out of the region.

[0090] Abnormal use of biological safety cabinet: the Ⅱ class biological safety cabinet used in the department is connected with the exhaust system, and the fan connected with the exhaust duct of the safety cabinet needs to be connected with the emergency power supply (UPS). The purpose is to maintain the negative pressure of the safety cabinet under power failure, so as to prevent the aerosol generated during microbial operation from escaping from the front window. One of the unique features of the Ⅱ class biological safety cabinet is that the vertical laminar flow of air filtered by the HEPA filter blows down from the top of the safety cabinet, which is called "sinking air flow". The sinking air flow constantly blows through the working area of the safety cabinet to protect the specimens in the cabinet from being contaminated by external dust or bacteria, so the fan needs to be turned on during use. If the biological safety cabinet is not connected with UPS or the fan is not turned on during use, an alarm will be triggered.

[0091] 3, abnormal behavior after experiment:

[0092] Medical waste disposal exception: Set up special yellow garbage bag color and logo for disposal of garbage, image recognition equipment to identify, specify the movable coordinate range, beyond the range will trigger an early warning.

[0093] Exit path exception, that is, to establish entry and exit reference coordinates, through image recognition system to identify the face orientation and positioning system to monitor the coordinate movement position, the exit path of personnel and goods can only be from the entrance coordinate to the exit coordinate direction, and cannot return.

[0094] Disinfection exception: wipe disinfection or ultraviolet irradiation. If not executed, an early warning will be triggered, and it cannot be left.

[0095] Self-warning, such as personnel needing help or finding problems can automatically warn.

[0096] Environmental abnormalities include:

[0097] 1. Basic indicators: basic temperature, humidity, smoke monitoring.

[0098] 2. Laboratory designated indicators:

[0099] Air flow: The air flow of the PCR laboratory must strictly follow the reagent storage and preparation area → specimen preparation area → amplification area → amplification product analysis area air pressure gradually decreasing mode, to prevent the amplification product from entering the area before amplification along the air flow. The wind speed flow direction must not be chaotic. In order to ensure the pressure difference in the room and avoid pollution, the opening and closing order of the air supply and exhaust fans should be clearly written on the air conditioning panel, and the sequence must not be chaotic.

[0100] Pressure difference: The static pressure difference between adjacent rooms with different air cleanliness levels should be greater than 5 Pa, and the static pressure difference between the clean room (zone) and the outdoor atmosphere should be greater than 10 Pa, and the equipment for monitoring the static pressure difference should be equipped and monitored regularly. Generally, the reagent preparation room and the sample processing room are slightly positive, to prevent external nucleic acid aerosol-containing air from entering and causing pollution; positive pressure effect can be achieved by controlling the air intake greater than the air exhaust. The nucleic acid amplification room and the product analysis room are slightly negative, to prevent the diffusion of nucleic acid-containing aerosols from polluting reagents and samples, and negative pressure effect can be achieved by controlling the air exhaust greater than the air intake. In an ideal situation, the PCR laboratory buffer room can be set to positive pressure, so that the indoor air does not flow to the outside, and the outdoor air does not flow to the inside. The PCR laboratory air intake requires the original central air conditioning control to install the central air conditioning air outlet to the designated point.

[0101] 3. Disinfection indicators

[0102] Ultraviolet: Ozone concentration monitoring.

[0103] Alcohol: Environmental alcohol concentration monitoring.

[0104] The laboratory monitoring method in the embodiment sets monitoring for external elements such as environmental instruments, and different behavior white lists or black lists can be set for different scenarios, so that the safety and standardization of laboratory experiments can be ensured from aspects such as access control, environment, instruments, and behavior abnormalities, and laboratory safety problems can be fed back to the relevant person in charge in a timely manner.

[0105] The laboratory monitoring device provided by the application is described below, and the laboratory monitoring device described below can be correspondingly referred to the laboratory monitoring method described above.

[0106] As shown in Figure 6 In one embodiment, a laboratory monitoring device includes an acquisition module 610, a first calculation module 620, and an alarm module 630.

[0107] The acquisition module 610 is configured to acquire a first vector and a second vector, the second vector being a vector obtained according to user experimental actions at a current time, and the first vector being a vector obtained according to user experimental actions at a previous time.

[0108] The first calculation module 620 is configured to obtain a similarity between the first vector and the second vector, and compare the similarity with a baseline threshold to determine whether an abnormal action occurs, the baseline threshold being a preset abnormal action determination criterion.

[0109] The alarm module 630 is configured to alarm when an abnormal action occurs.

[0110] In one embodiment, the laboratory monitoring device further includes a creation module configured to:

[0111] Acquire a laboratory basic model, the laboratory basic model being obtained according to a point cloud image of an internal space of a laboratory with a preset positioning point.

[0112] In one embodiment, the laboratory monitoring device further includes a storage module configured to:

[0113] Remove the first vector farthest from the current time based on a number of the plurality of first vectors obtained at the previous time.

[0114] In one embodiment, the laboratory monitoring device further includes a second calculation module configured to:

[0115] Obtain an expected score of each first vector based on a preset score of the plurality of first vectors.

[0116] Weight the expected score of the first vector based on an acquisition time and an acquisition number of the first vector to obtain an actual score of the first vector.

[0117] In one embodiment, the first calculation module 620 is specifically configured to:

[0118] An average of the actual scores of the first vectors is obtained based on the actual scores of the plurality of first vectors.

[0119] A similarity between the second vector and the first vector is obtained based on the average of the actual scores.

[0120] In one embodiment, the first calculation module 620 is further configured to:

[0121] The similarity between the first vector and the second vector is arranged linearly to obtain a similarity line.

[0122] It is determined that the abnormal action exists on both sides of the intersection position based on the intersection position of the baseline threshold and the similarity line.

[0123] When the intersection angle of the baseline threshold and the similarity line is greater than a first set angle value, it is determined that there may be an abnormal action.

[0124] When the intersection angle of the baseline threshold and the similarity line is greater than a second set angle value, it is determined that there is an abnormal action, and the second set angle value is greater than the first set angle value.

[0125] Figure 9 An example of a schematic diagram of the physical structure of an electronic device is shown, which can be a smart terminal, and the internal structure diagram can be as shown in Figure 9 The electronic device includes a processor, a memory, and a network interface connected through a system bus. The processor of the electronic device is configured to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The network interface of the electronic device is configured to communicate with external terminals through network connection. The computer program is executed by the processor to implement a laboratory monitoring method, which includes:

[0126] A first vector and a second vector are obtained, the second vector is a vector obtained according to the user's experimental action at the current time, and the first vector is a vector obtained according to the user's experimental action at the previous time;

[0127] A similarity between the first vector and the second vector is obtained based on the first vector and the second vector, and the similarity is compared with a baseline threshold to determine whether an abnormal action occurs, the baseline threshold being a preset abnormal action determination standard;

[0128] When it is determined that an abnormal action occurs, an alarm is given.

[0129] Those skilled in the art can understand that, Figure 9The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the electronic device to which the scheme of the present application is applied. The specific electronic device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0130] In another aspect, the present application also provides a computer storage medium storing a computer program, the computer program being executed by a processor to implement a laboratory monitoring method, the method comprising:

[0131] obtaining a first vector and a second vector, the second vector being a vector obtained according to a user's experimental action at a current time, and the first vector being a vector obtained according to a user's experimental action at a previous time;

[0132] obtaining a similarity between the first vector and the second vector, and comparing the similarity with a baseline threshold to determine whether an abnormal action occurs, the baseline threshold being a preset abnormal action determination criterion;

[0133] when it is determined that an abnormal action occurs, performing an alarm.

[0134] In another aspect, the present application also provides a computer storage medium storing a computer program, the computer program being executed by a processor to implement a laboratory monitoring method, the method comprising:

[0135] obtaining a first vector and a second vector, the second vector being a vector obtained according to a user's experimental action at a current time, and the first vector being a vector obtained according to a user's experimental action at a previous time;

[0136] obtaining a similarity between the first vector and the second vector, and comparing the similarity with a baseline threshold to determine whether an abnormal action occurs, the baseline threshold being a preset abnormal action determination criterion;

[0137] when it is determined that an abnormal action occurs, performing an alarm.

[0138] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiment methods. Any reference to memory, storage, database or other medium used in the embodiments provided by the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory.

[0139] By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0140] The technical features of the above embodiments can be combined in any way. In order to make the description simple, not all possible combinations of the technical features in the above embodiments are described, but as long as the combination of the technical features does not exist, it should be considered as the scope of the present application.

[0141] The above embodiments only express several embodiments of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent of the present application. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are within the scope of protection of the present application. Therefore, the scope of protection of the patent of the present application should be subject to the appended claims.

Claims

1. A laboratory monitoring method, characterized in that, The method includes: Obtain a first vector and a second vector, wherein the second vector is a vector obtained based on the user's experimental actions at the current moment, and the first vector is a vector obtained based on the user's experimental actions at a previous moment; The similarity between the first vector and the second vector is obtained, and the similarity is compared with a baseline threshold to determine whether an abnormal action has occurred. The baseline threshold is a preset abnormal action judgment standard. An alarm will be triggered when the abnormal action is detected. The step of obtaining the similarity between the two vectors based on the first vector and the second vector includes, prior to: The predicted score of each first vector is obtained based on multiple preset scores of the first vector; The predicted score of the first vector is calculated by weighting the acquisition time and the number of acquisitions of the first vector, and the actual score of the first vector is obtained. The step of obtaining the similarity between the two based on the first vector and the second vector includes: The average of the actual scores of the first vector is obtained based on the actual scores of multiple first vectors; The similarity between the second vector and the first vector is obtained based on the average of the actual scores; The step of comparing the similarity with a baseline threshold to determine whether an abnormal action has occurred includes: The similarity scores of the first vector and the second vector are arranged linearly to obtain a similarity line; Based on the intersection of the baseline threshold and the similarity line, it is determined that the abnormal action exists on both sides of the intersection.

2. The laboratory monitoring method according to claim 1, characterized in that, Prior to obtaining the first vector and the second vector, the process further includes: A basic model of the laboratory is obtained, which is based on a point cloud image of the interior space of the laboratory with preset positioning points.

3. The laboratory monitoring method according to claim 1, characterized in that, The method further includes: Based on the number of the first vectors obtained at previous times, the first vector that is furthest from the current time is removed.

4. The laboratory monitoring method according to claim 1, characterized in that, The step of comparing the similarity with a baseline threshold to determine whether an abnormal action has occurred further includes: When the intersection angle between the baseline threshold and the similarity line is greater than the first set angle value, it is determined that the abnormal action may exist. When the intersection angle between the baseline threshold and the similarity line is greater than the second set angle value, it is determined that there is an abnormal action, and the second set angle value is greater than the first set angle value.

5. A laboratory monitoring device, characterized in that, The apparatus for applying the laboratory monitoring method according to any one of claims 1-4 comprises: The acquisition module is used to acquire a first vector and a second vector, wherein the second vector is a vector obtained based on the user's experimental actions at the current moment, and the first vector is a vector obtained based on the user's experimental actions at a previous moment; The first calculation module is used to obtain the similarity between the first vector and the second vector, and compare the similarity with a baseline threshold to determine whether an abnormal action has occurred. The baseline threshold is a preset abnormal action judgment standard. An alarm module is used to issue an alarm when the abnormal action is detected.

6. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 4.

7. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.

Images