System and method based on laboratory process intelligent management

Abstract

The invention discloses a system and a method based on laboratory process intelligent management, and relates to the technical field of intelligent management. The system comprises an experiment task classification and sorting module, a historical data analysis and task duration prediction module, an overlapping time period analysis and intelligent scheduling module and a real-time monitoring and task progress adjustment module. The experiment task classification and sorting module is responsible for acquiring an initial experiment task list and carrying out task classification and sorting; the historical data analysis and task duration prediction module predicts the total duration of the experiment task by using historical data and provides accurate task duration prediction; time overlapping between the overlapping time period analysis and intelligent scheduling module processing tasks is carried out, and the task execution sequence and the equipment use time are intelligently adjusted; and the real-time monitoring and task progress adjusting module tracks the task execution condition in real time, analyzes the actual and predicted deviation and carries out necessary progress adjustment.

Description

Technical Field

[0001] The present invention relates to the field of intelligent management technology, and in particular to a system and method based on intelligent management of laboratory processes. Background Art

[0002] In modern scientific research and industrial experiments, laboratories are the core places for various scientific research, technology verification, product development and other important activities. Laboratory management involves the scheduling and management of resources such as laboratory equipment, experimental processes and experimental data. The traditional laboratory management model usually relies on manual arrangements, especially in the resource scheduling of equipment, which often has many shortcomings. First of all, the use and scheduling of laboratory equipment usually rely on manual management; due to the large variety of experimental tasks and the large differences in their respective needs, it is difficult to achieve real-time and accurate adjustment of the equipment's use period and experimental arrangement; in addition, when multiple experimental tasks need to use the same equipment, the equipment's use period may overlap, resulting in delays in the progress of the experiment.

[0003] In this context, many laboratories and scientific research institutions have gradually begun to use equipment reservation systems to manage laboratory equipment, usually using a fixed reservation method based on time periods, so that experimenters can view the available time of the equipment and make reservations. However, existing equipment reservation systems often lack a flexible scheduling mechanism and cannot dynamically adjust the available time period of the equipment according to the actual execution time of the experimental task. When an experimental task cannot be completed as planned due to timeout or other reasons, the system cannot automatically adjust the reservation time of subsequent tasks, resulting in a shortened available time for the subsequent scheduled experimental tasks, thus affecting the overall progress of the laboratory. Summary of the invention

[0004] The purpose of the present invention is to provide a system and method based on intelligent management of laboratory processes to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: A method based on intelligent management of laboratory processes, comprising the following steps: Step S100. Obtain an initial experimental task list from the laboratory management platform, classify the experimental tasks in the initial experimental task list by analyzing the initial experimental task list, and divide them into several experimental task types; for each experimental task type, combine the initial experimental task list to generate an initial experimental task ranking list; Step S200. For each experiment type, based on the corresponding initial experiment task ranking list, obtain the corresponding historical experiment data, associate the historical experiment data with the experiment tasks in the initial experiment task ranking list; analyze the association results to obtain the predicted total duration of the experiment tasks in the initial experiment task ranking list; Step S300. Based on the predicted total duration of the experimental tasks in the initial experimental task sorting list, identify the target experimental task pairs; analyze the target experimental task pairs to obtain the overlapping time periods of the target experimental task pairs, and intelligently allocate the usage order of the same experimental equipment of the target experimental task pairs in the overlapping time periods, and analyze and adjust the reservation time periods of subsequent experimental tasks accordingly; Step S400. Perform the experimental tasks in the order of the initial experimental task sorting list. After completing each experimental task, obtain the corresponding actual total duration, and compare the actual total duration of the corresponding experimental task with the predicted total duration to obtain the deviation between the two; and according to the deviation between the actual total duration of the currently completed experimental task and the predicted total duration, perform corresponding analysis and adjustments on the unfinished experimental tasks in the current initial experimental task sorting list.

[0006] Furthermore, step S100 includes: S101. Obtain an initial experimental task list from the laboratory management platform, wherein the initial experimental task list records specific description information of the experimental tasks; extract the experimental task number from the initial experimental task list, and each experimental task number is unique; for each experimental task, extract the corresponding required experimental equipment name from the initial experimental task list, and convert the required experimental equipment name into a unified vector format, thereby forming a required experimental equipment vector X_ID, and X_ID=[x1,x2,...,xn], wherein X_ID represents the required experimental equipment vector of the experimental task ID, x1 represents the first dimension eigenvalue of the required experimental equipment vector, x2 represents the second dimension eigenvalue of the required experimental equipment vector, and so on, xn represents the nth dimension eigenvalue of the required experimental equipment vector, wherein n represents the type of experimental equipment present in the laboratory; S102. Summarize the experimental equipment vectors required for all experimental tasks in the initial experimental task list, and calculate the similarity between the experimental equipment vector required for each experimental task and other required experimental equipment vectors in turn, and the corresponding calculation formula is: S(X_a,X_b)=|X_a∩X_b| / n; Where S(X_a,X_b) represents the similarity between the required experimental equipment vectors corresponding to experimental task a and experimental task b, and |X_a∩X_b| represents the number of the same dimension feature values ​​in the required experimental equipment vectors corresponding to experimental task a and experimental task b; those with similarities not equal to 0 are classified into one category, and all experimental tasks in the initial experimental task list are traversed, so as to divide the experimental tasks in the initial experimental task list into several experimental task types; S103. For each type of experimental task, obtain the specific description information of the corresponding experimental task from the initial experimental task list, obtain the appointment time period T0 of the corresponding experimental task according to the specific description information of the experimental task, and generate the initial experimental task sorting list of the corresponding experimental task type according to the sequence of the starting timestamps of the appointment time period T0 of the experimental task.

[0007] Further, step S200 includes: S201. For each experiment type, based on the corresponding initial experiment task sorting list, obtain the historical experiment data of each experiment task in the initial experiment task sorting list from the laboratory management platform; for each experiment task, associate the experiment task number with the corresponding historical experiment data to obtain the required experiment equipment sequence F, and F={f1,f2,..,fm}, where f1 represents the name of the first experiment equipment used in the experiment task, f2 represents the name of the second experiment equipment used in the experiment task, and so on, fm represents the name of the mth experiment equipment used in the experiment task, and m represents the number of experiment equipment used in the experiment task; S202. According to the required experimental equipment sequence F and in combination with the historical experimental data of the corresponding experimental task, calculate the average usage time μt and standard deviation σt of each experimental equipment in the required experimental equipment sequence F in the historical experimental data, so as to obtain the predicted usage time tf of the corresponding experimental equipment, and tf=μt+α·σt, where α represents the adjustment coefficient, which can be adjusted according to the actual situation of the task (for example, based on the frequency of use of the equipment or the complexity of the experiment); summarize the usage time tf of all experimental equipment in the required experimental equipment sequence F, so as to obtain the predicted total duration sum_tf of the corresponding experimental task.

[0008] Furthermore, step S300 includes: S301. Based on the initial experimental task sorting list, extract the predicted total duration of all experimental tasks in the initial experimental task sorting list, extract the starting timestamp of the appointment time period of each experimental task in the initial experimental task sorting list, and express it as t0; calculate the predicted time period T1 of each experimental task in the initial experimental task sorting list, and T1=[t0,t0+sum_tf]; according to the order of the initial experimental task sorting list, combined with the predicted total duration of all experimental tasks, refer to the calculation method of the predicted time period T1 of the first experimental task, and calculate the predicted time periods Ti of other experimental tasks in the initial experimental task sorting list in sequence, where i represents the sequence number of other experimental tasks; S302. Summarize the predicted time periods of all experimental tasks in the initial experimental task sorting list, and sort the predicted time periods of all experimental tasks according to the order of the initial experimental task sorting list; determine in turn whether there is an overlapping relationship between the predicted time periods of two adjacent experimental tasks in the initial experimental task sorting list, extract the experimental task numbers of all overlapping relationships, record them as target experimental task pairs, and express them as (IDj, IDj+1), where j represents the sequence number of the experimental task in the initial experimental task sorting list; summarize all target experimental task pairs to form a target experimental task set E, and E={e1,e2,...,ev}, where e1 represents the first target experimental task pair, e2 represents the second target experimental task pair, and so on, ev represents the vth target experimental task pair; S303. For each target experimental task pair in the target experimental task set E, calculate the overlap period Tc of the predicted time period of the target experimental task pair; based on the experimental task number of the target experimental task pair, respectively obtain the corresponding required experimental equipment sequence and the predicted usage time of each experimental equipment in the required experimental equipment sequence; according to the overlap period Tc, find the required experimental equipment of the target experimental task pair in the overlap period Tc; if the required experimental equipment corresponding to the two adjacent experimental tasks in the target experimental task pair are different, no processing is performed .... If the equipment is the same, compare the timestamps of the two adjacent experimental tasks in the target experimental task pair when using the experimental equipment, determine the order of using the experimental equipment according to the sequence of timestamps, and calculate the predicted timestamp t1 of the completion of the target experimental task pair according to the order of using the experimental equipment. If the predicted timestamp t1 is greater than the initial timestamp t0 of the appointment time period of the next experimental task in the initial experimental task sorting list, then the appointment time period of the subsequent experimental tasks will be postponed by the time span of t1-t0 in sequence, and the adjusted appointment time period will be output to the relevant personnel for confirmation and adjustment; otherwise, no adjustment will be made.

[0009] Furthermore, step S400 includes: Perform the experimental tasks in sequence according to the order of the initial experimental task sorting list. After each experimental task is completed, obtain the corresponding actual total duration ts, compare the actual total duration of the corresponding experimental task with the predicted total duration, and obtain the deviation △t=ts-sum_tf between the two; if △t is greater than 0, obtain the unfinished experimental task sequence W in the current initial experimental task sorting list, and analyze and adjust each experimental task in the unfinished experimental task sequence W with reference to the analysis process in step S300; if △t is less than or equal to 0, do not perform any processing.

[0010] A system based on intelligent management of laboratory processes, including: experimental task classification and sorting module, historical data analysis and task duration prediction module, overlapping time period analysis and intelligent scheduling module, and real-time monitoring and task progress adjustment module; The experimental task classification and sorting module obtains the initial experimental task list from the laboratory management platform, classifies the experimental tasks in the initial experimental task list by analyzing the initial experimental task list, and divides them into several experimental task types; for each experimental task type, combined with the initial experimental task list, generates an initial experimental task sorting list; The historical data analysis and task duration prediction module obtains the corresponding historical experimental data for each experiment type based on the corresponding initial experimental task ranking list, and associates the historical experimental data with the experimental tasks in the initial experimental task ranking list; analyzes the association results to obtain the predicted total duration of the experimental tasks in the initial experimental task ranking list; The overlapping time period analysis and intelligent scheduling module identifies the target experimental task pairs based on the predicted total duration of the experimental tasks in the initial experimental task sorting list; analyzes the target experimental task pairs to obtain the overlapping time periods of the target experimental task pairs, and intelligently allocates the usage order of the same experimental equipment of the target experimental task pairs in the overlapping time periods, and analyzes and adjusts the reservation time periods of subsequent experimental tasks accordingly; The real-time monitoring and task progress adjustment module performs experimental tasks in the order of the initial experimental task sorting list. After each experimental task is completed, the corresponding actual total duration is obtained, and the actual total duration of the corresponding experimental task is compared with the predicted total duration to obtain the deviation between the two; and according to the deviation between the actual total duration of the currently completed experimental task and the predicted total duration, the unfinished experimental tasks in the current initial experimental task sorting list are analyzed and adjusted accordingly.

[0011] Furthermore, the experimental task classification and ranking module includes a data collection unit, a task classification unit, and ranking list generation; The data collection unit obtains the initial experimental task list from the laboratory management platform, and the initial experimental task list records the specific description information of the experimental tasks; the task classification unit classifies the experimental tasks by analyzing the experimental equipment information required for the experimental tasks and using the similarity calculation method; the sorted list is generated for each experimental task type, and the experimental tasks corresponding to each experimental task type are sorted based on the appointment time period of the experimental tasks, thereby generating an initial experimental task sorting list.

[0012] Further, the historical data analysis and task duration prediction module includes a historical data association analysis unit and a task duration prediction unit; The historical data association analysis unit obtains historical experimental data from the laboratory management platform and associates it with the experimental tasks in the initial experimental task sorting list; by analyzing the historical data, the required experimental equipment sequence for each experimental task is obtained; the task duration prediction unit calculates the predicted usage time of the corresponding experimental equipment based on the required experimental equipment sequence and the historical experimental data of the corresponding experimental task; the usage time of all experimental equipment in the required experimental equipment sequence is summarized to obtain the predicted total duration of the corresponding experimental task.

[0013] Further, the overlapping period analysis and intelligent scheduling module includes an overlapping period analysis unit and an intelligent scheduling unit; The overlapping period analysis unit analyzes whether there is time overlap between experimental tasks based on the predicted duration and reservation period of the experimental tasks, identifies and extracts target experimental task pairs; the intelligent scheduling unit schedules the target experimental task pairs based on the usage order of the same equipment, and predicts the task completion time of the overlapping period; if there is a delay, the reservation period of the subsequent tasks is intelligently adjusted, and the adjustment information is output for relevant personnel to confirm and modify.

[0014] The progress monitoring unit performs the experimental tasks in the order of the initial experimental task sorting list, and obtains the corresponding actual total duration after completing each experimental task; the task adjustment unit compares the actual total duration of the corresponding experimental task with the predicted total duration to obtain the deviation between the two; and based on the deviation between the actual total duration of the currently completed experimental task and the predicted total duration, the unfinished experimental tasks in the current initial experimental task sorting list are analyzed and adjusted accordingly.

[0015] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention realizes the dynamic adjustment of experimental tasks through intelligent analysis based on historical experimental data and predicted total duration; unlike the traditional fixed time period reservation system, the system can automatically adjust the use period of the equipment according to the actual progress of the experimental task, thereby avoiding the shortening of the subsequent task time or equipment conflict caused by the delay of the experimental task, and ensuring that the overall progress of the laboratory is more accurate. The intelligent scheduling mechanism proposed in the present invention can automatically adjust the use arrangement of the equipment by analyzing the overlapping time periods of the experimental tasks and the use order of the experimental equipment. In particular, when multiple experimental tasks need to share the same equipment, the use order can be intelligently allocated according to the actual situation, reducing human intervention and improving the utilization efficiency of the equipment. Traditional laboratory equipment scheduling relies on manual management, which is prone to omissions and inefficiency; while the present invention reduces the workload of manual scheduling and processing through intelligent management processes, improves management efficiency, and effectively reduces the risk of equipment conflicts and experimental task delays caused by human errors. Through the analysis and prediction of historical experimental data, the present invention can accurately calculate the total duration of each experimental task, and make corresponding adjustments to the subsequent tasks according to the actual completion situation, minimizing the adverse effects caused by the uncertainty of the experimental time, thereby improving the accuracy and completion rate of the experimental tasks. The present invention makes full use of the idle time of each device through intelligent scheduling and dynamic adjustment of experimental equipment, reduces the idle and waiting time of equipment, and improves the utilization rate of equipment; at the same time, it reasonably adjusts the appointment time period of experimental tasks to avoid the waste of resources caused by task conflicts and improper scheduling. By combining the deviation between the predicted and actual completion time, the present invention can timely discover and correct the deviation in the experimental progress and ensure that the experimental tasks are completed on time; the system can automatically adjust the arrangement of subsequent tasks according to the actual progress during the experiment, making the laboratory progress more stable and controllable. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings: Figure 1 It is a module schematic diagram of a system based on intelligent management of laboratory processes of the present invention. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] See also Figure 1 , the present invention provides a technical solution: A system based on intelligent management of laboratory processes, including: experimental task classification and sorting module, historical data analysis and task duration prediction module, overlapping time period analysis and intelligent scheduling module, and real-time monitoring and task progress adjustment module; The experimental task classification and sorting module obtains the initial experimental task list from the laboratory management platform, classifies the experimental tasks in the initial experimental task list by analyzing the initial experimental task list, and divides them into several experimental task types; for each experimental task type, combined with the initial experimental task list, generates an initial experimental task sorting list; The historical data analysis and task duration prediction module obtains the corresponding historical experimental data for each experiment type based on the corresponding initial experimental task ranking list, and associates the historical experimental data with the experimental tasks in the initial experimental task ranking list; analyzes the association results to obtain the predicted total duration of the experimental tasks in the initial experimental task ranking list; The overlapping time period analysis and intelligent scheduling module identifies the target experimental task pairs based on the predicted total duration of the experimental tasks in the initial experimental task sorting list; analyzes the target experimental task pairs to obtain the overlapping time periods of the target experimental task pairs, and intelligently allocates the usage order of the same experimental equipment of the target experimental task pairs in the overlapping time periods, and analyzes and adjusts the reservation time periods of subsequent experimental tasks accordingly; The real-time monitoring and task progress adjustment module performs experimental tasks in the order of the initial experimental task sorting list. After each experimental task is completed, the corresponding actual total duration is obtained, and the actual total duration of the corresponding experimental task is compared with the predicted total duration to obtain the deviation between the two; and according to the deviation between the actual total duration of the currently completed experimental task and the predicted total duration, the unfinished experimental tasks in the current initial experimental task sorting list are analyzed and adjusted accordingly.

[0019] The experimental task classification and sorting module includes a data collection unit, a task classification unit, and sorting list generation; The data collection unit obtains the initial experimental task list from the laboratory management platform, and the initial experimental task list records the specific description information of the experimental tasks; the task classification unit classifies the experimental tasks by analyzing the experimental equipment information required for the experimental tasks and using the similarity calculation method; the sorted list is generated for each experimental task type, and the experimental tasks corresponding to each experimental task type are sorted based on the appointment time period of the experimental tasks, thereby generating an initial experimental task sorting list.

[0020] The historical data analysis and task duration prediction module includes a historical data association analysis unit and a task duration prediction unit; The historical data association analysis unit obtains historical experimental data from the laboratory management platform and associates it with the experimental tasks in the initial experimental task sorting list; by analyzing the historical data, the required experimental equipment sequence for each experimental task is obtained; the task duration prediction unit calculates the predicted usage time of the corresponding experimental equipment based on the required experimental equipment sequence and the historical experimental data of the corresponding experimental task; the usage time of all experimental equipment in the required experimental equipment sequence is summarized to obtain the predicted total duration of the corresponding experimental task.

[0021] The overlapping period analysis and intelligent scheduling module includes an overlapping period analysis unit and an intelligent scheduling unit; The overlapping period analysis unit analyzes whether there is time overlap between experimental tasks based on the predicted duration and reservation period of the experimental tasks, identifies and extracts target experimental task pairs; the intelligent scheduling unit schedules the target experimental task pairs based on the usage order of the same equipment, and predicts the task completion time of the overlapping period; if there is a delay, the reservation period of the subsequent tasks is intelligently adjusted, and the adjustment information is output for relevant personnel to confirm and modify.

[0022] The real-time monitoring and task progress adjustment module includes a progress monitoring unit and a task adjustment unit; The progress monitoring unit performs the experimental tasks in the order of the initial experimental task sorting list, and obtains the corresponding actual total duration after completing each experimental task; the task adjustment unit compares the actual total duration of the corresponding experimental task with the predicted total duration to obtain the deviation between the two; and based on the deviation between the actual total duration of the currently completed experimental task and the predicted total duration, the unfinished experimental tasks in the current initial experimental task sorting list are analyzed and adjusted accordingly.

[0023] A method based on intelligent management of laboratory processes, comprising the following steps: Step S100. Obtain an initial experimental task list from the laboratory management platform, classify the experimental tasks in the initial experimental task list by analyzing the initial experimental task list, and divide them into several experimental task types; for each experimental task type, combine the initial experimental task list to generate an initial experimental task ranking list; Step S200. For each experiment type, based on the corresponding initial experiment task ranking list, obtain the corresponding historical experiment data, associate the historical experiment data with the experiment tasks in the initial experiment task ranking list; analyze the association results to obtain the predicted total duration of the experiment tasks in the initial experiment task ranking list; Step S300. Based on the predicted total duration of the experimental tasks in the initial experimental task sorting list, identify the target experimental task pairs; analyze the target experimental task pairs to obtain the overlapping time periods of the target experimental task pairs, and intelligently allocate the usage order of the same experimental equipment of the target experimental task pairs in the overlapping time periods, and analyze and adjust the reservation time periods of subsequent experimental tasks accordingly; Step S400. Perform the experimental tasks in the order of the initial experimental task sorting list. After completing each experimental task, obtain the corresponding actual total duration, and compare the actual total duration of the corresponding experimental task with the predicted total duration to obtain the deviation between the two; and according to the deviation between the actual total duration of the currently completed experimental task and the predicted total duration, perform corresponding analysis and adjustments on the unfinished experimental tasks in the current initial experimental task sorting list.

[0024] Step S100 includes: S101. Obtain an initial experimental task list from the laboratory management platform, wherein the initial experimental task list records specific description information of the experimental tasks; extract the experimental task number from the initial experimental task list, and each experimental task number is unique; for each experimental task, extract the corresponding required experimental equipment name from the initial experimental task list, and convert the required experimental equipment name into a unified vector format, thereby forming a required experimental equipment vector X_ID, and X_ID=[x1,x2,...,xn], wherein X_ID represents the required experimental equipment vector of the experimental task ID, x1 represents the first dimension eigenvalue of the required experimental equipment vector, x2 represents the second dimension eigenvalue of the required experimental equipment vector, and so on, xn represents the nth dimension eigenvalue of the required experimental equipment vector, wherein n represents the type of experimental equipment present in the laboratory; In this embodiment, converting the required experimental equipment names into a unified vector format usually involves natural language processing (NLP) technology, especially text embedding methods. The goal is to convert text information such as equipment names into numerical vectors so that these vectors can be compared, classified or further operated in subsequent analysis and processing.

[0025] Assume that the required experimental equipment names are converted into a unified vector format using a bag-of-words model. Specifically, first, extract the words in all equipment names and build a vocabulary containing all unique words; for each equipment name, convert it into a vector with a dimension equal to the size of the vocabulary. Each element in the vector represents whether a word appears in the equipment name (1 means it appears, 0 means it does not appear).

[0026] Assuming that the only equipment in the laboratory is named "A" and "B", the dimension of the required experimental equipment vector is 2, and the corresponding vocabulary is: ["A", "B"]. For the experimental task requiring experimental equipment "A", the corresponding vector format is: [1,0], and for the experimental task requiring experimental equipment "B", the corresponding vector format is: [0,1].

[0027] S102. Summarize the experimental equipment vectors required for all experimental tasks in the initial experimental task list, and calculate the similarity between the experimental equipment vector required for each experimental task and other required experimental equipment vectors in turn, and the corresponding calculation formula is: S(X_a,X_b)=|X_a∩X_b| / n; Where S(X_a,X_b) represents the similarity between the required experimental equipment vectors corresponding to experimental task a and experimental task b, and |X_a∩X_b| represents the number of the same dimension feature values ​​in the required experimental equipment vectors corresponding to experimental task a and experimental task b; those with similarities not equal to 0 are classified into one category, and all experimental tasks in the initial experimental task list are traversed, so as to divide the experimental tasks in the initial experimental task list into several experimental task types; In this embodiment, it is assumed that there are 2 types of experimental equipment in the laboratory and there are 3 experimental tasks. The corresponding required experimental equipment vectors are: X_a=[1,1,0], X_b=[1,0,0], X_c=[0,0,1]; The similarities between X_a and X_b, X_a and X_c, and X_b and X_c are calculated in sequence, and the corresponding similarities are: S(X_a,X_b)=1 / 2, S(X_a,X_c)=0, S(X_b,X_c)=0; Thereby, the experimental tasks are divided into two types of experimental tasks, and experimental tasks a and b are of one type, and experimental task c is of another type.

[0028] S103. For each type of experimental task, obtain the specific description information of the corresponding experimental task from the initial experimental task list, obtain the appointment time period T0 of the corresponding experimental task according to the specific description information of the experimental task, and generate the initial experimental task sorting list of the corresponding experimental task type according to the sequence of the starting timestamps of the appointment time period T0 of the experimental task.

[0029] Step S200 includes: S201. For each experiment type, based on the corresponding initial experiment task sorting list, obtain the historical experiment data of each experiment task in the initial experiment task sorting list from the laboratory management platform; for each experiment task, associate the experiment task number with the corresponding historical experiment data to obtain the required experiment equipment sequence F, and F={f1,f2,..,fm}, where f1 represents the name of the first experiment equipment used in the experiment task, f2 represents the name of the second experiment equipment used in the experiment task, and so on, fm represents the name of the mth experiment equipment used in the experiment task, and m represents the number of experiment equipment used in the experiment task; S202. According to the required experimental equipment sequence F and in combination with the historical experimental data of the corresponding experimental task, calculate the average usage time μt and standard deviation σt of each experimental equipment in the required experimental equipment sequence F in the historical experimental data, so as to obtain the predicted usage time tf of the corresponding experimental equipment, and tf=μt+α·σt, where α represents the adjustment coefficient, which can be adjusted according to the actual situation of the task (for example, based on the frequency of use of the equipment or the complexity of the experiment); summarize the usage time tf of all experimental equipment in the required experimental equipment sequence F, so as to obtain the predicted total duration sum_tf of the corresponding experimental task.

[0030] Step S300 includes: S301. Based on the initial experimental task sorting list, extract the predicted total duration of all experimental tasks in the initial experimental task sorting list, extract the starting timestamp of the appointment time period of each experimental task in the initial experimental task sorting list, and express it as t0; calculate the predicted time period T1 of each experimental task in the initial experimental task sorting list, and T1=[t0,t0+sum_tf]; according to the order of the initial experimental task sorting list, combined with the predicted total duration of all experimental tasks, refer to the calculation method of the predicted time period T1 of the first experimental task, and calculate the predicted time periods Ti of other experimental tasks in the initial experimental task sorting list in sequence, where i represents the sequence number of other experimental tasks; S302. Summarize the predicted time periods of all experimental tasks in the initial experimental task sorting list, and sort the predicted time periods of all experimental tasks according to the order of the initial experimental task sorting list; determine in turn whether there is an overlapping relationship between the predicted time periods of two adjacent experimental tasks in the initial experimental task sorting list, extract the experimental task numbers of all overlapping relationships, record them as target experimental task pairs, and express them as (IDj, IDj+1), where j represents the sequence number of the experimental task in the initial experimental task sorting list; summarize all target experimental task pairs to form a target experimental task set E, and E={e1,e2,...,ev}, where e1 represents the first target experimental task pair, e2 represents the second target experimental task pair, and so on, ev represents the vth target experimental task pair; S303. For each target experimental task pair in the target experimental task set E, calculate the overlap period Tc of the predicted time period of the target experimental task pair; based on the experimental task number of the target experimental task pair, respectively obtain the corresponding required experimental equipment sequence and the predicted usage time of each experimental equipment in the required experimental equipment sequence; according to the overlap period Tc, find the required experimental equipment of the target experimental task pair in the overlap period Tc; if the required experimental equipment corresponding to the two adjacent experimental tasks in the target experimental task pair are different, no processing is performed .... If the equipment is the same, compare the timestamps of the two adjacent experimental tasks in the target experimental task pair when using the experimental equipment, determine the order of using the experimental equipment according to the sequence of timestamps, and calculate the predicted timestamp t1 of the completion of the target experimental task pair according to the order of using the experimental equipment. If the predicted timestamp t1 is greater than the initial timestamp t0 of the appointment time period of the next experimental task in the initial experimental task sorting list, then the appointment time period of the subsequent experimental tasks will be postponed by the time span of t1-t0 in sequence, and the adjusted appointment time period will be output to the relevant personnel for confirmation and adjustment; otherwise, no adjustment will be made.

[0031] In this embodiment, it is assumed that a certain experiment type has three experiment tasks, and the corresponding initial experiment task ranking list is experiment 1, experiment 2 and experiment 3, and the corresponding reservation time periods are: [8:00,9:00], [9:00,10:00], [10:00,12:00]; and the required experimental equipment sequences for the three experimental tasks are: F1={f3,f1,f4}, F2={f4,f2,f1,f5}, F3={f3,f1,f4}; Assume that the prediction time periods T1 of the three experimental tasks are: [8:00,9:30], [9:00,10:00], [10:00,12:30]; By comparison, we can find that Experiment 1 and Experiment 2 are the target experimental pair, and the corresponding overlapping time period Tc is: [9:00,9:30]. Assuming that the experimental equipment corresponding to the overlapping time period Tc is f4, and assuming that the predicted timestamp of Experiment 1 using f4 is earlier than that of Experiment 2, then for the experimental equipment f4, the experimental task of Experiment 1 is performed first, and then the experimental task of Experiment 2 is performed. Assuming that the completion timestamp of the target experimental pair is 10:20; since 10:20 is greater than the initial timestamp of 10:00 of the reservation time period of Experiment 3, it is necessary to postpone the reservation time period of Experiment 3 by 20 minutes, that is, the reservation time period of Experiment 3 is modified to [10:20,12:20], and the modified reservation time period of Experiment 3 is output to the relevant personnel, who will make the final confirmation.

[0032] Step S400 includes: Perform the experimental tasks in sequence according to the order of the initial experimental task sorting list. After each experimental task is completed, obtain the corresponding actual total duration ts, compare the actual total duration of the corresponding experimental task with the predicted total duration, and obtain the deviation △t=ts-sum_tf between the two; if △t is greater than 0, obtain the unfinished experimental task sequence W in the current initial experimental task sorting list, and analyze and adjust each experimental task in the unfinished experimental task sequence W with reference to the analysis process in step S300; if △t is less than or equal to 0, do not perform any processing.

[0033] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0034] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method based on intelligent management of laboratory processes, characterized in that: The method comprises the following steps: Step S100. Obtain an initial experimental task list from the laboratory management platform, classify the experimental tasks in the initial experimental task list by analyzing the initial experimental task list, and divide them into several experimental task types; for each experimental task type, combine the initial experimental task list to generate an initial experimental task ranking list; Step S200. For each experiment type, based on the corresponding initial experiment task ranking list, obtain the corresponding historical experiment data, associate the historical experiment data with the experiment tasks in the initial experiment task ranking list; analyze the association results to obtain the predicted total duration of the experiment tasks in the initial experiment task ranking list; Step S300. Based on the predicted total duration of the experimental tasks in the initial experimental task sorting list, identify the target experimental task pairs; analyze the target experimental task pairs to obtain the overlapping time periods of the target experimental task pairs, and intelligently allocate the usage order of the same experimental equipment of the target experimental task pairs in the overlapping time periods, and analyze and adjust the reservation time periods of subsequent experimental tasks accordingly; Step S400. Perform the experimental tasks in the order of the initial experimental task sorting list. After completing each experimental task, obtain the corresponding actual total duration, and compare the actual total duration of the corresponding experimental task with the predicted total duration to obtain the deviation between the two; and according to the deviation between the actual total duration of the currently completed experimental task and the predicted total duration, perform corresponding analysis and adjustments on the unfinished experimental tasks in the current initial experimental task sorting list.

2. A method based on intelligent management of laboratory processes according to claim 1, characterized in that: The step S100 includes: S101. Obtain an initial experimental task list from the laboratory management platform, wherein the initial experimental task list records specific description information of the experimental tasks; extract the experimental task number from the initial experimental task list, and each experimental task number is unique; for each experimental task, extract the corresponding required experimental equipment name from the initial experimental task list, and convert the required experimental equipment name into a unified vector format, thereby forming a required experimental equipment vector X_ID, and X_ID=[x1,x2,...,xn], wherein X_ID represents the required experimental equipment vector of the experimental task ID, x1 represents the first dimension eigenvalue of the required experimental equipment vector, x2 represents the second dimension eigenvalue of the required experimental equipment vector, and so on, xn represents the nth dimension eigenvalue of the required experimental equipment vector, wherein n represents the type of experimental equipment present in the laboratory; S102. Summarize the experimental equipment vectors required for all experimental tasks in the initial experimental task list, and calculate the similarity between the experimental equipment vector required for each experimental task and other required experimental equipment vectors in turn, and the corresponding calculation formula is: S(X_a,X_b)=|X_a∩X_b| / n; Where S(X_a,X_b) represents the similarity between the required experimental equipment vectors corresponding to experimental task a and experimental task b, and |X_a∩X_b| represents the number of the same dimension feature values ​​in the required experimental equipment vectors corresponding to experimental task a and experimental task b; those with similarities not equal to 0 are classified into one category, and all experimental tasks in the initial experimental task list are traversed, so as to divide the experimental tasks in the initial experimental task list into several experimental task types; S103. For each type of experimental task, obtain the specific description information of the corresponding experimental task from the initial experimental task list, obtain the appointment time period T0 of the corresponding experimental task according to the specific description information of the experimental task, and generate the initial experimental task sorting list of the corresponding experimental task type according to the sequence of the starting timestamps of the appointment time period T0 of the experimental task.

3. A method based on intelligent management of laboratory processes according to claim 2, characterized in that: The step S200 includes: S201. For each experiment type, based on the corresponding initial experiment task sorting list, obtain the historical experiment data of each experiment task in the initial experiment task sorting list from the laboratory management platform; for each experiment task, associate the experiment task number with the corresponding historical experiment data to obtain the required experiment equipment sequence F, and F={f1,f2,..,fm}, where f1 represents the name of the first experiment equipment used in the experiment task, f2 represents the name of the second experiment equipment used in the experiment task, and so on, fm represents the name of the mth experiment equipment used in the experiment task, and m represents the number of experiment equipment used in the experiment task; S202. According to the required experimental equipment sequence F and in combination with the historical experimental data of the corresponding experimental task, calculate the average usage time μt and standard deviation σt of each experimental equipment in the required experimental equipment sequence F in the historical experimental data, so as to obtain the predicted usage time tf of the corresponding experimental equipment, and tf=μt+α·σt, where α represents the adjustment coefficient; summarize the usage time tf of all experimental equipment in the required experimental equipment sequence F, so as to obtain the predicted total duration sum_tf of the corresponding experimental task.

4. A method based on intelligent management of laboratory processes according to claim 3, characterized in that: The step S300 includes: S301. Based on the initial experimental task sorting list, extract the predicted total duration of all experimental tasks in the initial experimental task sorting list, extract the starting timestamp of the appointment time period of each experimental task in the initial experimental task sorting list, and express it as t0; calculate the predicted time period T1 of each experimental task in the initial experimental task sorting list, and T1=[t0,t0+sum_tf]; according to the order of the initial experimental task sorting list, combined with the predicted total duration of all experimental tasks, refer to the calculation method of the predicted time period T1 of the first experimental task, and calculate the predicted time periods Ti of other experimental tasks in the initial experimental task sorting list in sequence, where i represents the sequence number of other experimental tasks; S302. Summarize the predicted time periods of all experimental tasks in the initial experimental task sorting list, and sort the predicted time periods of all experimental tasks according to the order of the initial experimental task sorting list; determine in turn whether there is an overlapping relationship between the predicted time periods of two adjacent experimental tasks in the initial experimental task sorting list, extract the experimental task numbers of all overlapping relationships, record them as target experimental task pairs, and express them as (IDj, IDj+1), where j represents the sequence number of the experimental task in the initial experimental task sorting list; summarize all target experimental task pairs to form a target experimental task set E, and E={e1,e2,...,ev}, where e1 represents the first target experimental task pair, e2 represents the second target experimental task pair, and so on, ev represents the vth target experimental task pair; S303. For each target experimental task pair in the target experimental task set E, calculate the overlap period Tc of the predicted time period of the target experimental task pair; based on the experimental task number of the target experimental task pair, respectively obtain the corresponding required experimental equipment sequence and the predicted usage time of each experimental equipment in the required experimental equipment sequence; according to the overlap period Tc, find the required experimental equipment of the target experimental task pair in the overlap period Tc; if the required experimental equipment corresponding to the two adjacent experimental tasks in the target experimental task pair are different, no processing is performed .... If the equipment is the same, compare the timestamps of the two adjacent experimental tasks in the target experimental task pair when using the experimental equipment, determine the order of using the experimental equipment according to the sequence of timestamps, and calculate the predicted timestamp t1 of the completion of the target experimental task pair according to the order of using the experimental equipment. If the predicted timestamp t1 is greater than the initial timestamp t0 of the appointment time period of the next experimental task in the initial experimental task sorting list, then the appointment time period of the subsequent experimental tasks will be postponed by the time span of t1-t0 in sequence, and the adjusted appointment time period will be output to the relevant personnel for confirmation and adjustment; otherwise, no adjustment will be made.

5. A method based on intelligent management of laboratory processes according to claim 4, characterized in that: The step S400 includes: Perform the experimental tasks in sequence according to the order of the initial experimental task sorting list. After each experimental task is completed, obtain the corresponding actual total duration ts, compare the actual total duration of the corresponding experimental task with the predicted total duration, and obtain the deviation △t=ts-sum_tf between the two; if △t is greater than 0, obtain the unfinished experimental task sequence W in the current initial experimental task sorting list, and analyze and adjust each experimental task in the unfinished experimental task sequence W with reference to the analysis process in step S300; if △t is less than or equal to 0, do not perform any processing.

6. A system based on intelligent management of laboratory processes, applied to a method based on intelligent management of laboratory processes according to any one of claims 1 to 5, characterized in that: The system includes: an experimental task classification and sorting module, a historical data analysis and task duration prediction module, an overlapping period analysis and intelligent scheduling module, and a real-time monitoring and task progress adjustment module; The experimental task classification and sorting module obtains an initial experimental task list from the laboratory management platform, classifies the experimental tasks in the initial experimental task list by analyzing the initial experimental task list, and divides the experimental tasks into several experimental task types; for each experimental task type, combined with the initial experimental task list, generates an initial experimental task sorting list; The historical data analysis and task duration prediction module obtains corresponding historical experimental data for each experiment type based on the corresponding initial experimental task ranking list, associates the historical experimental data with the experimental tasks in the initial experimental task ranking list; analyzes the association results to obtain the predicted total duration of the experimental tasks in the initial experimental task ranking list; The overlapping time period analysis and intelligent scheduling module identifies the target experimental task pairs based on the predicted total duration of the experimental tasks in the initial experimental task sorting list; analyzes the target experimental task pairs to obtain the overlapping time periods of the target experimental task pairs, and intelligently allocates the usage order of the same experimental equipment of the target experimental task pairs in the overlapping time periods, and analyzes and adjusts the reservation time periods of subsequent experimental tasks accordingly; The real-time monitoring and task progress adjustment module performs experimental tasks in the order of the initial experimental task sorting list. After each experimental task is completed, the corresponding actual total duration is obtained, and the actual total duration of the corresponding experimental task is compared with the predicted total duration to obtain the deviation between the two; and according to the deviation between the actual total duration of the currently completed experimental task and the predicted total duration, the unfinished experimental tasks in the current initial experimental task sorting list are analyzed and adjusted accordingly.

7. A system based on intelligent management of laboratory processes according to claim 6, characterized in that: The experimental task classification and sorting module includes a data acquisition unit, a task classification unit, and a sorting list generation; The data acquisition unit obtains an initial experimental task list from the laboratory management platform, and the initial experimental task list records specific description information of the experimental tasks; the task classification unit classifies the experimental tasks by analyzing the experimental equipment information required for the experimental tasks and using a similarity calculation method; the sorting list is generated for each experimental task type, and based on the appointment time period of the experimental tasks, the experimental tasks corresponding to each experimental task type are sorted, thereby generating an initial experimental task sorting list.

8. The system based on intelligent management of laboratory processes according to claim 6, characterized in that: The historical data analysis and task duration prediction module includes a historical data association analysis unit and a task duration prediction unit; The historical data association analysis unit obtains historical experimental data from the laboratory management platform and associates it with the experimental tasks in the initial experimental task sorting list; by analyzing the historical data, the required experimental equipment sequence for each experimental task is obtained; the task duration prediction unit calculates the predicted usage time of the corresponding experimental equipment based on the required experimental equipment sequence and in combination with the historical experimental data of the corresponding experimental task; and summarizes the usage time of all experimental equipment in the required experimental equipment sequence to obtain the predicted total duration of the corresponding experimental task.

9. The system based on intelligent management of laboratory processes according to claim 6, characterized in that: The overlapping period analysis and intelligent scheduling module includes an overlapping period analysis unit and an intelligent scheduling unit; The overlapping time period analysis unit analyzes whether there is time overlap between experimental tasks according to the predicted duration of the experimental tasks and the scheduled time period, and identifies and extracts the target experimental task pairs; the intelligent scheduling unit schedules the target experimental task pairs based on the usage order of the same equipment, and predicts the task completion time of the overlapping time period; If there is a delay, the appointment time period for subsequent tasks will be intelligently adjusted, and the adjustment information will be output for relevant personnel to confirm and modify.

10. A system based on intelligent management of laboratory processes according to claim 6, characterized in that: The real-time monitoring and task progress adjustment module includes a progress monitoring unit and a task adjustment unit; The progress monitoring unit performs the experimental tasks in the order of the initial experimental task ranking list, and obtains the corresponding actual total duration after completing each experimental task; the task adjustment unit compares the actual total duration of the corresponding experimental task with the predicted total duration to obtain the deviation between the two; and according to the deviation between the actual total duration of the currently completed experimental task and the predicted total duration, the unfinished experimental tasks in the current initial experimental task ranking list are analyzed and adjusted accordingly.

Images