Laboratory equipment management method and system based on artificial intelligence

Abstract

The invention relates to the field of artificial intelligence engineering, in particular to a laboratory equipment management method based on artificial intelligence, and the method comprises the steps: obtaining course plan data and equipment historical task record data through collection, and generating an equipment use feature vector table according to the course plan data and the equipment historical task record data; according to the method, course planning data are collected to extract course features, equipment state indexes are analyzed in combination with equipment historical records, and a multi-dimensional feature vector table is constructed to realize accurate equipment scheduling; a dynamic scheduling graph is constructed based on equipment performance, time concurrency and cost risk constraints, and a genetic algorithm is adopted to optimize and generate an optimal scheduling strategy; the equipment state is monitored through real-time sensor data, the strategy is dynamically adjusted according to the abnormal index, efficient utilization and risk management and control of equipment resources are achieved, laboratory management is promoted to be converted from a traditional manual mode to intelligent and digital modes, the equipment utilization rate and management efficiency are remarkably improved, and the operation cost is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of artificial intelligence engineering, in particular to a laboratory equipment management method and system based on artificial intelligence. BACKGROUND

[0002] In the field of laboratory equipment management, a scientific and reasonable equipment scheduling method should be based on factors such as experimental course plans and scientific research project requirements to achieve precise planning of equipment usage time. By collecting and analyzing course plan data, key characteristic parameters such as the use frequency and duration of different courses on equipment can be obtained, combined with performance indicators such as the maintenance cycle and operating state of the equipment, to form an optimized equipment scheduling scheme. In particular for high-precision analytical instruments and other devices sensitive to the use environment, a reasonable scheduling strategy is needed to avoid time periods prone to interference to ensure that the equipment operates in the best working condition, thereby improving the reliability of test data and the overall efficiency of equipment use.

[0003] However, the manual equipment management method commonly used in the prior art has obvious shortcomings: the equipment allocation decision mainly depends on the subjective experience of the management personnel, and cannot effectively integrate multi-source heterogeneous data such as course plans and equipment operating states, resulting in a lack of scientific basis for equipment resource scheduling, low comprehensive utilization rate of equipment, difficulty in ensuring timeliness of task execution, and easy occurrence of unreasonable phenomena such as equipment overload operation or long-term idling, which ultimately adversely affects the normal development of experimental teaching activities.

[0004] Therefore, there is an urgent need for a laboratory equipment management method and system based on artificial intelligence. SUMMARY

[0005] Therefore, it is necessary to provide a laboratory equipment management method and system based on artificial intelligence, which extracts course characteristics by collecting course plan data, analyzes equipment state indicators based on equipment historical records, constructs a multi-dimensional feature vector table to achieve precise equipment scheduling, constructs a dynamic scheduling atlas based on equipment performance, time concurrency and cost risk constraints, and optimizes the generation of the optimal scheduling strategy using a genetic algorithm. Through real-time sensor data monitoring of equipment state, dynamic adjustment of the strategy based on the abnormality index, efficient utilization and risk control of equipment resources, the transformation of laboratory management from traditional manual mode to intelligent and digital mode is promoted, equipment utilization rate and management efficiency are significantly improved, and operating costs are reduced.

[0006] The technical scheme of the present application is as follows: A laboratory equipment management method based on artificial intelligence, the method comprising: acquiring course plan data and equipment historical task record data by collection, and generating an equipment usage feature vector table according to the course plan data and the equipment historical task record data; constructing and generating a device state performance constraint, a time concurrency constraint and a cost risk constraint based on the course feature data and the device state indicator set, and integrating to obtain a mixed constraint condition set, and constructing and generating a scheduling graph based on the mixed constraint condition set; calculating the scheduling graph based on the feature vector table through a preset genetic algorithm to obtain a scheduling strategy, wherein the scheduling strategy comprises a preset device parameter threshold; optimizing the scheduling strategy based on the device sensor real-time data and the preset device parameter threshold to generate a corrected scheduling strategy by collecting and obtaining device sensor real-time data.

[0007] Specifically, the course plan data and the device historical task record data are collected and obtained, and a device use feature vector table is generated based on the course plan data and the device historical task record data, comprising: The course plan data is collected and obtained, and course feature data is obtained by feature extraction on the course plan data; The device historical task record data is collected and obtained, and a device state indicator set is obtained by analyzing the device historical task record data; The course feature data and the device state indicator set are combined to generate a device use feature vector table.

[0008] Specifically, the device state performance constraint, the time concurrency constraint and the cost risk constraint are constructed and generated based on the course feature data and the device state indicator set, and the mixed constraint condition set is obtained by integration, and the scheduling graph is constructed and generated based on the mixed constraint condition set, comprising: The device state performance constraint and the cost risk constraint are constructed and generated based on the device state indicator set; The time concurrency constraint is constructed and generated based on the course feature data; The device state performance constraint, the time concurrency constraint and the cost risk constraint are integrated to obtain a mixed constraint condition set; The scheduling graph is constructed and generated based on the mixed constraint condition set.

[0009] Specifically, the scheduling strategy is obtained by calculating the scheduling graph based on the feature vector table through a preset genetic algorithm, wherein the scheduling strategy comprises a preset device parameter threshold, comprising: Seed data is extracted based on the feature vector table, and a search space is constructed based on the scheduling graph; The genetic algorithm is initialized to generate a genetic algorithm population based on the seed data and the search space; The genetic algorithm population is iteratively optimized to obtain the scheduling strategy, wherein the scheduling strategy comprises preset equipment parameter thresholds.

[0010] Specifically, the scheduling strategy is optimized based on the equipment sensor real-time data and the preset equipment parameter thresholds to generate a corrected scheduling strategy, comprising: The equipment sensor real-time data is collected, and the offset abnormality index and the long-term abnormality trend index are calculated based on the equipment sensor real-time data and the preset equipment parameter thresholds; The offset abnormality index and the long-term abnormality index are calculated to obtain a comprehensive deviation index; The scheduling strategy is optimized based on the comprehensive deviation index to generate a corrected scheduling strategy.

[0011] Specifically, the system also comprises a feature vector generation module for collecting course plan data and equipment historical task record data, and generating an equipment use feature vector table based on the course plan data and the equipment historical task record data. The feature vector generation module is configured to collect course plan data and equipment historical task record data, and generate an equipment use feature vector table based on the course plan data and the equipment historical task record data. The scheduling graph construction module is configured to generate equipment state performance constraints, time concurrency constraints, and cost risk constraints based on the course feature data and the equipment state index set, integrate the constraints to obtain a mixed constraint condition set, and construct a scheduling graph based on the mixed constraint condition set. The scheduling strategy calculation module is configured to calculate the scheduling graph based on the feature vector table by using a preset genetic algorithm to obtain a scheduling strategy, wherein the scheduling strategy comprises preset equipment parameter thresholds. The scheduling strategy correction module is configured to collect equipment sensor real-time data, and optimize the scheduling strategy based on the equipment sensor real-time data and the preset equipment parameter thresholds to generate a corrected scheduling strategy.

[0012] Specifically, the feature vector generation module is further configured to collect course plan data, extract features from the course plan data to obtain course feature data, collect equipment historical task record data, analyze the equipment historical task record data to obtain an equipment state index set, and combine the course feature data and the equipment state index set to generate an equipment use feature vector table.

[0013] Specifically, the scheduling graph construction module is further configured to: generate the device state performance constraint and the cost risk constraint based on the set of device state indicators; generate the time concurrency constraint based on the course feature data; integrate the device state performance constraint, the time concurrency constraint and the cost risk constraint to obtain a set of mixed constraint conditions; and construct the scheduling graph based on the set of mixed constraint conditions.

[0014] Specifically, the scheduling strategy calculation module is further configured to: extract seed data based on the feature vector table, and search a space based on the scheduling graph; initialize a preset genetic algorithm based on the seed data and the search space to generate a genetic algorithm population; and iteratively optimize the genetic algorithm population to obtain the scheduling strategy, wherein the scheduling strategy comprises a preset device parameter threshold.

[0015] Specifically, the scheduling strategy correction module is further configured to: acquire device sensor real-time data, and calculate an offset abnormality index and a long-term abnormality trend index based on the device sensor real-time data and the preset device parameter threshold; calculate a comprehensive deviation index based on the offset abnormality index and the long-term abnormality index; and optimize the scheduling strategy based on the comprehensive deviation index to generate a corrected scheduling strategy.

[0016] Optionally, a computer device is also provided, which comprises a memory and a processor, the memory stores a computer program, and the processor implements the steps of the above-mentioned artificial intelligence-based laboratory equipment management method when executing the computer program.

[0017] Optionally, a computer readable storage medium is also provided, which stores a computer program, and the computer program is executed by a processor to implement the steps of the above-mentioned artificial intelligence-based laboratory equipment management method.

[0018] The present application relates to machine learning and deep learning technology, which achieves the following technical effects: The above-mentioned laboratory equipment management method and system based on artificial intelligence successively acquire course plan data and equipment historical task record data, generate an equipment use feature vector table according to the course plan data and the equipment historical task record data, construct and generate equipment state performance constraints, time concurrency constraints and cost risk constraints based on the course feature data and the equipment state indicator set, integrate to obtain a mixed constraint condition set, and construct and generate a scheduling graph based on the mixed constraint condition set; the scheduling graph is calculated based on the feature vector table by using a preset genetic algorithm, and a scheduling strategy is obtained, wherein the scheduling strategy includes a preset equipment parameter threshold; real-time data of an equipment sensor is acquired, and the scheduling strategy is optimized based on the real-time data of the equipment sensor and the preset equipment parameter threshold to generate a corrected scheduling strategy, thereby achieving at least one of the following technical effects: (1) By acquiring course plan data and extracting course features, combining equipment historical task record analysis and equipment state indicators, and accurately constructing an equipment use feature vector table, the allocation of laboratory equipment can closely match teaching needs and actual equipment performance, maximizing equipment utilization, avoiding resource waste, and ensuring that each piece of equipment can be used for the most needed experimental task at the right time.

[0019] (2) By using constraints such as current state performance, time concurrency and cost risk, the use of equipment is precisely controlled, and the running state of the equipment is monitored in real time. According to the comprehensive deviation index, the scheduling strategy is optimized in time, the equipment running risk is controlled to the minimum, and the cost expenditure caused by equipment failure, task overtime and other problems, such as equipment maintenance cost and experimental material loss cost, is reduced, thereby reducing the overall operation cost of the laboratory.

[0020] (3) By introducing multi-source data such as course plans, equipment historical records and real-time sensor data, intelligent scheduling decision-making and real-time abnormality monitoring and early warning are realized, the laboratory management is transformed from a traditional manual experience mode to a digital and intelligent mode, the management efficiency and decision-making scientificity are improved, and a more stable, efficient and safe equipment support environment is provided for experimental teaching. BRIEF DESCRIPTION OF DRAWINGS

[0021] Figure 1 It is a flowchart of the laboratory equipment management method based on artificial intelligence in one embodiment; Figure 2 It is a flowchart of the feature vector table generation in one embodiment; Figure 3 It is a structural block diagram of the laboratory equipment management system based on artificial intelligence in one embodiment. DETAILED DESCRIPTION

[0022] In the following description, for purposes of explanation and not limitation, specific details are set forth such as particular architectures, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application can be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known methods, devices, circuits, and

[0023] It will be understood that the terms "comprises" and / or "comprising," when used in this specification, include the presence of one or more features, integers, steps, operations, elements, and / or components but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0024] It will be understood that the term "and / or," when used in the specification and in the following claims, is intended to mean one or more of the associated listed items can be present, and, if not present, are not excluded.

[0025] As used in this specification and claims, the terms "if", "for example", and "like" can be construed to perform a similar function and can be interpreted to mean "if or when", or "e.g. when or whenever". Similarly, the phrase "if determined" or "if detected" can be construed to perform a similar function and can be interpreted to mean "if or when determined" or "if or when detected".

[0026] In addition, the terms "first", "second", "third", etc. as used in the description and the appended claims are used only to distinguish one element from another and do not otherwise limit the scope of the invention.

[0027] Reference throughout this specification to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present application. Thus, the appearances of the phrases "in one embodiment" or "in an embodiment" or "in some embodiments" or "in other embodiments" or "in still other embodiments" in various places throughout this specification are not necessarily all referring to the same embodiment, unless otherwise specifically stated. Furthermore, the term "comprising" or "containing" or "including" or "having" or variations thereof as used herein is used generically and not in the limitative sense, unless otherwise specifically stated.

[0028] In one embodiment, a terminal is provided, which is configured to: acquire course plan data and device historical task record data, generate a device usage feature vector table according to the course plan data and the device historical task record data; construct and generate device state performance constraints, time concurrency constraints and cost risk constraints based on the course feature data and the device state indicator set, integrate to obtain a mixed constraint condition set, and construct and generate a scheduling graph based on the mixed constraint condition set; calculate the scheduling graph based on the feature vector table by using a preset genetic algorithm, and obtain a scheduling strategy, wherein the scheduling strategy comprises a preset device parameter threshold; acquire device sensor real-time data, and optimize the scheduling strategy based on the device sensor real-time data and the preset device parameter threshold, and generate a corrected scheduling strategy.

[0029] The terminal can be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers and portable wearable devices.

[0030] In one embodiment, as shown in Figure 1 A laboratory equipment management method based on artificial intelligence is provided, which comprises the following steps: Step S100: acquiring course plan data and device historical task record data, and generating a device usage feature vector table according to the course plan data and the device historical task record data; Step S200: constructing and generating device state performance constraints, time concurrency constraints and cost risk constraints based on the course feature data and the device state indicator set, integrating to obtain a mixed constraint condition set, and constructing and generating a scheduling graph based on the mixed constraint condition set; Step S300: calculating the scheduling graph based on the feature vector table by using a preset genetic algorithm, and obtaining a scheduling strategy, wherein the scheduling strategy comprises a preset device parameter threshold; Step S400: acquiring device sensor real-time data, and optimizing the scheduling strategy based on the device sensor real-time data and the preset device parameter threshold, and generating a corrected scheduling strategy.

[0031] Step S410: acquiring device sensor real-time data, and calculating an offset abnormality index and a long-term abnormality trend index according to the device sensor real-time data and the preset device parameter threshold; Step S420: calculating the offset abnormality index and the long-term abnormality index, and obtaining a comprehensive deviation index; Step S430: optimizing the scheduling strategy based on the comprehensive deviation index, and generating a corrected scheduling strategy.

[0032] The artificial intelligence-based laboratory equipment management method and system described in the present application successively acquires course plan data and equipment historical task record data, generates an equipment use feature vector table according to the course plan data and the equipment historical task record data; constructs and generates equipment state performance constraints, time concurrency constraints and cost risk constraints based on the course feature data and the equipment state indicator set, integrates to obtain a mixed constraint condition set, and constructs and generates a scheduling graph based on the mixed constraint condition set; calculates the scheduling graph based on the feature vector table through a preset genetic algorithm, acquires a scheduling strategy, wherein the scheduling strategy includes a preset equipment parameter threshold; acquires equipment sensor real-time data, optimizes the scheduling strategy based on the equipment sensor real-time data and the preset equipment parameter threshold, and generates a corrected scheduling strategy. By structurally analyzing course plan data to extract teaching time, equipment type and other features, combining historical record analysis of equipment load rate, adaptability and other state indicators, and fusing to generate a high-dimensional feature vector table to realize demand-resource digital mapping. Then, equipment state, time concurrency, cost risk and other multi-dimensional constraints are integrated to construct a scheduling graph, a genetic algorithm is used to optimize resource utilization rate, timeliness and risk cost, and a scheduling strategy containing a preset threshold is output. In the execution phase, equipment sensor data is monitored in real time, the running state is quantified through an offset abnormality index and a long-term trend index, and finally a three-level corrected scheduling strategy is dynamically triggered based on a comprehensive deviation index. Further, at least one of the following technical effects is achieved: Firstly, by collecting course plan data and extracting course features, combining equipment historical task record analysis of equipment state indicators, and accurately constructing an equipment use feature vector table, the allocation of laboratory equipment can closely match teaching needs and equipment actual performance, maximizing equipment utilization, avoiding resource waste, and ensuring that each equipment can be used for the most needed experimental task at the right time.

[0033] Secondly, by constraining equipment use through current state performance, time concurrency and cost risk and other constraint conditions, and simultaneously monitoring equipment running state in real time, scheduling strategy is optimized in time according to a comprehensive deviation index, equipment running risk is controlled to the minimum, and cost expenditure caused by equipment failure, task overtime and other problems, such as equipment maintenance cost, experimental material loss cost and the like, is reduced, thereby reducing overall laboratory operating cost.

[0034] Thirdly, by introducing multi-source data such as course plan, equipment historical record, real-time sensor data, intelligent scheduling decision and real-time abnormality monitoring and early warning are realized, laboratory management is promoted from traditional manual experience mode to digital and intelligent mode, management efficiency and decision-making scientificity are improved, and a more stable, efficient and safe equipment support environment is provided for experimental teaching.

[0035] In one embodiment, as shown in Figure 2 Step S100: generating a device usage feature vector table according to course schedule data and device historical task record data obtained by collection, comprising: Step S110: extracting features from the course schedule data to obtain course feature data; In this step, the course schedule data collected, such as course schedule table, experimental equipment list, teaching resource table, experimental outline and teaching link design, is subjected to feature extraction by structured analysis method to obtain course feature data, including teaching time node, task duration, number of experimental links, instrument type list, and device concurrent usage rate.

[0036] The teaching time node is directly extracted from the time field in the course schedule table, standardized in the format of "week-date-period", and the collected content is: the week range of the course in the semester (such as weeks 3-18), the teaching date of each week (such as Tuesday), the specific period (such as 3-4 am), and the total number of class hours (such as 32 class hours).

[0037] The task duration is parsed from the "class hour arrangement" field in the course schedule table to directly obtain the duration data (unit: minute), and the collected content is: the start / end time of a single teaching task (such as 9:00-10:45), and the frequency of periodic tasks (such as twice a week).

[0038] The number of experimental links is directly counted from the experimental outline or the teaching link design, and the collected content is: the type of experiment (demonstration experiment, group training, comprehensive training) and the corresponding number of times (such as 2 times of demonstration experiment).

[0039] The instrument type list is directly extracted from the experimental equipment list or the teaching resource table, and is recorded in a standard format, and the collected content is: the device name (such as oscilloscope DS1052E, electron microscope SEMEVO10, spectrophotometer UV-1800), the function category (such as electronic measurement), the technical parameter (such as bandwidth 100MHz), and the supporting software (such as oscilloscope driver program V1.2).

[0040] Further, the concurrent usage rate is set as follows:

[0041] wherein, is the device concurrent usage rate, is the number of students in the course class, is the single-task device occupancy coefficient, The task demand equipment number is calculated, The single equipment carrying number of people is calculated.

[0042] The single task equipment occupancy coefficient is calculated Set, for example, when 1 person per station, 2 people per station, The task demand equipment number is calculated That is, the total equipment demand calculated according to the number of students and the occupancy coefficient, the single equipment carrying number of people is calculated Set, for example, 1 equipment supports a maximum of 50 people using at the same time,

[0043] Further, the device concurrency rate is normalized as follows:

[0044] Wherein, The normalized concurrency usage rate is between 0 and 1, The maximum concurrency usage rate is, for example, 1.0. By normalization, different dimensional parameters (such as the number of people, the length of time) can be ensured to have no calculation conflicts in subsequent calculations.

[0045] Step S120: Obtain a device state index set by analyzing the device historical task record data obtained by collecting the device historical task record data; In this step, the device state index set is obtained by analyzing the device historical task record data obtained by collecting the device historical task record data, including: usage load, i.e. running time ratio, running efficiency, i.e. task completion amount per unit time, and function adaptation degree.

[0046] Further, the usage load is set as follows:

[0047] Wherein, The usage load is a percentage (e.g. 80%), The actual usage time of the device (extracted from the device historical task record, unit: hours, e.g. 40 hours of cumulative use in a week), The theoretical available time of the device in the statistical period.

[0048] The result of the usage load is a percentage, for example, 80%, the actual usage time of the device is in hours, extracted from the device historical task record, for example, 40 hours of cumulative use in a week, the theoretical available time of the device in the statistical period is in hours, obtained by multiplying the number of days by 24 and subtracting the planned maintenance time, wherein the planned maintenance time is extracted from the device historical task record.​

[0049] Further, the operation efficiency is set as follows:

[0050] wherein, is the operation efficiency, is the number of effective tasks completed by the device.

[0051] The operation efficiency is in the unit of task number / hour, for example, 15 sets of experimental data / hour, and the number of effective tasks completed by the device is extracted from the historical task records of the device, for example, a device processed 120 sets of data last week.

[0052] Further, the function adaptation degree is set as follows:

[0053] wherein, is the adaptation degree score, is the number of task key parameters, is the weight of the qth parameter, is the correspondence degree of the device parameters to the task requirements, is the weighted matching degree sum, is the weight sum.

[0054] The adaptation degree score has a result of 0-10 points, for example, 9.2 points, the number of task key parameters includes the number of parameters such as precision, processing speed, compatibility, etc., and when the number is preset to 3, the weight of the mth parameter is set according to the task criticality, which is preset by an experimental administrator, for example: in a high-precision task, the precision weight W1=0.6, the speed W2=0.2, and the compatibility W3=0.2; in a regular task, the uniform weight, i.e., W1=W2=W3=0.33; the correspondence degree of the device parameters to the task requirements is set according to the deviation quantification of the device parameters and the task requirements, when fully satisfied, for example, the device bandwidth≥task requirement, then =10 points; when partially satisfied, for example, the device bandwidth is 80%-100% of the task requirement, then =6 points; when not satisfied, for example, the device bandwidth<80% of the task requirement, then =0 points.

[0055] The weighted matching degree sum represents the comprehensive matching score of the device parameters to the task requirements, for example, the weighted score of the precision and speed, and the weight sum ​, for normalization, ensuring S is in the range 0-10.

[0056] Step S130: Combine the course feature data and the device status indicator set to generate a device usage feature vector table.

[0057] In this step, the device status indicator set (L, E, S) is obtained by combination, and the course feature data is associated with the device status indicator for mapping, using data fusion technology (dimension alignment) to generate a device usage feature vector table.

[0058] Further, the association mapping rules are set as follows: By device ID and task type (such as "experimental class" "theoretical class"), the course requirements (such as "12 weeks need 2 oscilloscopes") are matched with the device status indicators (such as "oscilloscope A's , , ").

[0059] Further, the device usage feature vector in the device usage feature vector table is set as follows:

[0060] where T is the teaching time, is the task type, is the name of the mth device, and are the usage load, running efficiency, and adaptation score of the mth device, respectively, and m is the number of devices involved in the task.

[0061] The format of the teaching time T is X-Y weeks X morning / afternoon, such as "12-16 weeks Tuesday morning", and the task type is set to, for example, "experimental class", "theoretical class", "practical class", and the name of the mth device is set to, for example, "oscilloscope DS1052E", "signal generator AFG3022".

[0062] Further, the device usage feature vector table is set as follows:

[0063] where is the device usage feature vector of the kth task or course, k is the feature vector of the kth task / course, m is the number of devices involved in task k, is the teaching time window of the kth task, is the type of the kth task, is the name of the mth device involved in the kth task, is the usage load of the mth device involved in the kth task, The first task The identifier for each device uniquely identifies the device resource participating in the task. 'i' is the device index, with a value ranging from 1 to m. It is the first The first task The operating load of the equipment It is the first The first task The operating efficiency of the equipment. It is the first The first task Functional compatibility of the devices.

[0064] The first Device usage feature vector for a task or course Integrating historical status indicators of task time, type, and required equipment to provide input for the scheduling algorithm, the first... Type of task Used to differentiate task nature and match device functional scenarios, the first The first task Equipment identification Use it to uniquely identify the device resources participating in the task.

[0065] In one embodiment, step S200: Based on the course feature data and the set of equipment status indicators, construct and generate equipment status performance constraints, time concurrency constraints, and cost risk constraints, and integrate them to obtain a mixed constraint set; based on the mixed constraint set, construct and generate a scheduling graph, including: Step S210: Based on the set of equipment status indicators, construct and generate the equipment status performance constraints and the cost risk constraints; Step S220: Generate the time concurrency constraints based on the course feature data; Step S230: Integrate the device state performance constraints, the time concurrency constraints, and the cost risk constraints to obtain a set of mixed constraints; Step S240: Construct and generate a scheduling graph based on the set of hybrid constraints.

[0066] In this embodiment, a scheduling graph is constructed based on a set of mixed constraints. This is an intuitive and structured visualization tool. It can clearly display information such as the availability of laboratory equipment, task allocation sequence, and time arrangement under various constraints. The scheduling graph allows schedulers to easily understand the scheduling status of equipment, which helps to quickly formulate reasonable equipment usage plans, improve the scientificity and accuracy of equipment scheduling, thereby optimizing the overall operating efficiency of laboratory equipment and achieving reasonable allocation and efficient utilization of resources.

[0067] Further, the device state performance constraints include: Real-time availability (A): 0 (indicating unavailable, such as failure / maintenance) or 1 (indicating available), used to directly exclude the assignment possibility of unavailable devices (corresponding edges do not exist or have a weight of +∞); Adaptability (A): the matching score of the task T and the device D (set in the range of 0-10), high adaptability reduces edge weight, and is preferred; Load (L): historical usage load of the device, low-load devices are more likely to be idle within a time window, and are preferred for assignment; Efficiency (E): the task processing amount per unit time of the device, high-efficiency devices improve task timeliness, and are preferred. Further, the cost risk constraints include: Device energy consumption cost (C): device energy consumption cost per unit time (such as 0.5 yuan / h), increase the edge weight by a weight coefficient α (such as α = 0.3) to achieve cost optimization. Device failure probability (P): historical device failure probability of the device (such as 0.05), increase the edge weight by a weight coefficient β (such as β = 0.2) to achieve risk avoidance.

[0068] Concurrent risk (R): the conflict probability of device i processing task j with other tasks (set in the range of 0-1), increase the edge weight by a weight coefficient δ (such as δ = 0.1) to avoid resource contention. Further, the time concurrency constraints include:

[0069] Task time (T): compared with the idle time of device i (inferred by, for example, load 60% then idle 40% time), exclude edges with time overlap, such as device i has been occupied by task k, and task j overlaps with k in time Concurrent capacity (C): the maximum number of tasks that device i can process at the same time (such as

[0070] indicates a single-task device), limit the number of edges of each device node , thereby avoiding resource overload.

[0071]

[0072]

[0073] ​​​​​​​​​​​​​​Further, the construction of the scheduling graph includes the following steps: A. Construction of graph elements: A1. Node (V) setting: A11. Task node: contains task time window (e.g. Tuesday morning of week 12), task type Tt,j(e.g. experiment type).

[0074] A12. Equipment node: contains available state , historical performance (adaptability , load , efficiency , cost risk (equipment energy cost , equipment failure probability ), development capacity Mi(e.g. 1, representing a single-task equipment).

[0075] A2. Edge (E) and weight (W): A21. Edge existence condition: =1, and task time window matches the idle time of equipment Di(no conflict).

[0076] A22. Edge weight formula: A221. Normalization: all parameters are first normalized to the range [0, 1]: Normalization: ; Normalization: (probability is already in [0, 1]); Normalization: ; Normalization: ; A222. Weight coefficient adjustment: satisfies , and the initial value is based on laboratory strategy setting (e.g. prefer low risk when ).

[0077] A223. Correction formula:

[0078] wherein, is the edge weight, is the weight coefficient, is the normalized equipment energy cost, is the normalized equipment failure probability, is the normalized adaptability,​ is the normalized concurrency risk.

[0079] B, schedule graph construction: B1, node initialization: B11, task node (T) initialization: extract all tasks to be scheduled (such as experimental courses, theoretical courses) from the course plan data, and generate . .

[0080] B12, device node (D) initialization: filter devices from the experimental device list and real-time state (such as device sensor real-time data) to extract ( ). .

[0081] B2, edge set construction: For each , traverse ( ), check time conflict (calculate device idle period by load , compare with time window), if matched, create edge , calculate , C, constraint verification: C1, concurrency capacity verification: ensure the number of edges of (such as single-task device , only one edge is allowed).

[0082] C2, time uniqueness verification: no overlap between time windows of tasks and devices (verified by time attribute of face covering edge).

[0083] D, mathematical expression of schedule graph, set as follows:

[0084] wherein is the union of task node set and device node set , i.e. , is the directed edge from task to device ( ).

[0085] In one embodiment, step S300: based on the feature vector table, a preset genetic algorithm is used to calculate the schedule graph to obtain a scheduling strategy, wherein the scheduling strategy includes a preset device parameter threshold, including: Step S310: extracting seed data based on the feature vector table, and constructing a search space based on the scheduling graph; Step S320: initializing a genetic algorithm population based on the seed data and the search space; Step S330: iteratively optimizing the genetic algorithm population to obtain the scheduling strategy, wherein the scheduling strategy includes a preset device parameter threshold.

[0086] In this embodiment, the feature vector table of the extraction step provides multi-dimensional quantitative basis for task-device association, including teaching time window , , , , , , , as seed data for algorithm initialization. The scheduling graph provides a legal search space for the algorithm, ensuring that the allocation scheme meets the hardware and time constraints. Then, the genetic algorithm population is initialized, and the initial population is generated by legal allocation scheme. Each individual is a chromosome representing the task-device allocation matrix, which meets the graph edge constraints (such as tasks only connected to feasible devices, and the number of concurrent devices). The priority allocation of high-adaptation devices is used to improve the quality of the initial solution. At the same time, a matching degree function is constructed to find the scheduling strategy with optimal resource utilization, task timeliness, and risk cost.

[0087] Further, the matching degree function is set as follows:

[0088] wherein Z is the matching degree, , and Q correspond to resource utilization, task timeliness, and risk cost, respectively; , and correspond to the weights of resource utilization, task timeliness, and risk cost, respectively, and the weights are adjusted according to the teaching objectives. For example, if timeliness is emphasized during the experiment week, then .

[0089] Further, the resource utilization is set as follows:

[0090] wherein is the resource utilization, and the range is set to 0-1, is the idle time of device i, is the utilization rate of device i (The more compact the equipment allocation, the less idle time there is) (The closer to 1), m is the number of devices.

[0091] Furthermore, the task timeliness settings are as follows:

[0092] in, It refers to the timeliness of the task, with a range of 0-1. It is the number of tasks completed on time. This is the total number of tasks. If the task time window matches the device's allocated time period perfectly, it is considered to be completed on time.

[0093] Furthermore, the risk cost is set as follows:

[0094] in, It is a risk and a cost. It is equipment Energy consumption cost (yuan / hour). It is a task Use equipment Duration (hours) It is equipment The probability of failure, It is a task Importance weighting (e.g., core experimental courses) General Theory Course ).

[0095] In this embodiment, the iterative optimization operation of the genetic algorithm includes: Select Operation: Filter high-quality solutions by matching degree Z, and prioritize the retention of high and low equipment allocations to ensure functional matching and efficient resource utilization.

[0096] Crossover operation (two-point crossover): Exchange task device genes, utilize the fact that the solution is still highly adaptable after crossover (such as the exchange between highly adaptable devices), verify the graph constraints (time, concurrency), and generate a legal new solution.

[0097] Mutation operation (single point mutation): low probability adjustment of equipment allocation, priority replacement with high-performance equipment (improving timeliness, such as prioritizing high-performance equipment for experimental classes), and repair of concurrent overcapacity (redistributing excess tasks).

[0098] Repeated selection, crossover, and mutation are employed, with each generation of the population optimizing allocation using feature vector tables and graph constraints to gradually improve the matching degree Z (enhancing resources and timeliness while reducing risk). Convergence occurs after 100 generations or 10 consecutive generations when fitness has not improved, and the optimal scheduling strategy is output. Furthermore, an example of the scheduling strategy is shown below: ①Device allocation result: generate task-device mapping table, including time, device and historical indicators (load L, load E, load S), for example:

[0099] ②Task role fine-tuning configuration: Before class: experimenters calibrate devices according to (75% load) to ensure that the devices (15 groups / h) are fully loaded and ready for in-class tasks.

[0100] During class: teachers use (9.2 high adaptation) to conduct experiments, and students operate devices in groups (5 people / group), and experimenters monitor (load over 80% warning, trigger 56 correction). After class: high adaptation devices

[0101] are given priority maintenance, and low adaptation devices are given regular maintenance to optimize resource life. ③Threshold parameters:

[0102] Voltage threshold: , if , then (out of the allowed range); Temperature threshold: , if , then (trigger warning). In one embodiment, step S400: obtain device sensor real-time data by collection, optimize the scheduling strategy based on the device sensor real-time data and the preset device parameter threshold, and generate a corrected scheduling strategy, comprising:

[0103] Step S410: obtain device sensor real-time data by collection, and calculate the offset anomaly index and the long-term anomaly trend index according to the device sensor real-time data and the preset device parameter threshold; Step S420: calculate the offset anomaly index and the long-term anomaly index to obtain a comprehensive deviation index; Step S430: optimize the scheduling strategy based on the comprehensive deviation index to generate a corrected scheduling strategy.

[0104] ​In this embodiment, real-time data from the device's built-in sensors (such as voltage, temperature, and runtime sensors) is collected in real time. Two major anomaly indices are calculated using a quantification model. The offset anomaly index is used to monitor instantaneous parameter fluctuations (such as sudden power increases), while the long-term trend index is used to identify systematic deviations (such as continuous efficiency decay). This provides quantifiable anomaly evidence for dynamic correction, and finally, a correction scheduling strategy is generated based on the comprehensive deviation index.

[0105] Among them, the real-time data of the equipment sensors (denoted as) )include: Electrical parameters: operating voltage (like ); Physical condition: Equipment temperature (like ), vibration frequency ; Usage duration: Continuous running time (like (Hours, avoid overheating and aging).

[0106] Furthermore, the offset anomaly index is set as follows:

[0107] in, It is a deviation anomaly index. It is the deviation between the equipment operating parameters and the threshold parameters. It is the maximum value of the parameter deviation. It is the allowable fluctuation range of the equipment parameters (such as voltage 210-230V, range 20V). Dividing the two is to calculate the proportion of data that exceeds the threshold in the short term.

[0108] Furthermore, the setting of the deviation value between the parameter and the threshold. As shown below:

[0109] in, It is the deviation value between the parameter and the threshold. These are the equipment operating parameters. The threshold parameters (such as operating voltage) are extracted from the scheduling strategy. Safety range: 209V - 231V; Equipment temperature safety range: 0℃ - 40℃; Maximum continuous working time: 8 hours.

[0110] Furthermore, the long-term anomaly index is set as follows:

[0111] in, is a long-term abnormal trend index, is a current time device parameter deviation from a threshold, is a time window start time deviation, .

[0112] the long-term abnormal trend index represents data continuously deviates from a threshold and shows a deteriorating trend, such as initial deviation 0, current deviation 5℃, time window 1 hour, → normalized to 500%.

[0113] Further, the comprehensive deviation index is set as follows:

[0114] wherein, is a comprehensive deviation index, is a weight coefficient ( ), is a shift abnormal index (such as voltage fluctuation 10V, threshold range 20V, ), is a long-term abnormal trend index (such as temperature deteriorating 5℃ per hour, ).

[0115] the weight coefficient is used to adjust the priority of the two types of abnormalities, such as focusing on short-term fluctuations, focusing on long-term trends.

[0116] Further, the process of generating a revised scheduling strategy according to the comprehensive deviation index is as follows: low deviation ( ): maintain the original strategy, representing that the deviation is acceptable and no adjustment is needed.

[0117] medium deviation ( ): partial correction: update the edge weight of the scheduling graph (such as for a faulty device , increase its failure probability factor , make rise, reduce allocation; or reduce the concurrent capacity of a high-load device ).

[0118] re-optimization: run the genetic algorithm of step 300, only adjust the allocation of affected devices, such as replacing with a backup device, maintain task timeliness.

[0119] high deviation ( ): global correction: mark the abnormal device as unavailable ( ), update the scheduling graph node set (replace the faulty device), re-perform steps S300-S400 to generate a brand new scheduling strategy, such as assigning redundant devices, adjusting the task time window to avoid device maintenance periods.

[0120] In one embodiment, as shown in Figure 3 Also provided is an artificial intelligence-based laboratory equipment management system, the system comprising: a feature vector generation module for generating a device usage feature vector table by collecting course plan data and device historical task record data, and generating the device usage feature vector table based on the course plan data and the device historical task record data; a scheduling atlas construction module for constructing and generating device state performance constraints, time concurrency constraints, and cost risk constraints based on the course feature data and the device state indicator set, integrating to obtain a mixed constraint condition set, and constructing and generating a scheduling atlas based on the mixed constraint condition set; a scheduling strategy calculation module for calculating the scheduling atlas based on the feature vector table through a preset genetic algorithm, and obtaining a scheduling strategy, wherein the scheduling strategy includes a preset device parameter threshold; a scheduling strategy correction module for collecting and obtaining device sensor real-time data, optimizing the scheduling strategy based on the device sensor real-time data and the preset device parameter threshold, and generating a corrected scheduling strategy.

[0121] In another embodiment, the feature vector generation module is further configured to: collect course plan data, extract features from the course plan data to obtain course feature data; collect device historical task record data, analyze the device historical task record data to obtain a device state indicator set; and combine the course feature data and the device state indicator set to generate a device usage feature vector table.

[0122] In another embodiment, the scheduling atlas construction module is further configured to: construct and generate the device state performance constraints and the cost risk constraints based on the device state indicator set; construct and generate the time concurrency constraints based on the course feature data; integrate the device state performance constraints, the time concurrency constraints, and the cost risk constraints to obtain a mixed constraint condition set; and construct and generate a scheduling atlas based on the mixed constraint condition set.

[0123] In another embodiment, the scheduling strategy calculation module is further configured to: extract seed data based on the feature vector table, construct a search space based on the scheduling graph, initialize a genetic algorithm population based on the seed data and the search space, and obtain the scheduling strategy by iteratively optimizing the genetic algorithm population, wherein the scheduling strategy comprises a preset device parameter threshold.

[0124] In one embodiment, a computer device is provided, comprising a memory and a processor, the memory stores a computer program, and the processor implements the steps of the above-mentioned artificial intelligence-based laboratory equipment management method when executing the computer program.

[0125] In one embodiment, a computer readable storage medium is also provided, which stores a computer program, and the computer program is executed by a processor to implement the steps of the above-mentioned artificial intelligence-based laboratory equipment management method.

[0126] It should be noted that the information interaction, execution process and the like between the above modules are based on the same concept as the method embodiments of the present application, and the specific functions and technical effects brought about can be referred to the method embodiments part for details, which will not be repeated here.

[0127] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of each functional unit and module is exemplified, and in actual application, the above-mentioned functions can be completed by different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit, and the integrated unit can be realized in the form of hardware or software. In addition, the specific name of each functional unit and module is only for easy distinction, and does not limit the protection scope of the present application. The specific working process of the units and modules in the system can refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.

[0128] It should be noted that the information interaction, execution process and the like between the above modules are based on the same concept as the method embodiments of the present application, and the specific functions and technical effects brought about can be referred to the method embodiments part for details, which will not be repeated here.

[0129] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above functional units and modules is exemplified, and in actual application, the above functions can be completed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to complete all or part of the above described functions. Each functional unit or module in the embodiment can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit. In addition, the specific name of each functional unit or module is only for convenient distinction, and does not limit the protection scope of the present application. The specific working process of the unit or module in the system can refer to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0130] The embodiments of the present application further provide a network device, which comprises at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor implements the steps in any of the foregoing method embodiments when executing the computer program.

[0131] The embodiments of the present application further provide a computer readable storage medium, which stores a computer program, wherein the computer program is executable on a processor to implement the steps in any of the foregoing method embodiments.

[0132] The embodiments of the present application provide a computer program product, which, when running on a mobile terminal, enables the mobile terminal to implement the steps in any of the foregoing method embodiments.

[0133] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the present application can implement all or part of the processes in the above-mentioned embodiment methods through a computer program to instruct relevant hardware to complete, and the computer program can be stored in a computer readable storage medium. When the computer program is executed by a processor, the steps of each method embodiment described above can be implemented. The computer program includes computer program code, which can be in the form of source code, object code, executable files or some intermediate forms. The computer readable medium can at least include any entity or device capable of carrying the computer program code to the photographing device / terminal equipment, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium. For example, U disk, mobile hard disk, magnetic disk or optical disk, etc. In some jurisdictions, according to legislation and patent practice, the computer readable medium can not be an electrical carrier signal and a telecommunication signal.

[0134] In the above embodiments, the description of each embodiment has its own focus, and the parts not described or recorded in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0135] Those of ordinary skill in the art can understand that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether the functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Professionals can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0136] In the embodiments provided by the present application, it should be understood that the disclosed apparatus / network device and method can be implemented in other ways. For example, the above-described apparatus / network device embodiments are merely schematic, for example, the division of the modules or units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the shown or discussed each other can be indirect coupling or communication connection through some interfaces, devices or units, and can be electrical, mechanical or other forms.

[0137] The units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, i.e., may be located in one place, or may be distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0138] The above-described embodiments are only used to illustrate the technical solutions of the present application, but not limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that the technical solutions recorded in the foregoing embodiments can be modified, or some technical features can be replaced by equivalent ones; and these modifications or replacements do not make the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

[0139] An embodiment of the present application further provides a computer device, which comprises at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement the steps in any of the above-described methods.

[0140] The computer device can include, but is not limited to, a processor and a memory. Those skilled in the art can understand that the above description is an example of the computer device, and does not constitute a limitation on the computer device, and can include more or fewer components than the above description, or combine some components, or different components, for example, can also include an input / output device, a network access device, etc.

[0141] The processor can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or can also be any conventional processor.

[0142] The memory can be an internal storage unit of the computer device in some embodiments, such as a hard disk or a memory of the computer device. The memory can also be an external storage device of the computer device in other embodiments, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. equipped on the computer device. Further, the memory can include both an internal storage unit and an external storage device of the computer device. The memory is used to store an operating system, an application program, a BootLoader, data, and other programs, such as program codes of the computer program, etc. The memory can also be used to temporarily store data that has been output or will be output.

[0143] The technical features of the above embodiments can be combined in any manner. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described, but it should be understood that any combination of the technical features is within the scope of the present disclosure as long as there is no contradiction.

[0144] The above embodiments only express several implementation manners of the present application, and the description is relatively specific and detailed, but it should not be understood as a limitation on the scope of the present application. It should be noted that, for those skilled in the art, some modifications and improvements can be made without departing from the concept of the present application, and these are within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A laboratory equipment management method based on artificial intelligence, characterized in that, The method includes: By collecting course plan data and equipment historical task record data, a device usage feature vector table is generated based on the course plan data and equipment historical task record data; Based on the course feature data and the set of equipment status indicators, equipment status performance constraints, time concurrency constraints and cost risk constraints are constructed and generated, and integrated to obtain a set of mixed constraints. Based on the set of mixed constraints, a scheduling graph is constructed and generated. Based on the feature vector table, the scheduling graph is calculated using a preset genetic algorithm to obtain a scheduling strategy, wherein the scheduling strategy includes preset device parameter thresholds; By collecting real-time data from the device sensors, the scheduling strategy is optimized based on the real-time data from the device sensors and the preset device parameter thresholds, thereby generating a modified scheduling strategy.

2. The laboratory equipment management method based on artificial intelligence according to claim 1, characterized in that, The step of collecting course plan data and equipment historical task record data, and generating an equipment usage feature vector table based on the course plan data and equipment historical task record data, includes: Course plan data is obtained by collecting course plan data and then extracting features from the course plan data. By collecting and acquiring historical task record data of the equipment, and analyzing the historical task record data of the equipment, a set of equipment status indicators is obtained; The course feature data and the set of equipment status indicators are combined to generate a equipment usage feature vector table.

3. The laboratory equipment management method based on artificial intelligence according to claim 1, characterized in that, The process involves constructing and generating equipment status performance constraints, time concurrency constraints, and cost risk constraints based on the course feature data and the equipment status indicator set, integrating these constraints to obtain a mixed constraint set, and then constructing and generating a scheduling graph based on the mixed constraint set, including: Based on the set of equipment status indicators, the equipment status performance constraints and the cost risk constraints are constructed and generated. The time concurrency constraints are generated based on the course feature data. The device state performance constraints, the time concurrency constraints, and the cost risk constraints are integrated to obtain a set of mixed constraints. A scheduling graph is generated based on the aforementioned set of hybrid constraints.

4. The laboratory equipment management method based on artificial intelligence according to claim 1, characterized in that, The scheduling strategy is obtained by calculating the scheduling graph based on the feature vector table using a preset genetic algorithm. The scheduling strategy includes preset device parameter thresholds, including: Seed data is extracted based on the feature vector table, and a search space is constructed based on the scheduling graph. The genetic algorithm is initialized based on the seed data and the search space to generate a genetic algorithm population. The scheduling strategy is obtained by iteratively optimizing the genetic algorithm population, wherein the scheduling strategy includes preset device parameter thresholds.

5. The laboratory equipment management method based on artificial intelligence according to claim 1, characterized in that, The step of acquiring real-time data from device sensors, optimizing the scheduling strategy based on the real-time data and the preset device parameter thresholds, and generating a revised scheduling strategy includes: By collecting real-time data from the device sensors, and calculating the offset anomaly index and the long-term anomaly trend index based on the real-time data from the device sensors and the preset device parameter thresholds; The deviation index is obtained by calculating the deviation anomaly index and the long-term anomaly index; The scheduling strategy is optimized based on the comprehensive deviation index to generate a modified scheduling strategy.

6. A laboratory equipment management system based on artificial intelligence, characterized in that, The system includes: The feature vector generation module is used to collect course plan data and equipment historical task record data, and generate a device usage feature vector table based on the course plan data and equipment historical task record data; The scheduling graph construction module is used to construct and generate equipment status performance constraints, time concurrency constraints, and cost risk constraints based on the course feature data and the equipment status index set, and integrate them to obtain a mixed constraint set. The scheduling graph is then constructed and generated based on the mixed constraint set. The scheduling strategy calculation module is used to calculate the scheduling map based on the feature vector table using a preset genetic algorithm to obtain the scheduling strategy, wherein the scheduling strategy includes preset device parameter thresholds; The scheduling strategy correction module is used to acquire real-time data from the device sensors, optimize the scheduling strategy based on the real-time data from the device sensors and the preset device parameter thresholds, and generate a corrected scheduling strategy.

7. The artificial intelligence-based laboratory equipment management system according to claim 6, characterized in that, The feature vector generation module is also used for: Course plan data is obtained by collecting course plan data and then extracting features from the course plan data. By collecting and acquiring historical task record data of the equipment, and analyzing the historical task record data of the equipment, a set of equipment status indicators is obtained; The course feature data and the set of equipment status indicators are combined to generate a equipment usage feature vector table.

8. The artificial intelligence-based laboratory equipment management system according to claim 6, characterized in that, The scheduling graph construction module is also used for: Based on the set of equipment status indicators, the equipment status performance constraints and the cost risk constraints are constructed and generated. The time concurrency constraints are generated based on the course feature data. The device state performance constraints, the time concurrency constraints, and the cost risk constraints are integrated to obtain a set of mixed constraints. A scheduling graph is generated based on the aforementioned set of hybrid constraints.

9. A computer 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 5.

10. A computer-readable storage medium having a computer program stored thereon, 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 5.

Images