A cold resistance experiment management method and system for fruit trees

Abstract

The present invention provides a method and system for managing fruit tree cold resistance experiments, which relates to the technical field of experimental management. The method includes: generating a digital review model based on the multimodal records of fruit tree cold resistance experiments carried out by an expert group within a preset past time; enabling the expert group to view and operate the digital review model; identifying future experimental assistance requirements generated when the expert group views and operates the digital review model; and interactively providing the corresponding assistance to the expert group that conforms to the future experimental assistance requirements. Generating the digital review model and enabling the expert group to view and operate the digital review model provides a convenient and efficient way for the expert group to review historical experimental situations, improving the efficiency of future experimental planning. In addition, identifying the future experimental assistance requirements generated when the expert group views and operates the digital review model and interactively providing the corresponding assistance to the expert group that conforms to the future experimental assistance requirements provides systematic and intelligent assistance to the expert group, further improving the efficiency of future experimental planning.

Description

Technical Field

[0001] The present invention relates to the technical field of experimental management, and particularly relates to a method and system for managing fruit tree cold resistance experiments. Background Art

[0002] With the increasingly significant impact of climate change on crop growth and yield, how to improve the cold resistance of fruit trees has become a key topic in the field of agricultural research. Fruit tree cold resistance experiments are an important means to address this challenge. When conducting such experiments, experts need to continuously plan and design future experiments. In this process, reviewing the situation of historical experiments is an important prerequisite for planning.

[0003] However, current fruit tree cold resistance experiments usually rely on manual records and lack a convenient and efficient way to review the situation of historical experiments, thus affecting the work efficiency of experts in future experiment planning.

[0004] In addition, after reviewing the situation of historical experiments, experts still need to independently make future experiment planning decisions, lacking systematic and intelligent assistance, which further reduces the work efficiency of experts in future experiment planning and may also affect the comprehensiveness of experiment planning.

[0005] In summary, there is an urgent need for a solution. Summary of the Invention

[0006] One of the purposes of the present invention is to provide a method for managing fruit tree cold resistance experiments, which generates a digital review model for the expert group to view and operate, provides a convenient and efficient way for the expert group to review the situation of historical experiments, improves the efficiency of future experiment planning. In addition, it identifies the future experiment assistance needs generated when the expert group views and operates the digital review model, and interactively provides corresponding assistance to the expert group that conforms to the future experiment assistance needs, provides systematic and intelligent assistance to the expert group, further improves the efficiency of future experiment planning, and more improves the comprehensiveness of experiment planning.

[0007] A method for managing fruit tree cold resistance experiments provided by an embodiment of the present invention includes:

[0008] Generating a digital review model based on the multimodal records of the expert group conducting fruit tree cold resistance experiments in the past first preset time;

[0009] Providing the digital review model for the expert group to view and operate;

[0010] Identifying the future experiment assistance needs generated when the expert group views and operates the digital review model;

[0011] Interactively providing corresponding assistance to the expert group that conforms to the future experiment assistance needs.

[0012] Optionally, the future experimental assistance requirements generated when the identification expert group views the digital review model of the operation include:

[0013] When the expert group views the digital review model of the operation, if the expert group generates a new trigger moment and the total number of generated trigger moments exceeds the number threshold, obtain the first behavior dynamic sequence between the two most recently continuously generated trigger moments by the expert group; wherein, the trigger moment includes: the moment when the expert group views the digital review model of the operation and the digital review model presents a standard model situation;

[0014] Based on the first behavior dynamic sequence, decide the active output control library;

[0015] Based on the active output control library, perform corresponding active output control on the digital review model viewed by the expert group;

[0016] Obtain the second behavior dynamic sequence within the second preset time before and after the end moment of the active output control by the expert group;

[0017] Based on the second behavior dynamic sequence, determine the future experimental assistance requirements.

[0018] Optionally, the decision of the active output control library based on the first behavior dynamic sequence includes:

[0019] Perform feature representation on the first behavior dynamic sequence to obtain the first sequence feature set;

[0020] Obtain multiple groups of corresponding first standard sequence feature sets and active output control knowledge;

[0021] Match the first sequence feature set with each first standard sequence feature set one by one to obtain multiple first matching degrees;

[0022] Take the active output control knowledge corresponding to the first standard sequence feature set with the largest first matching degree with the first sequence feature set as the first content to be stored in the library;

[0023] When the largest first matching degree exceeds the matching degree threshold, establish the active output control library based on the first content to be stored in the library; otherwise, perform time-axis representation on the first content to be stored in the library to obtain the control time axis;

[0024] Endow the control time axis with target control constraints;

[0025] Integrate the control time axis after endowing the target control constraints to obtain the second content to be stored in the library;

[0026] Based on the second content to be stored in the library, establish the active output control library;

[0027] Wherein, the target control constraints include:

[0028] When i = 1, allow the execution of the i-th control strategy on the control timeline;

[0029] When 1 < i ≤ j, after the execution of the (i - 1)-th control strategy on the control timeline is completed, allow the execution of the i-th control strategy on the control timeline; among them, the difference between the sum of the control weights of the first j control strategies on the control timeline and the weight sum threshold is the smallest; the weight sum threshold is the corresponding value of the difference between the maximum first matching degree and the matching degree threshold in the weight sum threshold library; in the weight sum threshold library, the larger the difference between the maximum first matching degree and the matching degree threshold, the smaller the corresponding value;

[0030] When j < i ≤ N, determine whether the execution timing condition of the i-th control strategy on the control timeline is met. If it is met, allow the execution of the i-th control strategy; where N is the total number of control strategies on the control timeline.

[0031] Optionally, determining the future experiment assistance requirements based on the second behavior as a dynamic sequence includes:

[0032] Perform feature representation on the second behavior as a dynamic sequence to obtain a second sequence feature set;

[0033] Obtain multiple groups of corresponding second standard sequence feature sets and standard future experiment assistance requirements;

[0034] Match the second sequence feature set with each second standard sequence feature set one by one to obtain multiple second matching degrees;

[0035] Use the standard future experiment assistance requirement corresponding to the second standard sequence feature set with the largest second matching degree with the second sequence feature set as the future experiment assistance requirement.

[0036] Optionally, the interactive providing of corresponding assistance to the expert group that conforms to the future experiment assistance requirements includes:

[0037] Determine the experiment assistance strategy corresponding to the future experiment assistance requirement from the experiment assistance strategy library;

[0038] Perform sequence representation on the experiment assistance strategy to obtain a strategy execution sequence;

[0039] Determine the target local sequence from the strategy execution sequence; where, after some first assistance strategies in the target local sequence are executed first, the expert group has the ability to independently complete the execution goal of some second assistance strategies in the target local sequence;

[0040] Based on the strategy execution sequence, start providing assistance to the expert group. During the assistance process, after the first assistance strategy in the target local sequence is executed, obtain the necessity of executing the second assistance strategy in the target local sequence;

[0041] When the necessity exceeds the necessity threshold, execute the second auxiliary strategy in the target local sequence.

[0042] Optionally, obtaining the necessity for executing the second auxiliary strategy in the target local sequence includes:

[0043] Start timing and obtain the third behavior dynamic sequence generated by the expert group after starting the timing;

[0044] When the timing duration does not exceed the duration threshold, perform quantization processing on the third behavior dynamic sequence based on the quantization template to obtain the necessity; otherwise, the necessity is counted as a preset threshold; where the preset threshold exceeds the necessity threshold.

[0045] A fruit tree cold resistance experiment management system provided by an embodiment of the present invention includes:

[0046] A generation module for generating a digital review model based on multimodal records of the fruit tree cold resistance experiment carried out by the expert group in the past first preset time;

[0047] A support module for allowing the expert group to view and operate the digital review model;

[0048] An identification module for identifying future experiment assistance requirements generated when the expert group views and operates the digital review model;

[0049] An assistance module for interactively providing corresponding assistance to the expert group that conforms to the future experiment assistance requirements.

[0050] Optionally, the identification module identifying the future experiment assistance requirements generated when the expert group views and operates the digital review model includes:

[0051] When the expert group views and operates the digital review model, if the expert group generates a new trigger moment and the total number of generated trigger moments exceeds the number threshold, obtain the first behavior dynamic sequence between the two most recently continuously generated trigger moments by the expert group; where the trigger moment includes: the moment when the expert group views and operates the digital review model and the digital review model presents a standard model situation;

[0052] Based on the first behavior dynamic sequence, determine the active output control library;

[0053] Based on the active output control library, perform corresponding active output control on the digital review model viewed and operated by the expert group;

[0054] Obtain the second behavior dynamic sequence of the expert group within the second preset time before and after the end moment of the active output control;

[0055] Based on the second behavior dynamic sequence, determine the future experiment assistance requirements.

[0056] Optionally, the decision-making active output control library based on the first dynamic sequence includes:

[0057] Perform feature representation on the first dynamic sequence to obtain a first sequence feature set;

[0058] Obtain multiple groups of corresponding first standard sequence feature sets and active output control knowledge;

[0059] Match the first sequence feature set with each first standard sequence feature set one by one to obtain multiple first matching degrees;

[0060] Use the active output control knowledge corresponding to the first standard sequence feature set with the largest first matching degree with the first sequence feature set as the first content to be stored in the library;

[0061] When the largest first matching degree exceeds the matching degree threshold, establish an active output control library based on the first content to be stored in the library; otherwise, perform a time-axis representation on the first content to be stored in the library to obtain a control time axis;

[0062] Assign target control constraints to the control time axis;

[0063] Integrate the control time axis after assigning the target control constraints to obtain the second content to be stored in the library;

[0064] Establish an active output control library based on the second content to be stored in the library;

[0065] Among them, the target control constraints include:

[0066] When i = 1, allow the i-th control strategy on the control time axis to execute;

[0067] When 1 < i ≤ jj, when the (i - 1)-th control strategy on the control time axis is executed, allow the i-th control strategy on the control time axis to execute; among them, the difference between the sum of the control weights of the first j control strategies on the control time axis and the weight sum threshold is the smallest; the weight sum threshold is the corresponding value of the difference between the largest first matching degree and the matching degree threshold in the weight sum threshold library; in the weight sum threshold library, the larger the difference between the largest first matching degree and the matching degree threshold, the smaller the corresponding value;

[0068] When j < i ≤ N, determine whether the execution timing condition of the i-th control strategy on the control time axis is met. If it is met, allow the i-th control strategy to execute; where N is the total number of control strategies on the control time axis.

[0069] Optionally, the determination of future experimental assistance requirements based on the second dynamic sequence includes:

[0070] Perform feature representation on the second dynamic sequence to obtain a second sequence feature set;

[0071] Obtain multiple groups of second standard sequence feature sets and standard future experiment auxiliary requirements that correspond one by one;

[0072] Match the second sequence feature set with each second standard sequence feature set one by one to obtain multiple second matching degrees;

[0073] Use the standard future experiment auxiliary requirement corresponding to the second standard sequence feature set with the largest second matching degree with the second sequence feature set as the future experiment auxiliary requirement.

[0074] Other features and advantages of the present invention will be described in the subsequent specification, and, in part, will be obvious from the specification, or will be understood by implementing the present invention. The objectives and other advantages of the present invention can be achieved and obtained by the structures specifically pointed out in the written specification and the drawings.

[0075] The technical solutions of the present invention will be further described in detail below through the drawings and embodiments. Brief Description of the Drawings

[0076] The drawings are used to provide a further understanding of the present invention and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the present invention and do not constitute a limitation to the present invention. In the drawings:

[0077] Figure 1 It is a schematic diagram of a fruit tree cold resistance experiment management method in an embodiment of the present invention;

[0078] Figure 2 It is a schematic diagram of a fruit tree cold resistance experiment management system in an embodiment of the present invention. Detailed Embodiments

[0079] The following describes the preferred embodiments of the present invention with reference to the drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention and are not used to limit the present invention.

[0080] The embodiment of the present invention provides a fruit tree cold resistance experiment management method, as Figure 1 shown, including:

[0081] S1. Generate a digital review model based on the multimodal records of the fruit tree cold resistance experiments carried out by the expert group in the past first preset time;

[0082] In S1, the expert group includes multiple fruit tree cold resistance experiment experts; the first preset time can be, for example: 30 days; the multimodal records at least include: historical experiment processes, historical experiment results, expert discussion information, experimental notes, fruit tree cold resistance experiment research literature, etc.; the digital review model is a digital three-dimensional model that can visually display the multimodal records. When generating the digital review model, data visualization tools can be used for generation;

[0083] S2. Provide the digital review model for the expert group to view and operate;

[0084] In S2, when the expert group views and operates the digital review model, the review of the historical experiment situation can be completed, and the planning and design of future experiments can be started;

[0085] S3. Identify the future experiment auxiliary requirements generated when the expert group views and operates the digital review model;

[0086] In S3, the future experiment auxiliary requirements are the requirements generated when the expert group plans and designs future experiments, such as: experiment optimization schemes under certain specific conditions, data analysis requirements, additional experiment condition suggestions, etc.;

[0087] S4. Interactively provide corresponding assistance to the expert group that conforms to the future experiment auxiliary requirements.

[0088] In S4, after identifying the future experiment auxiliary requirements, interactively provide corresponding assistance to the expert group that conforms to the future experiment auxiliary requirements.

[0089] This application generates a digital review model, provides the digital review model for the expert group to view and operate, provides a convenient and efficient way for the expert group to review the historical experiment situation, improves the efficiency of future experiment planning. In addition, it identifies the future experiment auxiliary requirements generated when the expert group views and operates the digital review model, and interactively provides corresponding assistance to the expert group that conforms to the future experiment auxiliary requirements, provides systematic and intelligent assistance to the expert group, further improves the efficiency of future experiment planning, and more improves the comprehensiveness of experiment planning.

[0090] In one embodiment, S3. Identify the future experiment auxiliary requirements generated when the expert group views and operates the digital review model, including:

[0091] S31. When the expert group views and operates the digital review model, if the expert group generates a new trigger moment and the total number of generated trigger moments exceeds the number threshold, obtain the first behavior dynamic sequence between the two most recently continuously generated trigger moments of the expert group; wherein, the trigger moment includes: the moment when the expert group views and operates the digital review model and the digital review model presents the standard model situation;

[0092] In S31, the standard situation at least includes: the digital review model shows content representing that the expert group is about to enter a new idea stage (such as the digital review model shows historical experiment operation comparison information, indicating that the expert group wants to find problems in historical experiment operations, etc.); the number threshold can be, for example: 3; if the expert group generates a new trigger moment and the total number of generated trigger moments exceeds the number threshold, it means that the new idea stage the expert group is about to enter tends to be stable, and based on the first behavior dynamic sequence between the two most recently consecutive trigger moments, the active output control library can be decided. The first behavior dynamic sequence contains multiple personnel behaviors arranged in the order of generation. The personnel behavior knowledge includes: behaviors such as viewing the digital review model, personnel conversation behaviors, collaborative decision-making behaviors, etc.;

[0093] S32. Based on the first behavior dynamic sequence, decide the active output control library;

[0094] In S32, the first behavior dynamic sequence can reflect the behavior situation of the expert group after the most recent time when it is about to enter a new idea stage. This behavior situation can initially reflect what kind of assistance the expert group may hope to obtain, that is, the initial assistance demand. The active output control library is used to control the digital review model to actively output content for detecting whether the expert group has this initial assistance demand. Therefore, the active output control library can be decided based on the first behavior dynamic sequence;

[0095] S33. Based on the active output control library, perform corresponding active output control on the digital review model viewed by the expert group;

[0096] In S33, after the active output control library makes a decision, perform corresponding active output control on the digital review model viewed by the expert group based on it;

[0097] S34. Obtain the second behavior dynamic sequence of the expert group within the second preset time before and after the end moment of the active output control;

[0098] In S34, the expert group will generate behaviors representing whether it has an initial assistance demand within a certain time before and after the end of the active output control. Therefore, the second behavior dynamic sequence can be used to determine future experimental assistance requirements; the second preset time can be, for example: 300 seconds; the second behavior dynamic sequence contains behaviors such as the behavior of the user operating the digital review model to perform active output under the control of the active output control library and personnel conversation behaviors arranged in the order of generation time;

[0099] S35. Based on the second behavior dynamic sequence, determine future experimental assistance requirements.

[0100] In S35, finally, determine future experimental assistance requirements based on the second behavior dynamic sequence.

[0101] The embodiments of the present invention introduce a trigger moment, combine it with an expert group to generate a new trigger moment, and determine whether to enter the future experimental assistance requirement identification opportunity when the total number of generated trigger moments exceeds a number threshold. Between two recently continuously generated trigger moments, a first behavior dynamic sequence serving as the basis for identification control is specifically obtained, which greatly improves the working efficiency of the system and reduces the working resources of the system. Secondly, an active output control library is introduced, and corresponding active output control is performed on the digital review model based on it. Before and within a second preset time after the end of the active output control, a second behavior dynamic sequence serving as the basis for determining future experimental assistance requirements is specifically obtained, and the future experimental assistance requirements of the expert group are determined in a probing manner, which greatly improves the identification efficiency and accuracy of future experimental assistance requirements.

[0102] In one embodiment, S32, based on the first behavior dynamic sequence, making a decision on the active output control library, includes:

[0103] S321. Performing feature representation on the first behavior dynamic sequence to obtain a first sequence feature set;

[0104] In S321, the features in the first sequence feature set at least include: behavior type, behavior generation time, same behavior, etc.;

[0105] S322. Obtaining multiple groups of corresponding first standard sequence feature sets and active output control knowledge;

[0106] In S322, the active output control is at least to indicate how to control the active output of the digital review model to detect whether there is a preliminary assistance requirement for the expert group in the case of the behavior characterized by the first standard sequence feature set. For example, if the first standard sequence feature set characterizes that the expert group wants to change the previous experimental operation, the active output control knowledge indicates that within a certain future time, the proposed changed experimental operations and the corresponding reasons for the change are output in sequence;

[0107] S323. Matching the first sequence feature set with each first standard sequence feature set one by one to obtain multiple first matching degrees;

[0108] In S323, the larger the first matching degree, the more applicable the active output control knowledge corresponding to the first standard sequence feature set is to the current active output control;

[0109] S324. Taking the active output control knowledge corresponding to the first standard sequence feature set with the largest first matching degree with the first sequence feature set as the first content to be stored in the library;

[0110] In S324, the active output control knowledge corresponding to the first standard sequence feature set with the largest first matching degree with the first sequence feature set is relatively the most applicable to the current active output control, and it is taken as the first content to be stored in the library;

[0111] S325. When the maximum first matching degree exceeds the matching degree threshold, an active output control library is established based on the first content to be stored in the library; otherwise, a timeline representation of the first content to be stored in the library is performed to obtain a control timeline.

[0112] In S325, the matching degree threshold can be, for example: 90%; when the maximum first matching degree exceeds the matching degree threshold, it means that the first content to be stored in the library can be used for current active output control, and an active output control library is established based on it; otherwise, further processing of the first content to be stored in the library is required; when performing the timeline representation, multiple control strategies to be executed and their corresponding execution time periods are parsed in the first content to be stored in the library, and each control strategy is set on the timeline based on the corresponding execution time periods to obtain a control timeline.

[0113] S326. Assign target control constraints to the control timeline.

[0114] In S326, since the first content to be stored in the library cannot be directly used for current active output control, target control constraints are assigned to the control timeline.

[0115] S327. Integrate the control timeline after assigning the target control constraints to obtain the second content to be stored in the library.

[0116] In S327, after the control timeline is assigned the target control constraints, it can be used for current active output control and is integrated as the second content to be stored in the library.

[0117] S328. Establish an active output control library based on the second content to be stored in the library.

[0118] Among them, the target control constraints include:

[0119] Constraint 1. When i = 1, allow the i-th (counting from the front to the back) control strategy on the control timeline to be executed.

[0120] In Constraint 1, the first control strategy on the control timeline can be directly executed.

[0121] Constraint 2. When 1 < i ≤ j, when the (i - 1)-th (counting from the front to the back) control strategy on the control timeline is executed, allow the i-th control strategy on the control timeline to be executed; among them, the difference between the sum of the control weights of the first j control strategies on the control timeline and the weight sum threshold is the smallest; the weight sum threshold is the corresponding value of the difference between the maximum first matching degree and the matching degree threshold in the weight sum threshold library; in the weight sum threshold library, the greater the difference between the maximum first matching degree and the matching degree threshold, the smaller the corresponding value.

[0122] In Constraint 2, the difference (the difference between the larger value and the smaller value) between the sum of the control weights of the first j (counting from the front to the back) control strategies on the control time axis and the weight sum threshold is minimized, making j unique; the greater the control weight of a control strategy, the greater the degree of necessity for the execution of the control strategy. For example, if the experimental operation that outputs the most recommended change and the corresponding reason for the change are obtained after the execution of the control strategy, its control weight is set to the maximum value of 10; the greater the difference (the difference between the larger value and the smaller value) between the maximum first matching degree and the matching degree threshold, the higher the degree to which the first content to be stored in the library cannot be used for the current active output control. Therefore, the greater the intensity of restricting the free execution of the control strategy, the smaller the corresponding weight sum threshold in the weight sum threshold library; through the constraint of Constraint 2, multiple control strategies will not be executed simultaneously, avoiding situations such as work interference caused by the simultaneous execution of operations for which the expert group does not have corresponding preliminary assistance requirements.

[0123] Constraint 3: When j < i ≤ N, determine whether the execution timing condition of the i-th control strategy on the control time axis is met. If it is met, allow the i-th control strategy to be executed; where N is the total number of control strategies on the control time axis.

[0124] In Constraint 3, an execution timing condition is introduced for the control strategy. It is executed only when the execution timing condition is met, further restricting the free execution of the control strategy in the subsequent control output stage, and further avoiding situations such as work interference caused by directly executing operations for which the expert group does not have corresponding preliminary assistance requirements; the execution timing condition can be a condition that can represent the need for the control strategy to be executed. For example, if the control strategy execution is to output the experimental operation of the recommended change and the corresponding reason for the change, set its execution timing condition to that the expert group views and rejects all the previously output experimental operations of the recommended change and the corresponding reasons for the change.

[0125] The embodiment of the present invention introduces the first standard sequence feature set and the active output control knowledge, quickly determines the first knowledge to be stored in the library that is relatively most suitable for the current active output control based on the first matching degree, and then quickly determines whether the first knowledge to be stored in the library needs further processing based on the size relationship between the maximum first matching degree and the matching degree threshold, greatly improving the efficiency and accuracy of the decision-making of the active output control library and enhancing the applicability of the system; when further processing the first knowledge to be stored in the library, the first content to be stored in the library is represented as a control time axis, and the target control constraint is given to the control time axis, optimizing the rhythm of the active output control based on the target control constraint, greatly enhancing the suitability of the active output control library for controlling the content for detecting whether the expert group has such a preliminary assistance requirement in the active output of the digital review model, improving the detection effect, further enhancing the applicability of the system, and at the same time, being more user-friendly and intelligent.

[0126] In one embodiment, S35, determining future experimental assistance requirements based on the second behavior dynamic sequence, includes:

[0127] S351. Perform feature representation on the second behavior dynamic sequence to obtain a second sequence feature set;

[0128] In S351, the features in the second sequence feature set at least include: the number of times the user adopts the content actively output by the digital review model under the control of the active output control library, the type of content adopted, etc.;

[0129] S352. Obtain multiple groups of corresponding second standard sequence feature sets and standard future experimental assistance requirements;

[0130] In S352, the standard future experimental assistance requirement represents the future experimental assistance requirement of the expert group in the situation characterized by the second standard sequence feature set. For example, if the second standard sequence feature set represents that the expert group has accepted the experimental operation of a certain proposed change, the corresponding standard future experimental assistance requirement is the specific change suggestion plan for the experimental operation of the proposed change;

[0131] S353. Match the second sequence feature set with each second standard sequence feature set one by one to obtain multiple second matching degrees;

[0132] In S353, the second matching degree represents the degree to which the standard future experimental assistance requirement corresponding to the second standard sequence feature set can be used as the future experimental assistance requirement of the expert group;

[0133] S354. Use the standard future experimental assistance requirement corresponding to the second standard sequence feature set with the largest second matching degree with the second sequence feature set as the future experimental assistance requirement.

[0134] In S354, use the standard future experimental assistance requirement corresponding to the second standard sequence feature set with the largest second matching degree as the future experimental assistance requirement.

[0135] The embodiment of the present invention introduces multiple groups of corresponding second standard sequence feature sets and standard future experimental assistance requirements, and quickly determines the standard future experimental assistance requirement most suitable as the future experimental assistance requirement based on the second matching degree, improving the efficiency and accuracy of determining the future experimental assistance requirement.

[0136] In one embodiment, S4, interactively providing corresponding assistance to the expert group that conforms to the future experimental assistance requirement, includes:

[0137] S41. Determine the experimental assistance strategy corresponding to the future experimental assistance requirement from the experimental assistance strategy library;

[0138] In S41, the experimental assistance strategy is a strategy for the system to execute to meet the future experimental assistance needs of the expert group;

[0139] S42. Perform sequence representation on the experimental assistance strategy to obtain a strategy execution sequence;

[0140] In S42, when performing sequence representation, sort the multiple assistance strategies in the experimental assistance strategy according to the execution order to obtain a strategy execution sequence;

[0141] S43. Determine a target local sequence from the strategy execution sequence; wherein, after some first assistance strategies in the target local sequence are executed first, the expert group has the ability to independently complete the execution target of some second assistance strategies in the target local sequence;

[0142] In S43, the target local sequence contains multiple consecutive assistance strategies in the strategy execution sequence; the execution target is the target to be achieved after the assistance strategy is executed; that some first assistance strategies are executed first and then the expert group has the ability to independently complete the execution target of some second assistance strategies in the target local sequence means that, for example: the future experimental assistance requirement is a specific change suggestion plan for the experimental operation that needs to be changed by this suggestion, the first assistance strategy is to initially output some content of this specific change suggestion plan, the execution target of the second assistance strategy is to enable the expert group to know all the content of this specific change suggestion plan, and the expert group can make decisions on the remaining content by itself after viewing this part of the content;

[0143] S44. Based on the strategy execution sequence, start to assist the expert group. During the assistance process, when the first assistance strategy in the target local sequence is executed, obtain the necessity degree for the execution of the second assistance strategy in the target local sequence;

[0144] In S44, when starting to assist the expert group based on the strategy execution sequence, execute the assistance strategies therein in sequence according to the sequence position; the necessity degree represents the degree of necessity for the execution of the second assistance strategy in the target local sequence;

[0145] S45. When the necessity degree exceeds the necessity degree threshold, execute the second assistance strategy in the target local sequence;

[0146] In S45, the necessity degree threshold can be, for example: 8; when the necessity degree exceeds the necessity degree threshold, it represents that the degree of necessity for the execution of the second assistance strategy in the target local sequence is relatively large, and execute the second assistance strategy in the target local sequence;

[0147] Wherein, in S44, obtaining the necessity degree for the execution of the second assistance strategy in the target local sequence includes:

[0148] S441. Start timing and obtain the third behavior dynamic sequence generated by the expert group after starting timing;

[0149] In S441, the third row in the dynamic sequence includes the behavior of viewing the digital review model of the expert group generated successively after the start of timing, the behavior of personnel conversation, etc. included in the second row in the dynamic sequence, which are sorted in chronological order of generation time.

[0150] S442. When the timing duration does not exceed the duration threshold, based on the quantization template, quantize the third row in the dynamic sequence to obtain the necessity degree; otherwise, the necessity degree is counted as a preset threshold; wherein, the preset threshold exceeds the necessity degree threshold.

[0151] In S442, the duration threshold can be, for example: 120 seconds; there are corresponding necessity degrees for different third rows in the dynamic sequence in the quantization template. The behavior situation represented by the third row in the dynamic sequence indicates that the expert group has completed the execution target of some of the second auxiliary strategies in the target partial sequence more, and the corresponding necessity degree is greater; when the timing duration exceeds the duration threshold, direct copying by the system is required, and the necessity degree meter is directly the preset threshold exceeding the necessity degree threshold.

[0152] The embodiment of the present invention introduces the target partial sequence, enabling the expert group to independently complete the execution of subsequent strategies using some of the information obtained after the execution of the first auxiliary strategy, enhancing the autonomy of the expert group and reducing the burden on the system, making the auxiliary behavior more flexible and efficient; secondly, it can dynamically adjust the necessity degree of the second auxiliary strategy according to the behavior of the expert group, accurately judge whether it is necessary to continue to execute the second auxiliary strategy, thus avoiding unnecessary intervention and resource consumption; in addition, through dynamic timing and necessity degree evaluation, the system can adapt to different situations, automatically adjust the support for the expert group, and improve the applicability of the system.

[0153] The embodiment of the present invention provides a fruit tree cold resistance experiment management system, as Figure 2 shown, including:

[0154] A generation module 1, configured to generate a digital review model based on the multi-modal records of the expert group conducting fruit tree cold resistance experiments in the past first preset time;

[0155] A support module 2, configured to allow the expert group to view and operate the digital review model;

[0156] An identification module 3, configured to identify the future experiment assistance requirements generated when the expert group views and operates the digital review model;

[0157] An assistance module 4, configured to interactively provide corresponding assistance to the expert group that conforms to the future experiment assistance requirements.

[0158] The identification module identifies the future experiment assistance requirements generated when the expert group views and operates the digital review model, including:

[0159] When the expert group views the operation digital review model, if the expert group generates a new trigger moment and the total number of generated trigger moments exceeds the number threshold, obtain the first behavior dynamic sequence between the two most recently continuously generated trigger moments by the expert group; wherein, the trigger moment includes: the moment when the expert group views the operation digital review model and the digital review model presents the standard model situation;

[0160] Based on the first behavior dynamic sequence, decide the active output control library;

[0161] Based on the active output control library, perform corresponding active output control on the digital review model of the expert group's viewing operation;

[0162] Obtain the second behavior dynamic sequence within the second preset time before and after the end moment of the active output control by the expert group;

[0163] Based on the second behavior dynamic sequence, determine the future experimental assistance requirements.

[0164] The decision of the active output control library based on the first behavior dynamic sequence includes:

[0165] Perform feature representation on the first behavior dynamic sequence to obtain the first sequence feature set;

[0166] Obtain multiple groups of corresponding first standard sequence feature sets and active output control knowledge;

[0167] Match the first sequence feature set with each first standard sequence feature set one by one to obtain multiple first matching degrees;

[0168] Take the active output control knowledge corresponding to the first standard sequence feature set with the largest first matching degree with the first sequence feature set as the first content to be stored in the library;

[0169] When the maximum first matching degree exceeds the matching degree threshold, establish an active output control library based on the first content to be stored in the library; otherwise, perform time-axis representation on the first content to be stored in the library to obtain the control time axis;

[0170] Endow the control time axis with target control constraints;

[0171] Integrate the control time axis after endowing the target control constraints to obtain the second content to be stored in the library;

[0172] Based on the second content to be stored in the library, establish an active output control library;

[0173] Among them, the target control constraints include:

[0174] When i = 1, allow the i-th control strategy on the control time axis to execute;

[0175] When 1 < i ≤ j, after the (i - 1)-th control strategy on the control timeline is executed, the i-th control strategy on the control timeline is allowed to be executed; among them, the difference between the sum of the control weights of the first j control strategies on the control timeline and the weight sum threshold is the smallest; the weight sum threshold is the corresponding value of the difference between the maximum first matching degree and the matching degree threshold in the weight sum threshold library; in the weight sum threshold library, the larger the difference between the maximum first matching degree and the matching degree threshold, the smaller the corresponding value.

[0176] When j < i ≤ N, determine whether the execution timing condition of the i-th control strategy on the control timeline is met. If it is met, the i-th control strategy is allowed to be executed; where N is the total number of control strategies on the control timeline.

[0177] Determining the future experimental assistance requirements based on the second behavior dynamic sequence includes:

[0178] Performing feature representation on the second behavior dynamic sequence to obtain a second sequence feature set;

[0179] Obtaining multiple groups of corresponding second standard sequence feature sets and standard future experimental assistance requirements;

[0180] Matching the second sequence feature set with each second standard sequence feature set one by one to obtain multiple second matching degrees;

[0181] Taking the standard future experimental assistance requirement corresponding to the second standard sequence feature set with the largest second matching degree with the second sequence feature set as the future experimental assistance requirement.

[0182] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and its equivalent technologies, the present invention also intends to include these modifications and variations.

Claims

1. A fruit tree cold resistance experimental management method, characterized in that: include: Generate a digital review model based on the multimodal records of the fruit tree cold resistance experiment conducted by the expert group within the first preset time in the past; Provide a digital review model of the operation for the expert group to review; Identify future experimental assistance needs arising from the expert group's review of the operational digital retrospective model; Interactively provide corresponding assistance to the expert group in line with future experimental assistance needs; The identification panel reviewed future experimental assistance needs arising from the operational digital retrospective model, including: When the expert group views the operation digital review model, if the expert group generates a new trigger moment and the total number of generated trigger moments exceeds the number threshold, the first behavior dynamic sequence between the two most recent consecutive trigger moments of the expert group is obtained; wherein the trigger moment includes: the moment when the expert group views the operation digital review model so that the digital review model appears in a standard model situation; the standard model situation includes: the digital review model displays content representing that the expert group is about to enter a new idea stage; Based on the first behavior dynamic sequence, the decision is made to actively output the control library; Based on the active output control library, the digital review model of the expert group's review operation is subjected to corresponding active output control; Obtain a second behavior dynamic sequence of the expert group within a second preset time before and after the end moment of the active output control; Based on the second behavior dynamic sequence, determine future experimental assistance needs; The decision-making active output control library based on the first behavior dynamic sequence includes: Perform feature representation on the dynamic sequence of the first behavior to obtain a first sequence feature set; Acquire multiple groups of one-to-one corresponding first standard sequence feature sets and active output control knowledge; Matching the first sequence feature set with each first standard sequence feature set one by one to obtain a plurality of first matching degrees; Taking the active output control knowledge corresponding to the first standard sequence feature set with the largest first matching degree between the first sequence feature set as the first content to be stored; When the maximum first matching degree exceeds the matching degree threshold, an active output control library is established based on the first content to be stored; otherwise, a time axis is represented for the first content to be stored to obtain a control time axis; Give the control time axis target control constraints; Integrate the control timeline after assigning the target control constraint to obtain the second content to be stored; Based on the second content to be stored, an active output control library is established; Wherein, the target control constraints include: When i=1, the i-th control strategy on the control time axis is allowed to execute; When 1<i≤j, when the execution of the i-1th control strategy on the control timeline is completed, the execution of the i-th control strategy on the control timeline is allowed; wherein the difference between the sum of the control weights of the first j control strategies on the control timeline and the weight and threshold is the smallest; the weight and threshold is the corresponding value of the difference between the maximum first matching degree and the matching threshold in the weight and threshold library; in the weight and threshold library, the larger the difference between the maximum first matching degree and the matching threshold, the smaller the corresponding value; When j<i≤N, determine whether the execution timing condition of the i-th control strategy on the control timeline is met, and if so, allow the i-th control strategy to be executed; wherein N is the total number of control strategies on the control timeline.

2. The fruit tree cold resistance experimental management method according to claim 1, characterized in that: Determining future experimental assistance needs based on the second behavior dynamic sequence includes: Perform feature representation on the dynamic sequence of the second behavior to obtain a feature set of the second sequence; Obtain multiple sets of one-to-one corresponding second standard sequence feature sets and standard future experimental auxiliary requirements; Matching the second sequence feature set with each second standard sequence feature set one by one to obtain a plurality of second matching degrees; The standard future experiment auxiliary demand corresponding to the second standard sequence feature set with the second largest matching degree between the second sequence feature sets is used as the future experiment auxiliary demand.

3. The fruit tree cold resistance experimental management method according to claim 1, characterized in that: The interactive assistance provided to the expert group is in accordance with the future experimental assistance needs, including: Determine the experimental assistance strategy corresponding to the future experimental assistance needs from the experimental assistance strategy library; Perform sequence representation on the experimental auxiliary strategy to obtain the strategy execution sequence; Determine a target local sequence from the strategy execution sequence; wherein, a portion of the first auxiliary strategy in the target local sequence is first executed to enable the expert group to have the ability to independently complete the execution target of a portion of the second auxiliary strategy in the target local sequence; Based on the strategy execution sequence, the expert group begins to be assisted. During the assistance process, after the first auxiliary strategy in the target local sequence is executed, the necessity of executing the second auxiliary strategy in the target local sequence is obtained; When the degree of necessity exceeds the degree of necessity threshold, a second auxiliary strategy in the target partial sequence is executed.

4. The fruit tree cold resistance experimental management method according to claim 3, characterized in that: The obtaining of the necessity of executing the second auxiliary strategy in the target local sequence includes: Start timing, and obtain the third behavior dynamic sequence generated by the expert group after the timing starts; When the timing duration does not exceed the duration threshold, the third behavior dynamic sequence is quantized based on the quantization template to obtain the necessity degree; otherwise, the necessity degree is calculated as a preset threshold; wherein the preset threshold exceeds the necessity degree threshold.

5. A fruit tree cold resistance experimental management system, characterized in that: include: A generation module, for generating a digital review model based on the multimodal records of the fruit tree cold resistance experiment conducted by the expert group within the first preset time in the past; Support module for the expert group to review the operational digital review model; An identification module for identifying future experimental assistance needs generated by the expert group reviewing the operational digital retrospective model; An assistance module is used to interactively provide corresponding assistance to the expert group in accordance with the future experimental assistance needs; The identification module identifies future experimental assistance needs arising from the expert group's review of the operational digital review model, including: When the expert group views the operation digital review model, if the expert group generates a new trigger moment and the total number of generated trigger moments exceeds the number threshold, the first behavior dynamic sequence between the two most recent consecutive trigger moments of the expert group is obtained; wherein the trigger moment includes: the moment when the expert group views the operation digital review model so that the digital review model appears in a standard model situation; the standard model situation includes: the digital review model displays content representing that the expert group is about to enter a new idea stage; Based on the first behavior dynamic sequence, the decision is made to actively output the control library; Based on the active output control library, the digital review model of the expert group's review operation is subjected to corresponding active output control; Obtain a second behavior dynamic sequence of the expert group within a second preset time before and after the end moment of the active output control; Based on the second behavior dynamic sequence, determine future experimental assistance needs; The decision-making active output control library based on the first behavior dynamic sequence includes: Perform feature representation on the dynamic sequence of the first behavior to obtain a first sequence feature set; Acquire multiple groups of one-to-one corresponding first standard sequence feature sets and active output control knowledge; Matching the first sequence feature set with each first standard sequence feature set one by one to obtain a plurality of first matching degrees; Taking the active output control knowledge corresponding to the first standard sequence feature set with the largest first matching degree between the first sequence feature set as the first content to be stored; When the maximum first matching degree exceeds the matching degree threshold, an active output control library is established based on the first content to be stored; otherwise, a time axis is represented for the first content to be stored to obtain a control time axis; Give the control time axis target control constraints; Integrate the control timeline after assigning the target control constraint to obtain the second content to be stored; Based on the second content to be stored, an active output control library is established; Wherein, the target control constraints include: When i=1, the i-th control strategy on the control time axis is allowed to execute; When 1<i≤j, when the execution of the i-1th control strategy on the control timeline is completed, the execution of the i-th control strategy on the control timeline is allowed; wherein the difference between the sum of the control weights of the first j control strategies on the control timeline and the weight and threshold is the smallest; the weight and threshold is the corresponding value of the difference between the maximum first matching degree and the matching threshold in the weight and threshold library; in the weight and threshold library, the larger the difference between the maximum first matching degree and the matching threshold, the smaller the corresponding value; When j<i≤N, determine whether the execution timing condition of the i-th control strategy on the control timeline is met, and if so, allow the i-th control strategy to be executed; wherein N is the total number of control strategies on the control timeline.

6. The fruit tree cold resistance experimental management system according to claim 5, characterized in that: Determining future experimental assistance needs based on the second behavior dynamic sequence includes: Perform feature representation on the dynamic sequence of the second behavior to obtain a feature set of the second sequence; Obtain multiple sets of one-to-one corresponding second standard sequence feature sets and standard future experimental auxiliary requirements; Matching the second sequence feature set with each second standard sequence feature set one by one to obtain a plurality of second matching degrees; The standard future experiment auxiliary demand corresponding to the second standard sequence feature set with the second largest matching degree between the second sequence feature sets is used as the future experiment auxiliary demand.

Images