Information processing method and device, electronic device, and computer readable medium

Abstract

The present disclosure provides an information processing method and device, which relates to the fields of grain storage management and safe production technology. The specific implementation scheme is: obtaining input parameters; determining the subject to be controlled and ventilation rules based on the input parameters and the grain storage knowledge map; judging whether ventilation conditions are met based on the subject to be controlled and the ventilation control model; in response to the judgment result that ventilation conditions are met, ventilating the subject to be controlled according to the ventilation rules; obtaining updated ventilation rules based on the grain storage situation model and the multimodal intelligent analysis model, and determining the storage service information of the subject to be controlled based on the grain storage situation model and the attributes of the subject to be controlled; obtaining the storage process information of the subject to be controlled based on the storage service information, the green grain storage process knowledge base, and the green grain storage control model; obtaining operation prompt information based on the storage process information, the grain storage safety production knowledge map, and the grain storage safety production accident case knowledge map; improving the efficiency and accuracy of information processing.

Description

Technical Field

[0001] The present invention relates to the field of grain storage management and safe production technology, and in particular to an information processing method and device, an electronic device, and a computer-readable storage medium. Background Art

[0002] Grain depots are important infrastructures. Some grain depots with better conditions have installed and deployed multiple cameras in the office area, storage area and granary to monitor the operation of various business operations in real time. Grain depot managers use these image information, grain depot management regulations, and their own management knowledge and experience to store grain and judge whether the grain depot business operations are normal.

[0003] Existing grain depots do not have a unified automated management system. They only rely on manual storage of grain or monitoring of grain depot operations, which is inefficient and unable to effectively manage the grain in the depot.

[0004] The information disclosed in this background technology section is only intended to enhance the understanding of the overall background of the disclosure and should not be regarded as an acknowledgement or any form of suggestion that the information constitutes the prior art already known to a person skilled in the art. Summary of the invention

[0005] The present disclosure provides an information processing method and apparatus, an electronic device, and a computer-readable storage medium.

[0006] According to the first aspect, an information processing method is provided, which includes: obtaining input parameters; determining a subject to be controlled and ventilation rules based on the input parameters and a grain storage knowledge graph; judging whether ventilation conditions are met based on the subject to be controlled and a ventilation control model; in response to a judgment result that ventilation conditions are met, ventilating the subject to be controlled according to the ventilation rules; and updating the ventilation rules based on a grain storage situation model and a multimodal intelligent analysis model to obtain updated ventilation rules.

[0007] According to a second aspect, an information processing device is provided, which includes: an acquisition unit configured to acquire input parameters; a determination unit configured to determine a subject to be controlled and ventilation rules based on the input parameters and a grain storage knowledge graph; a judgment unit configured to judge whether ventilation conditions are met based on the subject to be controlled and a ventilation control model; a control unit configured to perform ventilation processing on the subject to be controlled according to the ventilation rules in response to a judgment result that ventilation conditions are met; and an update unit configured to perform ventilation processing on the subject to be controlled according to the ventilation rules in response to a judgment result that ventilation conditions are met.

[0008] According to a third aspect, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method described in any implementation manner of the first aspect.

[0009] According to a fourth aspect, a non-transitory computer-readable storage medium storing computer instructions is provided, where the computer instructions are used to cause a computer to execute the method described in any implementation of the first aspect.

[0010] The information processing method and device provided by the embodiment of the present disclosure first obtain input parameters; secondly, based on the input parameters and the grain storage knowledge graph, determine the subject to be controlled and the ventilation rules; thirdly, based on the subject to be controlled and the ventilation control model, determine whether the ventilation conditions are met; thirdly, in response to the judgment result that the ventilation conditions are met, ventilate the subject to be controlled according to the ventilation rules; finally, based on the grain storage situation model and the multimodal intelligent analysis model, update the ventilation rules to obtain the updated ventilation rules. Through the input parameters and the grain storage knowledge graph, determine the subject to be controlled, detect whether the ventilation conditions are met based on the subject to be controlled and the intelligent ventilation control model, and when the ventilation conditions are met, ventilate the subject to be controlled, which can intelligently monitor whether the grain in the grain depot needs to be ventilated; further, based on the grain storage situation model and the multimodal intelligent analysis model, update the ventilation rules in real time, so that the processing of the subject to be controlled can be updated in real time under the scientific grain storage situation, improve the safety of grain in the grain depot, reduce monitoring manpower, and save monitoring costs.

[0011] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0013] Figure 1 is a flow chart of an embodiment of an information processing method according to the present disclosure;

[0014] Figure 2 is a schematic structural diagram of an embodiment of an information processing device according to the present disclosure;

[0015] Figure 3 The block diagram is a block diagram of an electronic device for implementing the information processing method according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0016] Unless explicitly stated otherwise, throughout the specification and claims, the term “comprise” or variations such as “include” or “comprising”, etc., will be understood to include the stated elements or components but not to exclude other elements or components.

[0017] The technical solution of the present disclosure is described below by means of specific embodiments. It should be understood that one or more steps mentioned in the present disclosure do not exclude the existence of other methods and steps before and after the combination step, or other methods and steps may be inserted between these explicitly mentioned steps. It should also be understood that these examples are only used to illustrate the present disclosure and are not used to limit the scope of the present disclosure. Unless otherwise specified, the numbering of each method step is only for the purpose of identifying each method step, and does not limit the order of arrangement of each method or limit the scope of implementation of the present disclosure. Changes or adjustments in their relative relationships can also be regarded as the scope of implementation of the present disclosure without substantial changes in the technical content.

[0018] The sources of the raw materials and instruments used in the examples are not particularly limited and can be purchased from the market or prepared according to conventional methods known to those skilled in the art.

[0019] If the grain stored in the granary is not properly stored, it may generate heat, condense, become mildewed, and become infested with insects, which may seriously affect food security.

[0020] Generally, a grain condition measurement and control system needs to be deployed in a grain depot to measure the temperature of the grain pile and the humidity of the air on the surface and inside the grain pile. In recent years, some grain depots have also deployed oxygen and carbon dioxide sensors to monitor the gas content of the grain pile. Grain depot custodians judge the health status of the grain pile based on the data measured by these sensors, as well as their years of grain storage expertise and practical experience. Once they find signs of heating, condensation, mildew, or insects in the grain, or there is a possibility of these phenomena, they must carry out grain storage operations such as ventilation and fumigation. However, relying solely on manual judgment will result in low implementation efficiency and high human costs.

[0021] In view of the above defects, the present disclosure proposes an information processing method, which automatically determines whether the controlled subject meets the ventilation conditions. When the ventilation conditions are met, the controlled subject is ventilated according to the ventilation rules, thereby improving the safety of grain in the grain depot, reducing the work intensity of the staff, and improving the work efficiency. Figure 1 A process 100 according to an embodiment of the information processing method of the present disclosure is shown. The information processing method comprises the following steps:

[0022] Step 101, obtaining input parameters.

[0023] In this embodiment, the multimodal knowledge base of the grain depot is the basis of the grain depot's brain, and the execution entity on which the information processing method runs is a grain depot management system. An operation interface is set on the grain depot management system, and users or managers can input parameters into the operation interface. The grain depot management system manages or controls the grain depot based on the input parameters.

[0024] In this embodiment, the input parameters are indicator data currently input or historically input by the management personnel, and the input parameters include: the subject to be controlled and the attribute information of the subject to be controlled, wherein the subject to be controlled is the object that needs to be managed by the execution subject on which the information processing method runs, and the object belongs to the current grain warehouse, for example, the grain in granary No. 1; the attribute information is the attributes of the controlled object, for example, the source and area where the subject to be controlled is located.

[0025] Step 102, based on the input parameters and the grain storage knowledge graph, determine the subject to be controlled and the ventilation rules.

[0026] In this embodiment, the grain storage knowledge graph is a graph related to grain storage, and the grain storage knowledge graph includes: basic types of grains, storage rules for various types of grains, grain condition inspection rules for various types of grains, abnormal grain condition identification rules for various types of grains, abnormal grain condition disposal rules for various types of grains, pest types, various pest control rules, ventilation rules for various types of grains, fumigation rules for various types of grains, etc.

[0027] In this embodiment, the ventilation rules are ventilation rules for ventilating the subject to be controlled. The ventilation rules can limit the ventilation method of ventilating the subject to be controlled, such as cooling ventilation, precipitation ventilation, anti-condensation ventilation, heat removal ventilation, conditioning ventilation, etc.; according to the ventilation rules, ventilation operations can be performed on the subject to be controlled, such as: opening windows, opening windows to the full extent, turning on fans, and turning on fans.

[0028] In this embodiment, the ventilation rules are the above step 102 including: based on the input parameters, determining the subject to be controlled; based on the subject to be controlled, obtaining the ventilation rules related to the subject to be controlled from the grain storage knowledge graph, and obtaining the subject to be controlled and the ventilation rules.

[0029] Step 103, based on the subject to be controlled and the ventilation control model, determine whether ventilation conditions are met.

[0030] In this embodiment, the ventilation control model is a model for judging whether the grain depot where the subject to be controlled currently is located meets the ventilation conditions. The ventilation control model is a model developed based on various grain industry standard procedures. After obtaining the subject to be controlled, the attribute information of the subject to be controlled is determined. Based on the attribute information, the basic information such as the warehouse type, fan type, grain storage ecological area, working mode (cooling ventilation, precipitation ventilation, anti-condensation ventilation, heat removal ventilation, conditioning ventilation), grain condition, dew point temperature, etc. of the grain depot where the subject to be controlled is located is obtained. The basic information is input into the ventilation control model. The ventilation control model can automatically calculate the absolute humidity of the air, the enthalpy value of the wet air, the specific volume of the wet air, the dew point of the air, etc., and automatically calculate whether the ventilation conditions are met according to the formula, and automatically judge whether the ventilation needs to be suspended or terminated. When the ventilation needs to be suspended or terminated, it is determined that the ventilation conditions are not met; otherwise, it is determined that the ventilation conditions are met.

[0031] Step 104 , in response to the judgment result that ventilation conditions are met, ventilation treatment is performed on the controlled subject according to ventilation rules.

[0032] In this embodiment, the ventilation rules include a processing method for ventilating the subject to be controlled. Ventilating the subject to be controlled according to the rules means ventilating the subject to be controlled according to the processing method indicated by the ventilation rules. For example, ventilating the subject to be controlled according to the ventilation rules includes: opening the window of the granary where the subject to be controlled is located.

[0033] Optionally, when the judgment result is that ventilation conditions are not met, the ventilation rules are updated directly based on the grain storage situation model and the multimodal intelligent analysis model to obtain updated ventilation rules, and continue to judge whether ventilation conditions are met based on the subject to be controlled and the ventilation control model.

[0034] Step 105, based on the grain storage situation model and the multimodal intelligent analysis model, the ventilation rules are updated to obtain updated ventilation rules.

[0035] In this embodiment, the grain storage situation model is a model for analyzing the attributes and service change curves of multiple different types of objects in historical periods. Six-tuple data of multiple different types of objects are established in the grain storage situation model. By querying the six-tuple data in the grain storage situation model, the process processing rules required for each object at each time point can be determined.

[0036] Specifically, the grain storage situation model includes: six-tuple data including attributes, past, current situation, trend, relationship and service, where attribute refers to a certain type of data, such as grain temperature; past refers to the value, action and characteristics of the attribute in the past period of time (such as high temperature, gradient abnormality, etc.); current situation refers to the current value, action and characteristics of the attribute, and trend refers to the predicted value and characteristics of the attribute in the future, which is predicted by the "multimodal intelligent analysis model"; service refers to various grain storage and preservation behaviors, such as ventilation, fumigation, nitrogen storage and other disposal suggestions and detailed processes; relationship refers to the correspondence between the combined data of attributes, past, current situation and trend and the service.

[0037] In this embodiment, the multimodal intelligent analysis model is used to predict the attributes of the subject to be controlled and obtain the development trend of the subject to be controlled in the future time period.

[0038] In this embodiment, the above-mentioned step 105 includes: matching the attributes of the subject to be controlled and the subject to be controlled with the six-tuple number of the grain storage situation model respectively to obtain the past and current situation of the subject to be controlled; inputting the past and current situation into the multimodal intelligent analysis model to obtain the trend output by the multimodal intelligent analysis model; matching the trend output by the multimodal intelligent analysis model with the six-tuple number of the grain storage situation model to obtain the grain storage and preservation behavior of the subject to be controlled, and when the grain storage and preservation behavior includes ventilation disposal suggestions, the ventilation disposal suggestions in the grain storage and preservation behavior are used as updated ventilation rules.

[0039] Optionally, the above step 105 also includes: obtaining combined data such as past, current, and trend of the attributes of the subject to be controlled from the grain storage situation model, the grain storage situation model selects specific grain storage services that meet the combined data, and executes the specific grain storage service.

[0040] In this embodiment, the execution entity on which the information processing method runs, that is, the brain of the grain depot, will connect and integrate the relevant contents in various knowledge bases that need to be used in the course of various business progress, so as to provide comprehensive, accurate and consistent knowledge.

[0041] The information processing method provided by the embodiment of the present disclosure first obtains input parameters; secondly, based on the input parameters and the grain storage knowledge graph, determines the subject to be controlled and the ventilation rules; thirdly, based on the subject to be controlled and the ventilation control model, determines whether the ventilation conditions are met; thirdly, in response to the judgment result that the ventilation conditions are met, the subject to be controlled is ventilated according to the ventilation rules; finally, based on the grain storage situation model and the multimodal intelligent analysis model, the ventilation rules are updated to obtain the updated ventilation rules. Through the input parameters and the grain storage knowledge graph, the subject to be controlled is determined, and whether the ventilation conditions are met is detected based on the subject to be controlled and the intelligent ventilation control model. When the ventilation conditions are met, the subject to be controlled is ventilated, and whether the grain in the grain depot needs to be ventilated can be intelligently monitored; further, based on the grain storage situation model and the multimodal intelligent analysis model, the ventilation rules are updated in real time, so that the processing of the subject to be controlled can be updated in real time under the scientific grain storage situation, thereby improving the safety of grain in the grain depot, reducing monitoring manpower, and saving monitoring costs.

[0042] Optionally, for some grain depots with relatively strict requirements, the above information processing method also includes: determining the first subject and nitrogen filling recommendation information; judging whether the nitrogen filling conditions are met based on the first subject and the nitrogen filling control model; in response to the judgment result that the nitrogen filling conditions are met, nitrogen filling the first subject according to the nitrogen filling recommendation information.

[0043] In some embodiments of the present disclosure, the above-mentioned information processing method also includes: determining the storage service information of the subject to be controlled based on the grain storage situation model and the attributes of the subject to be controlled; obtaining the storage process information of the subject to be controlled based on the storage service information, the green grain storage process knowledge base, and the green grain storage control model.

[0044] In this embodiment, the attributes of the subject to be controlled are the inherent properties of the subject to be controlled itself, and the attributes of the subject to be controlled can be obtained from the grain storage knowledge graph and also from a preset database.

[0045] In this embodiment, the custody service information is the custody behavior of the subject to be controlled.

[0046] In this embodiment, the attributes of the subject to be controlled are matched with the attributes in the grain storage situation model to obtain the attributes of the grain storage situation model that match the attributes of the subject to be controlled, and the services corresponding to the attributes of the grain storage situation model that match the attributes of the subject to be controlled are used as storage service information.

[0047] In this embodiment, the storage process information is the specific process flow and process steps of the storage behavior of the subject to be controlled.

[0048] In this embodiment, the green grain storage process knowledge base is a process knowledge base related to grain storage. Specifically, the green grain storage process knowledge base includes process equipment, process, process steps, process parameters, etc. of various grain storage methods such as ventilation, nitrogen gas storage, carbon dioxide gas storage, and temperature control (low temperature, quasi-low temperature) storage.

[0049] In this embodiment, the green grain storage control model is a knowledge base for the control subject to perform different grain storage methods. Specifically, the green grain storage control model includes input parameters, starting conditions, control logic, abnormal control and other control methods for various grain storage methods such as ventilation, nitrogen gas storage, carbon dioxide gas storage, and temperature control (low temperature, quasi-low temperature) storage.

[0050] In this embodiment, after determining the custody service information, the custody behavior in the custody service information is determined; the process equipment, process, process steps, and process parameters related to the custody behavior are selected from the green grain storage process knowledge base; the input parameters, start-up conditions, control logic, abnormal control and other control methods related to the process equipment, process, process steps, and process parameters are selected from the green grain storage control model, and all control methods and process steps are sorted in chronological order to obtain the custody process information of the subject to be controlled.

[0051] The information processing method provided in this embodiment determines the storage service information of the subject to be controlled based on the grain storage situation model and the attributes of the subject to be controlled; based on the storage service information, the green grain storage process knowledge base, and the green grain storage control model, the storage process information of the subject to be controlled is obtained, which provides a reliable implementation method for more rational storage of the subject to be controlled and improves the safety of grain storage.

[0052] In some embodiments of the present disclosure, the above-mentioned information processing method also includes: obtaining operation prompt information for each process step of the subject to be controlled based on storage process information, grain warehouse production safety knowledge graph, and grain warehouse production safety accident case knowledge graph.

[0053] In this embodiment, the grain depot safety production knowledge graph is a safety production graph related to grain storage. Specifically, the grain depot safety production knowledge graph is based on some common industry requirements and standard procedures for grain depot safety production, and uses a bidirectional long short-term memory network and a convolutional neural network to extract entities to construct the resulting knowledge graph. The grain depot safety production knowledge graph includes information on safety production requirements such as grain in and out of warehouses, simple grain storage, fumigation and gas conditioning, fire prevention and explosion prevention.

[0054] In this embodiment, the grain depot production safety accident case knowledge graph edits the food safety warning audio and video released by relevant departments, as well as the production safety accidents that have occurred in the industry, into videos including the food safety accident process and causes of the accidents, and associates the accident process, causes of the accidents, etc. with the relevant content of the "Grain Depot Production Safety Knowledge Graph" in the form of text, video, sound, etc. to obtain a knowledge graph.

[0055] In this embodiment, the operation prompt information is information that prompts the state that affects production safety during the process of the process flow or process step operation. The operation prompt information can be intuitive information represented in multiple modal forms. For example, the operation prompt information is the text, picture, video, and sound of the production safety risks, precautions, and previous accidents of each process step of the grain storage operation. The operation prompt information can also be a control signal for controlling the process equipment. When the operation prompt information is a control signal, the corresponding process equipment can be controlled to shut down or pause.

[0056] In this embodiment, the above-mentioned operation prompt information for each process step of the subject to be controlled based on the storage process information, the grain depot production safety knowledge graph, and the grain depot production safety accident case knowledge graph includes: matching the storage process information with the information in the grain depot production safety knowledge graph and the grain depot production safety accident case knowledge graph respectively; in response to the storage process information matching the warning information affecting production safety in the grain depot production safety knowledge graph and the grain depot production safety accident case knowledge graph, the warning information is associated with the process step of the storage process information, and the associated information is used as the operation prompt information.

[0057] The information processing method provided in this embodiment obtains operation prompt information for each process step of the subject to be controlled based on the storage process information, the grain warehouse production safety knowledge graph, and the grain warehouse production safety accident case knowledge graph. While reasonably storing the subject to be controlled, it provides more rational process steps for operating the subject to be controlled, thereby improving the convenience and rationality of the operation of the subject to be controlled.

[0058] In some optional implementations of the present disclosure, the above-mentioned grain depot production safety knowledge graph is constructed through the following steps: based on the grain depot industry standard procedure information and entity extraction rules, the production entities and the production requirement information of each production entity are obtained; based on the production entities and the production requirement information, the grain depot production safety knowledge graph is obtained.

[0059] In this optional implementation, the grain depot industry standard procedure information is information related to industry requirements and standard procedures. For example, the grain depot industry standard procedure information includes: grain depot production safety codes, grain circulation industry production safety inspection guidelines, etc.

[0060] In this optional implementation, the entity extraction rule is a rule that identifies entities with specific meanings from text and classifies them into predefined categories. The main task of the entity extraction rule is to identify production entities such as grain, warehouses, and processes from the text corresponding to the grain warehouse industry standard procedure information.

[0061] In this optional implementation, the production entity is an entity related to grain storage and grain circulation, such as different types of grains, different types of warehouses, etc. The production requirement information is a necessary requirement for production safety of the production entity, such as grain in and out warehouse requirements, grain ventilation requirements, grain fumigation requirements, etc.

[0062] In this optional implementation, the above-mentioned grain depot production safety knowledge graph based on production entities and production requirement information includes: for each production entity, determining the production requirement information of the production entity; associating and storing the production entity with its corresponding production requirement information to obtain the grain depot production safety knowledge graph.

[0063] The method for constructing a grain depot production safety knowledge graph provided by this optional implementation method obtains production entities and production requirement information of each production entity based on the grain depot industry standard procedure information and entity extraction rules; based on the production entities and production requirement information, a grain depot production safety knowledge graph is obtained, and the grain depot industry requirements and entity extraction rules can be combined to obtain a grain depot production safety knowledge graph, thereby improving the accuracy and reliability of the grain depot production safety knowledge graph.

[0064] In some embodiments of the present disclosure, the above-mentioned information processing method also includes: using a large language model adapter to generate production prompt words; generating production accident videos based on production prompt words and Wensheng video models; and adding production accident videos to the grain warehouse production safety accident case knowledge graph.

[0065] In this embodiment, the large language model adapter is a device that can be connected to the large model. The current mainstream large model can be connected through the large language model adapter. When there is no characteristic knowledge in the existing knowledge base, the large language model is needed to feedback relevant answers; at the same time, the Wensheng video model is connected.

[0066] In this embodiment, the production prompt words are prompt contents that instruct the large model to generate corresponding contents. By calling the "large language model adapter", the large language model prompt words are automatically produced, which can maximize the adaptation to the needs of the large model.

[0067] In this embodiment, the Vincent video model may be a model for generating videos. Inputting text information such as production prompt words into the Vincent video model may obtain a production accident video output by the Vincent video model.

[0068] In this embodiment, adding the production accident video to the grain depot production safety accident case knowledge graph includes: determining the production entity corresponding to the production accident video; based on the production entity, merging the production accident video with the video related to the production entity in the grain depot production safety accident case knowledge graph.

[0069] The information processing method provided in this embodiment completes the knowledge graph of grain depot production safety accident cases through a large model. Specifically: many existing grain depot production safety accident cases do not have pictures and video data of the accident, let alone accident cause analysis videos. If all videos are produced manually, the efficiency is too low. The Wensheng video model is called through the large language model adapter to automatically produce prompt words, and automatically generate accident scene pictures and videos. Through repeated iterations and manual review, the knowledge graph of grain depot production safety accident cases can be completed.

[0070] The information processing method provided in this embodiment adopts a large language model adapter to generate production prompt words; based on the production prompt words and the Wensheng video model, a production accident video is generated, and the production accident video is added to the knowledge graph of grain depot production safety accident cases. While enriching the knowledge graph of grain depot production safety accident cases, it provides effective materials for grain depot management and improves the reliability of grain depot management.

[0071] In some embodiments of the present disclosure, the above-mentioned information processing method also includes: based on the subject to be controlled and the updated ventilation rules, using a large language model adapter to generate suggestion prompt words; based on the suggestion prompt words and the large language model, generating operation guidance information of the subject to be controlled.

[0072] In this embodiment, the operation instruction information is information that instructs the operator or controller to execute the updated ventilation rules; the suggestion prompt word is a prompt word that prompts the large language model to output the operation instruction information. By inputting the suggestion prompt word into the large language model, the large language model can give reasonable operation instruction information to the operator or controller.

[0073] In this embodiment, the large language model adapter is a model that can integrate the information of the controlled subject and the updated ventilation rules. The large language model adapter organically combines the operation plan, operation process monitoring and other functions in the updated ventilation rules, and further enables the large language model to generate operation guidance information, which can enable grain custodians to better understand the operation steps, operation risks, and operation optimization suggestions.

[0074] The information processing method provided in this embodiment uses a large language model adapter to generate suggestion prompt words based on the subject to be controlled and the updated ventilation rules; based on the suggestion prompt words and the large language model, the operation guidance information of the subject to be controlled is generated. The generated operation guidance information provides a reliable basis for optimizing the operation of the subject to be controlled, and enables the staff to perform reasonable operations on the subject to be controlled based on the operation guidance information.

[0075] In some optional implementations of the present disclosure, a grain storage knowledge graph is obtained by the following steps: entity extraction is performed on the specified grain and oil storage corpus to obtain storage entities and storage specification information; based on the storage entities and storage specification information, a grain storage knowledge graph including basic storage information of various grains is generated.

[0076] In this optional implementation, the storage rule information is rule information for storing different types of grains under different processes or procedures.

[0077] In this optional implementation, a bidirectional long short-term memory network and a convolutional neural network can be used to extract entities from the grain and oil storage corpus to construct a grain preservation knowledge graph; specifically, entities related to various types of grains are first extracted from the grain and oil storage corpus; then, custody rule information related to the custody rules related to grain storage is extracted from the grain and oil storage corpus; based on the grain and oil storage corpus, the custody rule information closest to each entity is determined and associated to obtain a grain preservation knowledge graph.

[0078] In this optional implementation, the storage rule information includes: storage rules for various types of grains, grain condition inspection rules for various types of grains, abnormal grain condition identification rules for various types of grains, abnormal grain condition disposal rules for various types of grains, pest types, various pest control rules, ventilation rules for various types of grains, fumigation rules for various types of grains, etc.

[0079] The method for obtaining a grain storage knowledge graph provided by this optional implementation first performs entity extraction on the specified grain and oil storage corpus to obtain storage entities and storage specification information; then, based on the storage entities and storage specification information, a grain storage knowledge graph including basic storage information of a variety of grains is generated, which provides a reliable implementation method for obtaining the grain storage knowledge graph and improves the reliability of obtaining the grain storage knowledge graph.

[0080] The information processing method provided in this embodiment creates a stable, reliable, and co-evolving grain storage knowledge base by combining the interpretability and reliability of the knowledge graph, the strong logic of the situation modeling, and the powerful semantic understanding ability of the large model. The combined knowledge graph includes: basic intelligent ventilation control model, grain storage knowledge graph, grain depot production safety knowledge graph, grain depot production safety accident case knowledge graph, grain storage situation model, green grain storage process knowledge base, green grain storage control model, and large language model adapter to fully express the rules and regulations, common sense, experience, mechanism knowledge, expert knowledge, data knowledge, etc. of grain storage.

[0081] Further references Figure 2 As an implementation of the methods shown in the above figures, the present disclosure provides an embodiment of an information processing device, which is similar to Figure 1 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0082] like Figure 2 As shown, the information processing device 200 provided in this embodiment includes: an acquisition unit 201, a determination unit 202, a judgment unit 203, a control unit 204, and an update unit 205. Among them, the acquisition unit 201 can be configured to acquire input parameters. The determination unit 202 can be configured to determine the subject to be controlled and the ventilation rules based on the input parameters and the grain storage knowledge graph. The judgment unit 203 can be configured to judge whether the ventilation conditions are met based on the subject to be controlled and the ventilation control model. The control unit 204 can be configured to perform ventilation processing on the subject to be controlled according to the ventilation rules in response to the judgment result that the ventilation conditions are met. The update unit 205 can be configured to perform ventilation processing on the subject to be controlled according to the ventilation rules in response to the judgment result that the ventilation conditions are met.

[0083] In this embodiment, the specific processing of the acquisition unit 201, the determination unit 202, the judgment unit 203, the control unit 204, and the updating unit 205 in the information processing device 200 and the technical effects thereof can be referred to in Figure 1 The relevant descriptions of step 101, step 102, step 103, step 104, and step 105 in the corresponding embodiments are not repeated here.

[0084] In some embodiments of the present disclosure, the information processing device 200 further includes: a storage unit (not shown in the figure), and the storage unit is further configured to: determine the storage service information of the subject to be controlled based on the grain storage situation model and the attributes of the subject to be controlled; and obtain the storage process information of the subject to be controlled based on the storage service information, the green grain storage process knowledge base, and the green grain storage control model.

[0085] In some embodiments of the present disclosure, the above-mentioned information processing device 200 also includes: a process operation unit (not shown in the figure), and the above-mentioned process operation unit is further configured to: obtain operation prompt information for each process step of the subject to be controlled based on storage process information, grain warehouse production safety knowledge graph, and grain warehouse production safety accident case knowledge graph.

[0086] In some embodiments of the present disclosure, the above-mentioned grain depot production safety knowledge graph is constructed by a first construction unit (not shown in the figure), and the above-mentioned first construction unit is configured to: obtain production entities and production requirement information of each production entity based on grain depot industry standard procedure information and entity extraction rules; obtain grain depot production safety knowledge graph based on production entities and production requirement information.

[0087] In some embodiments of the present disclosure, the above-mentioned information processing device 200 also includes: an adding unit (not shown in the figure), and the above-mentioned adding unit is further configured to: use a large language model adapter to generate production prompt words; generate production accident videos based on production prompt words and Wensheng video models; add the production accident videos to the knowledge graph of grain warehouse production safety accident cases.

[0088] In some embodiments of the present disclosure, the information processing device 200 further includes: an operation unit (not shown in the figure), and the operation unit is further configured to: generate suggestion prompt words based on the subject to be controlled and the updated ventilation rules, using a large language model adapter; and generate operation guidance information of the subject to be controlled based on the suggestion prompt words and the large language model.

[0089] In some embodiments of the present disclosure, the above-mentioned grain storage knowledge graph is obtained by using a second construction unit (not shown in the figure), and the above-mentioned second construction unit is configured to: perform entity extraction on the specified grain and oil storage corpus to obtain storage entities and storage specification information; based on the storage entities and storage specification information, generate a grain storage knowledge graph including basic storage information of multiple grains.

[0090] The information processing method and device provided by the embodiment of the present disclosure, first, the acquisition unit 201 acquires input parameters; secondly, the determination unit 202 determines the subject to be controlled and the ventilation rules based on the input parameters and the grain storage knowledge map; thirdly, the judgment unit 203 judges whether the ventilation conditions are met based on the subject to be controlled and the ventilation control model; then, the control unit 204 responds to the judgment result that the ventilation conditions are met, and performs ventilation processing on the subject to be controlled according to the ventilation rules; finally, the updating unit 205 updates the ventilation rules based on the grain storage situation model and the multimodal intelligent analysis model to obtain the updated ventilation rules. Through the input parameters and the grain storage knowledge map, the subject to be controlled is determined, and whether the ventilation conditions are met is detected based on the subject to be controlled and the intelligent ventilation control model. When the ventilation conditions are met, the subject to be controlled is ventilated, and whether the grain in the grain depot needs to be ventilated can be intelligently monitored; further, based on the grain storage situation model and the multimodal intelligent analysis model, the ventilation rules are updated in real time, so that the processing of the subject to be controlled can be updated in real time under the scientific grain storage situation, thereby improving the safety of grain in the grain depot, reducing monitoring manpower, and saving monitoring costs.

[0091] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0092] Figure 3 A schematic block diagram of an example electronic device 300 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their modes are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0093] like Figure 3 As shown, the device 300 includes a computing unit 301, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 302 or a computer program loaded from a storage unit 308 into a random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the device 300 can also be stored. The computing unit 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0094] A number of components in the device 300 are connected to the I / O interface 305, including: an input unit 306, such as a keyboard, a mouse, etc.; an output unit 307, such as various types of displays, speakers, etc.; a storage unit 308, such as a disk, an optical disk, etc.; and a communication unit 309, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 309 allows the device 300 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0095] The computing unit 301 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 301 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 301 performs the various methods and processes described above, such as information processing methods. For example, in some embodiments, the information processing method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 308. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 300 via the ROM 302 and / or the communication unit 309. When the computer program is loaded into the RAM 303 and executed by the computing unit 301, one or more steps of the information processing method described above may be performed. Alternatively, in other embodiments, the computing unit 301 may be configured to perform the information processing method in any other appropriate manner (e.g., by means of firmware).

[0096] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0097] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable information processing device, so that the program code, when executed by the processor or controller, implements the modes / operations specified in the flow chart and / or block diagram. The program code may be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.

[0098] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0099] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0100] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0101] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0102] The foregoing description of specific exemplary embodiments of the present disclosure is for the purpose of illustration and demonstration. These descriptions are not intended to limit the present disclosure to the precise form disclosed, and it is clear that many changes and variations can be made based on the above teachings. The purpose of selecting and describing the exemplary embodiments is to explain the specific principles of the present disclosure and its practical application, so that those skilled in the art can realize and utilize various different exemplary embodiments of the present disclosure and various different selections and changes. The scope of the present disclosure is intended to be defined by the claims and their equivalents.

Claims

1. An information processing method, characterized in that: The method comprises: Get input parameters; Based on the input parameters and the grain storage knowledge graph, determine the subject to be controlled and the ventilation rules; Based on the subject to be controlled and the ventilation control model, determining whether ventilation conditions are met; In response to the judgment result that the ventilation condition is met, ventilating the subject to be controlled according to the ventilation rule; Based on the grain storage situation model and the multimodal intelligent analysis model, the ventilation rules are updated to obtain updated ventilation rules. The ventilation rules are updated based on the grain storage situation model and the multimodal intelligent analysis model to obtain updated ventilation rules, including: matching the subject to be controlled and the attributes of the subject to be controlled with the six-tuple number of the grain storage situation model respectively to obtain the past and current status of the subject to be controlled; inputting the past and current status into the multimodal intelligent analysis model to obtain the trend output by the multimodal intelligent analysis model, wherein the trend refers to the predicted value and characteristics of the attribute for a period of time in the future; matching the trend with the six-tuple number of the grain storage situation model to obtain the grain storage behavior of the subject to be controlled, and when the grain storage behavior includes ventilation disposal suggestions, using the ventilation disposal suggestions as the updated ventilation rules; Based on the grain storage situation model and the attributes of the subject to be controlled, the storage service information of the subject to be controlled is determined; based on the storage service information, the green grain storage process knowledge base, and the green grain storage control model, the storage process information of the subject to be controlled is obtained, including: matching the attributes of the subject to be controlled with the attributes in the grain storage situation model to obtain the grain storage situation model attributes that match the attributes of the subject to be controlled, and using the services corresponding to the grain storage situation model attributes that match the attributes of the subject to be controlled as the storage service information; after determining the storage service information, determining the storage behavior in the storage service information; selecting process equipment, process, process steps, and process parameters related to the storage behavior from the green grain storage process knowledge base; selecting control methods related to process equipment, process, process steps, and process parameters from the green grain storage control model, the control methods including input parameters, start conditions, control logic, and abnormal control, sorting all control methods and process in chronological order, and obtaining the storage process information of the subject to be controlled; Based on the storage process information, the grain depot safety production knowledge graph, and the grain depot safety production accident case knowledge graph, operation prompt information for each process step of the subject to be controlled is obtained, including: matching the storage process information with the information in the grain depot safety production knowledge graph and the grain depot safety production accident case knowledge graph respectively; in response to the storage process information matching the warning information affecting safety production in the grain depot safety production knowledge graph and the grain depot safety production accident case knowledge graph, the warning information is associated with the process step of the storage process information, and the associated information is used as the operation prompt information; Using a large language model adapter to generate production prompt words; based on the production prompt words and the Wensheng video model, generating a production accident video; adding the production accident video to the grain depot safety production accident case knowledge graph; Based on the subject to be controlled and the updated ventilation rules, a large language model adapter is used to generate suggestion prompt words; based on the suggestion prompt words and the large language model, operation guidance information of the subject to be controlled is generated.

2. According to the method of claim 1, the grain depot safety production knowledge graph is constructed by the following steps: Based on the grain depot industry standard procedure information and entity extraction rules, obtain the production entity and the production requirement information of each production entity; Based on the production entity and the production requirement information, a knowledge graph of grain depot production safety is obtained.

3. The method according to claim 1 or 2, wherein: The grain storage knowledge graph is obtained by the following steps: Entity extraction is performed on the specified grain and oil storage corpus to obtain storage entities and storage specification information; Based on the storage entity and the storage specification information, a grain storage knowledge graph including a variety of basic grain storage information is generated.

4. An information processing device, characterized in that: The device comprises: An acquisition unit configured to acquire input parameters; A determination unit configured to determine a subject to be controlled and a ventilation rule based on the input parameters and the grain storage knowledge graph; A judgment unit is configured to judge whether ventilation conditions are met based on the subject to be controlled and the ventilation control model; A control unit is configured to, in response to a judgment result that ventilation conditions are met, perform ventilation processing on the subject to be controlled according to the ventilation rule; The updating unit is configured to update the ventilation rules based on the grain storage situation model and the multimodal intelligent analysis model to obtain updated ventilation rules; the updating unit is further configured to: match the subject to be controlled and the attributes of the subject to be controlled with the six-tuple number of the grain storage situation model respectively to obtain the past and current status of the subject to be controlled; input the past and current status into the multimodal intelligent analysis model to obtain the trend output by the multimodal intelligent analysis model, and the trend refers to the predicted value and characteristics of the attribute for a period of time in the future; match the trend with the six-tuple number of the grain storage situation model to obtain the grain storage behavior of the subject to be controlled, and when the grain storage behavior includes ventilation treatment suggestions, use the ventilation treatment suggestions as the updated ventilation rules; The storage unit is configured to determine the storage service information of the subject to be controlled based on the grain storage situation model and the attributes of the subject to be controlled; obtain the storage process information of the subject to be controlled based on the storage service information, the green grain storage process knowledge base, and the green grain storage control model, specifically including: matching the attributes of the subject to be controlled with the attributes in the grain storage situation model to obtain the grain storage situation model attributes that match the attributes of the subject to be controlled, and using the services corresponding to the grain storage situation model attributes that match the attributes of the subject to be controlled as the storage service information; after determining the storage service information, determining the storage behavior in the storage service information; selecting process equipment, process, process steps, and process parameters related to the storage behavior from the green grain storage process knowledge base; selecting control methods related to process equipment, process, process steps, and process parameters from the green grain storage control model, wherein the control methods include input parameters, start conditions, control logic, and abnormal control, and all control methods and process processes are sorted in chronological order to obtain the storage process information of the subject to be controlled; The process operation unit is configured to obtain operation prompt information for each process step of the subject to be controlled based on the storage process information, the grain depot production safety knowledge graph, and the grain depot production safety accident case knowledge graph, specifically including: matching the storage process information with the information in the grain depot production safety knowledge graph and the grain depot production safety accident case knowledge graph respectively; in response to the storage process information matching the warning information affecting production safety in the grain depot production safety knowledge graph and the grain depot production safety accident case knowledge graph, associating the warning information with the process step of the storage process information, and using the associated information as the operation prompt information; The adding unit is configured to use a large language model adapter to generate production prompt words; generate a production accident video based on the production prompt words and the Wensheng video model; and add the production accident video to the grain depot production safety accident case knowledge graph; The operation unit is configured to generate suggestion prompt words based on the subject to be controlled and the updated ventilation rules by using a large language model adapter; and generate operation guidance information of the subject to be controlled based on the suggestion prompt words and the large language model.

5. An electronic device, characterized in that: include: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method according to any one of claims 1 to 3.

6. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to enable the computer to execute the method according to any one of claims 1 to 3.

Images