Method for feeding back abnormal operation of refrigeration equipment, refrigeration equipment and storage medium
By establishing a knowledge base in refrigeration equipment, using deep learning models and knowledge graphs to integrate data, and monitoring and output solutions in real time, the problem that users cannot detect and solve equipment abnormalities in a timely manner, improving user operation efficiency and reducing maintenance time.
Patent Information
- Application Number
- CN202310507136.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-05-06
- Publication Date
- 2024-11-08
AI Technical Summary
In the prior art, refrigeration equipment will not actively provide problems and solutions when it is operating abnormally, resulting in users being unable to discover and solve problems in a timely manner. The operation status log and solution manual are mainly on the enterprise side, which makes users difficult to operate and cumbersome repair methods.
By obtaining historical data and real-time data, preprocessing and key information extraction, establishing a knowledge base, using deep learning models for entity and relationship extraction, combining knowledge graph fusion, real-time monitoring and archive data, judge exceptions based on preset thresholds and output to solve plan.
Passing abnormal operation logs and solutions to the user side improves the speed and efficiency of users to solve problems, reduces repair time, and avoids the impact of equipment abnormalities on users.
Smart Images

Figure CN118912793A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of abnormal feedback of refrigeration equipment, and in particular to a method for feeding back abnormal operation of refrigeration equipment, refrigeration equipment and a storage medium. Background Art
[0002] With the maturity of speech recognition ASR technology, the intelligent communication function between users and smart refrigeration equipment has been realized. In most cases, users are the active party issuing commands or voice, such as adding language to the refrigeration equipment or asking questions. However, when the refrigeration equipment is running in an abnormal state, users ask how to solve a certain problem of the refrigeration equipment or ask the manufacturer to repair it. When users ask questions, they may get irrelevant answers due to recognition errors in the process of describing the problem. Manufacturer repairs will take a long time and the trouble of on-site repairs will cause users to be unable to use the refrigeration equipment for a long time.
[0003] Therefore, in the prior art, when the refrigeration equipment operates abnormally, the problems and solutions will not be proactively provided, resulting in users being unable to discover and solve the problems in a timely manner. In addition, the operating status logs of the refrigeration equipment and the manuals for specific solutions are all on the enterprise side, resulting in users not knowing how to operate and solve the problems when faced with them, wasting time and making the maintenance process complicated. Summary of the invention
[0004] The purpose of the present invention is to provide a method for feedback of abnormal operation of refrigeration equipment, refrigeration equipment and storage medium; to solve the problem in the prior art that when the refrigeration equipment operates abnormally, the problems and solutions that arise will not be actively provided, resulting in users being unable to discover and solve the problems in time, and the operation status log of the refrigeration equipment and the manual for specific solutions are all on the enterprise side, resulting in users not knowing how to operate and solve the problems when faced with them, which wastes time and makes the maintenance process complicated.
[0005] To achieve one of the above-mentioned purposes of the invention, the present invention provides a method for feedback of abnormal operation of refrigeration equipment, the method comprising: obtaining historical data and extracting to form first information, the historical data comprising abnormal operation logs and abnormal operation solution documents; storing the first information in a knowledge base; obtaining real-time data and comparing it with a preset standard threshold, if the real-time data is greater than the standard threshold, configuring abnormal data conversion text and querying the knowledge base; outputting the corresponding information in the knowledge base.
[0006] As a further improvement of the present invention, the method also includes: the historical data is formed into text format data through preprocessing and key information is extracted from the text format data to form first information, and the processed data includes structured data, semi-structured data and unstructured data; the key information extraction includes entity extraction and relationship extraction through a deep learning model, the entity extraction is used to extract category information, and the relationship extraction is used to extract triple information in the text format data, and the triple information includes a subject and the relationship between multiple subjects.
[0007] As a further improvement of the present invention, the method also includes: the processing of the real-time data includes: obtaining the real-time data and storing the real-time data in a historical database; the real-time data and the original historical data form new historical data in the historical database, extracting second information based on the new historical data, fusing the first information and the second information through entity alignment and updating the fusion result in the knowledge base.
[0008] As a further improvement of the present invention, the method also includes: fusing the knowledge graph through ontology fusion technology, storing the fusion result of the knowledge graph in the knowledge base, the knowledge graph including the solution to abnormal operation of refrigeration equipment; establishing an association between the fusion result of the first information and the second information and the fusion result of the knowledge graph.
[0009] As a further improvement of the present invention, the method also includes: setting the real-time data archiving time; if the archiving time is reached, opening the historical data updating branch to store the real-time data in a historical database; if the archiving time is not reached, opening the real-time data monitoring branch to detect the operating status of the refrigeration equipment in real time.
[0010] As a further improvement of the present invention, the method also includes: the processing of the real-time data also includes: real-time data preprocessing, converting the real-time data into text format data, extracting features in the text format data; pre-setting templates and standard thresholds; comparing the size of the features and the standard thresholds; if the features are greater than the standard thresholds, configuring the abnormal data conversion text according to the template with the preset value; performing entity extraction and relationship extraction according to the configured template text; querying the knowledge base based on the subjects extracted by the entity extraction and the relationship extraction and retrieving corresponding information under the same subject in the knowledge base, wherein the corresponding information includes abnormal data solutions.
[0011] As a further improvement of the present invention, the method further includes: if the characteristic data is less than or equal to a standard threshold, returning to perform real-time data collection.
[0012] As a further improvement of the present invention, the method also includes: outputting the corresponding information in the knowledge base including: detecting the setting status, the setting status being whether the user receives abnormal reminders; if the detection is yes, outputting the abnormal data conversion text and outputting the corresponding information in the knowledge base, the information including the abnormal data solution; if the detection is no, returning to execute real-time data collection.
[0013] The present invention also provides a refrigeration device, comprising a memory and a processor, wherein the refrigeration device comprises: the memory stores a computer program that can be run on the processor, and when the program is executed on the processor, the steps in the above-mentioned method of feedback on abnormal operation of the refrigeration device are implemented.
[0014] The present invention also provides a storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the method for feedback of abnormal operation of a refrigeration device are implemented.
[0015] Compared with the prior art, the present invention has the following beneficial effects: traditional abnormal operation logs and solution documents are not only used on the enterprise side, but also on the user side. Various solutions to abnormal operation are stored based on the abnormal operation logs and solution documents and integrated with the knowledge graph. Then, solutions are queried according to the corresponding data acquired in real time and actively fed back to users, which greatly improves the speed and efficiency of user solutions and avoids the dangers caused by abnormal operation and the impact of abnormal operation of refrigeration equipment on users. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] Figure 1 It is a flow chart of the method for providing feedback on abnormal operation of refrigeration equipment according to the present invention.
[0017] Figure 2 It is a flow chart for comparing and judging the real-time data collected by the present invention with the preset standard threshold value.
[0018] Figure 3 It is a system diagram in the refrigeration equipment of the present invention. DETAILED DESCRIPTION
[0019] The present invention will be described in detail below in conjunction with the specific embodiments shown in the accompanying drawings. However, these embodiments do not limit the present invention, and any structural, methodological, or functional changes made by a person skilled in the art based on these embodiments are all within the scope of protection of the present invention.
[0020] In the first embodiment of the present invention, a method for feedback of abnormal operation of a refrigeration device is provided. Although the present application provides the following implementation method or process Figure 1The method operation steps shown are based on routine or no creative labor, and the execution order of the steps in the method that do not have a necessary causal relationship in logic is not limited to the execution order provided in the implementation mode of this application. Figure 1 As shown, a method for feedback of abnormal operation of refrigeration equipment, the steps are as follows:
[0021] S1: Acquire historical data and extract it to form first information, wherein the historical data includes abnormal operation logs and abnormal operation solution documents.
[0022] In one embodiment of the present invention, the abnormal operation log can be loaded in advance into the refrigeration equipment system, including all other users' past abnormal data logs; the abnormal operation solution document can also be loaded in advance into the refrigeration equipment system, including various solutions to the abnormal problems of refrigeration equipment, such as the knowledge graph of abnormal problems of refrigeration equipment, etc.
[0023] Furthermore, historical data includes structured data, semi-structured data and unstructured data, so it is necessary to convert data with different structures into text format data.
[0024] S2: Storing the first information in a knowledge base.
[0025] S3: Acquire real-time data and compare it with a preset standard threshold. If the real-time data is greater than the standard threshold, configure abnormal data conversion text and query the knowledge base. It should be noted that the real-time data is the data of the current operating state of the refrigeration equipment detected. The standard threshold is the normal data value of each part when the refrigeration equipment is operating normally.
[0026] S4: Output the corresponding information in the knowledge base.
[0027] In one embodiment of the present invention, the historical data is preprocessed to form text format data and key information is extracted from the text format data to form the first information.
[0028] Furthermore, key information extraction includes entity extraction and relationship extraction through a deep learning model, wherein the entity extraction is used to extract category information, and the relationship extraction is used to extract triple information in text format data, wherein the triple information includes a subject and the relationship between multiple subjects.
[0029] For example, the text information of the abnormal operation solution document in the knowledge base is "The solution to the blockage of the refrigeration equipment drain is to flush the drain with clean water." The entity extraction task will specify the category of the vocabulary to be extracted. For example, if the category is "electrical appliances," "refrigeration equipment" will be extracted from the text information. Relation extraction is to extract triple information from the text. For example, the two words "refrigeration equipment" and "drain" will be extracted from the above text information, and the relationship between the two words is "component." The relationship between the words in the relationship extraction is manually determined in advance. At present, named entity recognition and relationship extraction usually use the same deep learning model for information extraction, such as the deep learning model SpERT.
[0030] In one embodiment of the present invention, the processing of real-time data includes:
[0031] Acquire real-time data and store it in the historical database; specifically, this process can be understood as archiving, and update the abnormal operation log in the historical data in real time. You can also set the archiving time, and archive the collected real-time data in the historical data during the archiving time, including all refrigeration equipment operation logs from the last archiving time to the current archiving time.
[0032] Furthermore, the real-time data and the original historical data (which can be understood as the abnormal operation log and abnormal operation solution document initially loaded into the refrigeration equipment) form new historical data in the historical database, and the new historical data includes the abnormal operation log and abnormal operation solution document initially loaded into the refrigeration equipment and the current refrigeration equipment operation log collected in real time. Specifically, the real-time data periodically archives the collected refrigeration equipment operation data in the historical data according to the set archiving time; extracts the second information based on the new historical data, fuses the first information and the second information through entity alignment, and updates the fusion result in the knowledge base.
[0033] Regarding the above entity alignment, it should be noted that entity alignment is mainly because the names corresponding to the same type of things are different during the extraction process. For example, the electrical appliance extracted from the historical data is "refrigeration equipment", but the electrical appliance extracted from the text information "Diversified functions of electric refrigeration equipment" in the new historical data after integrating real-time data is "electric refrigeration equipment". In order to unify the thing "refrigeration equipment", it is necessary to uniformly assign the "electric refrigeration equipment" here to "refrigeration equipment".
[0034] In the first embodiment of the present invention, a knowledge graph is fused through ontology fusion technology, and the fusion result of the knowledge graph is stored in a knowledge base, wherein the knowledge graph includes a solution to abnormal operation of refrigeration equipment; an association is established between the fusion result of the first information and the second information and the fusion result of the knowledge graph.
[0035] Regarding the above ontology fusion, it should be noted that ontology fusion is mainly aimed at the fusion between different graphs. In addition to storing historical data, it is also possible to directly obtain other knowledge graphs and put them into the knowledge base. Using ontology fusion, two knowledge graphs can be merged into one knowledge graph.
[0036] Furthermore, entity alignment and ontology fusion techniques can be implemented with corresponding deep learning models.
[0037] In one embodiment of the present invention, the archiving time of real-time data is set as follows:
[0038] If the archiving time is reached, the historical data updating branch is opened to store the real-time data in the historical database; if the archiving time is not reached, the real-time data monitoring branch is opened to detect the operating status of the refrigeration equipment in real time.
[0039] Furthermore, in this embodiment, the processing of real-time data also includes: Figure 2 As shown:
[0040] Real-time data preprocessing, converting the real-time data into text format data, and extracting features from the text format data;
[0041] Preset templates and standard thresholds. It should be noted that the preset value template is because when abnormal data is detected, it is necessary to convert the abnormal data into query statements and search for abnormal solutions in the knowledge base.
[0042] Compare the size of the feature and the standard threshold; if the feature is greater than the standard threshold, configure the abnormal data conversion text according to the preset template; if the feature data is less than or equal to the standard threshold, return to perform real-time data collection. This process is used to check whether there is abnormal data in the real-time data. The standard threshold has been stored in the cloud system in advance; based on the comparison of real-time data, the program automatically checks for abnormal data. For example, the water level at the drain outlet of the refrigeration equipment, such as the standard threshold is 0 to 2 cm, but the value captured in the real-time data is 3 cm. If it exceeds the threshold range, it means that there is an abnormality in the drain outlet of the refrigeration equipment.
[0043] Perform entity extraction and relationship extraction based on the configured template text. For example, the above shows that the real-time data of the refrigeration equipment drain outlet is 3 cm, which exceeds the standard threshold: 0-2 cm. When configuring the template, it is found that the real-time data is greater than the standard threshold and can be matched as "exceeding the range". The converted template data is "refrigeration equipment drain outlet exceeds the range". After performing entity extraction and relationship extraction on the text, the parsed information is "refrigeration equipment-->components-->drain outlet"; "drain outlet-->abnormal problem-->exceeding the range".
[0044] Based on the subject extracted from entity and relationship, the knowledge base is queried and corresponding information is retrieved under the same subject in the knowledge base. The corresponding information includes solutions to abnormal data. For example, according to the above analysis steps, the solution to "the drain outlet of the refrigeration equipment exceeds the range" is queried in the knowledge base. The above same subject represents the refrigeration equipment and the drain outlet. Based on the "refrigeration equipment" in the detected information, the various components of the refrigeration equipment are searched, and the corresponding information about the drain outlet in the knowledge base is searched based on the "drain outlet". Then, the solution to the corresponding information under the drain outlet is queried according to the abnormal problem.
[0045] Furthermore, in this embodiment, the corresponding information in the output knowledge base includes:
[0046] Detecting a setting status, wherein the setting status is whether the user receives abnormality reminders;
[0047] If the detection result is yes, outputting the abnormal data conversion text and the corresponding information in the knowledge base, wherein the information includes the abnormal data solution;
[0048] If the detection result is negative, the system returns to perform real-time data collection.
[0049] In a second embodiment of the present invention, a refrigeration device is provided, including a memory and a processor.
[0050] The memory stores a computer program that can be run on the processor, and when the program is executed on the processor, the steps in the method for providing feedback on abnormal operation of a refrigeration device in the first embodiment are implemented.
[0051] Further, such as Figure 3 As shown, the refrigeration equipment includes the following systems:
[0052] The terminal monitoring module is installed inside the refrigeration equipment to monitor real-time data.
[0053] Historical database: The historical database is used to store historical data and real-time data. Historical data includes abnormal operation logs and abnormal operation solution documents.
[0054] The acquisition module is connected to the terminal monitoring module and is used to collect real-time data and historical data and transmit them to the knowledge base.
[0055] The knowledge base is used to store real-time data and historical data. The knowledge base includes a fusion module. The fusion module uses ontology fusion technology to fuse different knowledge graphs, and uses entity alignment technology to fuse the original historical data in the historical database and the new historical data after incorporating the real-time data. The original historical data represents the abnormal operation logs and abnormal operation solution documents initially loaded, and the new historical data represents the data formed after the real-time data is collected and stored in the historical database together with the abnormal operation logs and abnormal operation solution documents.
[0056] The comparison module is connected to the acquisition module. The acquisition module transmits the collected real-time data to the comparison module. A standard threshold is preset inside the comparison module. The real-time data is compared with the standard threshold. If the real-time data is less than the standard threshold, it returns to execute real-time data collection; if the real-time data is greater than the standard threshold, it enters the configuration module.
[0057] Configuration module, preset value template, entity extraction and relationship extraction based on the configured template text. For example, the real-time data of the refrigeration equipment drain outlet is 3 cm, and the standard threshold is 0-2 cm. When configuring the template, it is found that the real-time data is greater than the standard threshold and can be matched as "exceeding the range". The converted template data is "refrigeration equipment drain outlet exceeds the range". After entity extraction and relationship extraction of the text, the parsed information is "refrigeration equipment-->components-->drain outlet"; "drain outlet-->abnormal problem-->exceeding the range".
[0058] The query module is connected to the configuration module and the knowledge base respectively. The query module is used to query the knowledge base according to the information in the configuration module and find out the solution from the knowledge base.
[0059] The output module is connected to the query module and outputs the answer based on the solution found by the query module in the knowledge base.
[0060] In a third embodiment of the present invention, a storage medium is provided, wherein the storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the method for providing feedback on abnormal operation of a refrigeration device in the first embodiment are implemented.
[0061] In summary, the present invention aims to solve the problem that the existing technology does not actively provide the problem and solution when the refrigeration equipment operates abnormally, resulting in the user being unable to discover and solve the problem in time, and the operation status log of the refrigeration equipment and the manual for specific solutions are all on the enterprise side, which results in the user not knowing how to operate and solve the problem when faced with the problem, which wastes time and makes the maintenance process complicated.
[0062] The present invention mainly stores historical data in the knowledge base, including abnormal operation logs and abnormal operation solution documents, and obtains real-time data, uses preset standard thresholds to compare real-time data, determines whether the refrigeration equipment is operating abnormally, and then queries the abnormal solution from the knowledge base. At the same time, the real-time data is regularly archived in the knowledge base for updating the knowledge base, which is convenient for updating new refrigeration equipment problems in the knowledge base. The real-time data and historical data in the knowledge base, as well as multiple knowledge graphs and abnormal operation solution documents in the knowledge base are integrated by using entity alignment and ontology fusion models, and the solutions to abnormal operation problems are output using configured templates.
[0063] In the present invention, traditional abnormal operation logs and solution documents are not only used on the enterprise side, but also on the user side. Various solutions to abnormal operation are stored based on the abnormal operation logs and solution documents and integrated with the knowledge graph. Then, solutions are queried according to the corresponding data obtained in real time and actively fed back to users, which greatly improves the speed and efficiency of user solutions and avoids the dangers caused by abnormal operation and the impact of abnormal operation of refrigeration equipment on users.
[0064] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems, systems and modules can refer to the corresponding processes in the aforementioned method implementation methods and will not be repeated here.
[0065] In several embodiments provided in the present application, it should be understood that the disclosed systems, systems and methods can be implemented in other ways. For example, the system implementation described above is only schematic, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, systems or modules, which can be electrical, mechanical or other forms. The modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, that is, they may be located in one place, or they may be distributed on multiple network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the present implementation scheme.
[0066] In addition, each functional module in each embodiment of the present application can be integrated into a processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The above-mentioned integrated module can be implemented in the form of hardware or in the form of hardware plus software functional modules. The above-mentioned integrated module implemented in the form of software functional modules can be stored in a computer-readable storage medium. The above-mentioned software functional modules are stored in a storage medium, including a number of instructions for a computer system (which can be a personal computer, a server, or a network system, etc.) or a processor (processor) to perform some steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk.
[0067] Finally, it should be noted that the above implementation modes are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned implementation modes, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned implementation modes, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various implementation modes of the present application.
Claims
1. A method for feedback of abnormal operation of refrigeration equipment, characterized in that: include: Acquire historical data and extract it to form first information, wherein the historical data includes abnormal operation logs and abnormal operation solution documents; storing the first information in a knowledge base; Acquire real-time data and compare it with a preset standard threshold. If the real-time data is greater than the standard threshold, configure abnormal data conversion text and query the knowledge base; Output the corresponding information in the knowledge base.
2. The method for abnormal operation of feedback refrigeration equipment according to claim 1, characterized in that: The historical data is formed into text format data through preprocessing and key information is extracted from the text format data to form the first information, and the processed data includes structured data, semi-structured data and unstructured data; The key information extraction includes entity extraction and relationship extraction through a deep learning model, wherein the entity extraction is used to extract category information, and the relationship extraction is used to extract triple information in text format data, wherein the triple information includes a subject and the relationship between multiple subjects.
3. The method for abnormal operation of feedback refrigeration equipment according to claim 2, characterized in that: The processing of the real-time data includes: Acquire the real-time data and store the real-time data in a historical database; The real-time data and the original historical data form new historical data in the historical database, the second information is extracted based on the new historical data, the first information and the second information are fused through entity alignment, and the fusion result is updated in the knowledge base.
4. The method for abnormal operation of feedback refrigeration equipment according to claim 3, characterized in that: The knowledge graph is fused through ontology fusion technology, and the fusion result of the knowledge graph is stored in the knowledge base, wherein the knowledge graph includes a solution to abnormal operation of refrigeration equipment; an association is established between the fusion result of the first information and the second information and the fusion result of the knowledge graph.
5. The method for abnormal operation of feedback refrigeration equipment according to claim 4, characterized in that: Setting the real-time data archiving time; If the archiving time is reached, the historical data update branch is opened to store the real-time data in the historical database; If the archiving time has not been reached, the real-time data monitoring branch is opened to detect the operating status of the refrigeration equipment in real time.
6. The method for abnormal operation of feedback refrigeration equipment according to claim 4, characterized in that: The processing of the real-time data also includes: Real-time data preprocessing, converting the real-time data into text format data, and extracting features from the text format data; Pre-set templates and standard thresholds; Compare the size of the feature to the standard threshold; If the feature is greater than a standard threshold, the abnormal data is converted into text according to a template configuration of a preset value; Perform entity extraction and relationship extraction based on the configured template text; The subject extracted based on the entity extraction and the relationship extraction queries the knowledge base and retrieves the corresponding information under the same subject in the knowledge base, wherein the corresponding information includes the abnormal data solution.
7. The method for abnormal operation of a feedback refrigeration device according to claim 1, characterized in that: If the characteristic data is less than or equal to the standard threshold, the process returns to perform real-time data collection.
8. The method for abnormal operation of a feedback refrigeration device according to claim 6, characterized in that: Outputting the corresponding information in the knowledge base includes: Detecting a setting status, wherein the setting status is whether the user receives abnormality reminders; If the detection result is yes, outputting the abnormal data conversion text and the corresponding information in the knowledge base, wherein the information includes the abnormal data solution; If the detection result is negative, the system returns to perform real-time data collection.
9. A refrigeration device, comprising a memory and a processor, characterized in that: The memory stores a computer program that can be run on the processor, and when the program is executed on the processor, the steps in the method for feedback of abnormal operation of a refrigeration device as claimed in any one of claims 1 to 8 are implemented.
10. A storage medium storing a computer program, characterized in that: When the computer program is executed by the processor, the steps in the method for feedback of abnormal operation of a refrigeration device as claimed in any one of claims 1 to 8 are implemented.
