Building equipment control system and method based on artificial intelligence, equipment and medium

Through the construction equipment control system based on artificial intelligence, the energy consumption problem in the operation and maintenance stage of construction equipment is solved. By responding to user queries in a modular manner, we generate consulting replies, determine maintenance engineers or control instructions, optimize equipment operation, and realize energy conservation and Efficient use.

CN119048046APending Publication Date: 2024-11-29CHINA MERCHANTS SHEKOU DIGITAL CITY TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410892713.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-04
Publication Date
2024-11-29

AI Technical Summary

Technical Problem

Energy consumption of construction equipment during operation and maintenance is difficult to effectively control, resulting in energy waste.

Method used

Adopt an artificial intelligence-based building equipment control system, including a question-and-answer preprocessing module, a question-and-answer module, a question-and-answer assistant module, a fault order dispatch module and an energy-saving control module. By preprocessing and classifying user query text, the corresponding module is called to generate consultation reply , determine the maintenance engineer or generate control instructions to optimize the equipment operation mode.

Benefits of technology

It realizes precise control of construction equipment, reduces energy waste, improves operating efficiency, provides a convenient and efficient user experience, and reduces energy waste caused by failures.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119048046A_ABST
    Figure CN119048046A_ABST
Patent Text Reader

Abstract

The invention discloses a building equipment control system, method, equipment and medium based on artificial intelligence, and the system comprises a question-answer preprocessing module, a question classification module, a question-answer assistant module, a fault order sending module and an energy-saving control module. The question and answer preprocessing module is used for preprocessing the obtained user query text; the question classification module is used for inputting the preprocessed user query text into a pre-trained question classification model to obtain a question classification to which the user query text output by the question classification model belongs; and the question classification module is also used for sending the preprocessed user query text to different modules for processing according to the question classification of the user query text. According to the building equipment control system based on artificial intelligence, different modules are controlled to respond through the classification of the problem to which the user queries the text belongs, the operation efficiency of the building equipment is improved, and energy waste is reduced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of building technology, and in particular to an artificial intelligence-based building equipment control system, method, equipment and medium. Background Art

[0002] With the continuous acceleration of urbanization, the proportion of building energy consumption in global energy consumption is increasing. At present, there are two main energy-saving methods in the construction industry: one is to adopt various energy-saving technologies in the planning and design stage of the building, and the other is to adopt high-efficiency and energy-saving facilities and equipment in the selection of building equipment. However, these measures are mainly concentrated in the planning, design and construction stages of the building. As the building equipment is put into use, it is impossible to control the energy consumption in its operation and maintenance stages.

[0003] Therefore, how to reduce energy consumption during the operation and maintenance stages of building equipment is an urgent problem to be solved. Summary of the invention

[0004] Based on this, the embodiments of the present invention provide a construction equipment control system, method, equipment and medium based on artificial intelligence to solve the problem of energy waste in the operation and maintenance stages of existing construction equipment.

[0005] In a first aspect, a building equipment control system based on artificial intelligence is provided, the building equipment control system comprising a question and answer preprocessing module, a question classification module, a question and answer assistant module, a fault dispatching module and an energy-saving control module;

[0006] The question-answer preprocessing module is used to preprocess the acquired user query text and send the preprocessed user query text to the question classification module;

[0007] The question classification module is used to input the preprocessed user query text into a pre-trained question classification model to obtain the question classification to which the user query text belongs output by the question classification model;

[0008] When the question to which the user query text belongs is classified as a facility and equipment consultation category, the question classification module is used to send the pre-processed user query text to the question-answering assistant module, so that the question-answering assistant module queries the facility and equipment knowledge base according to the pre-processed user query text to generate a consultation reply and a technical guidance plan for construction equipment;

[0009] When the problem classification to which the user query text belongs is a hardware fault insurance policy category, the problem classification module is used to send the pre-processed user query text to the fault dispatching module, so that the fault dispatching module queries the facility equipment knowledge base according to the pre-processed user query text to determine the target maintenance engineer;

[0010] When the question classification to which the user query text belongs is classified as the equipment energy-saving control category, the question classification module is used to send the preprocessed user query text to the energy-saving control module, so that the energy-saving control module queries the facility equipment knowledge base according to the preprocessed user query text and generates control instructions for the building equipment.

[0011] Optionally, the question-answering assistant module queries the facility equipment knowledge base according to the preprocessed user query text to generate a consultation reply and a technical guidance plan about the construction equipment, including:

[0012] The question-and-answer assistant module is used to query the facility equipment knowledge base based on the preprocessed user query text, determine the target knowledge items corresponding to the user query text, and generate consultation replies and technical guidance plans about the construction equipment based on the target knowledge items.

[0013] Optionally, the fault dispatching module queries a facility equipment knowledge base according to the pre-processed user query text to determine a target maintenance engineer, including:

[0014] The fault dispatching module is used to query the facility equipment knowledge base according to the preprocessed user query text to determine candidate maintenance engineers, wherein the candidate maintenance engineers are determined based on the preprocessed user query text and the professional fields of maintenance engineers stored in the facility equipment knowledge base, and the number of the candidate maintenance engineers is N, where N≥1, and N is a positive integer;

[0015] The fault dispatching module is also used to determine a target maintenance engineer according to the comprehensive scores of the N candidate maintenance engineers.

[0016] Optionally, the fault dispatching module is used to determine the target maintenance engineer according to the comprehensive scores of the N candidate maintenance engineers, including:

[0017] The fault dispatch module is also used to obtain the professional matching degree, position matching degree, work efficiency matching degree, work reputation matching degree and workload availability of N candidate maintenance engineers, and determine the corresponding comprehensive score of each candidate maintenance engineer based on the professional matching degree, the position matching degree, the work efficiency matching degree, the work reputation matching degree and the workload availability.

[0018] Optionally, the professional matching degree is obtained based on the professional field and skill list of the maintenance engineer;

[0019] The job matching degree is obtained based on the job grade, training record, and awards and commendations of the maintenance engineer;

[0020] The work efficiency matching degree is obtained based on the work order category, processing quantity, and processing time of the historical work orders of the maintenance engineer;

[0021] The reputation matching degree is obtained based on the maintenance engineer's historical problem evaluation, user ratings, complaint records, and praise records;

[0022] The workload availability is obtained based on the maintenance engineer's working hours, whether he is on vacation, or whether he is away from work.

[0023] Optionally, the energy-saving control module queries a facility equipment knowledge base according to the preprocessed user query text to generate a control instruction for building equipment, including:

[0024] The energy-saving control module is used to query the facility equipment knowledge base according to the preprocessed user query text, determine the energy-saving strategy information corresponding to the user query text, and generate control instructions for the building equipment based on the energy-saving strategy information.

[0025] Optionally, the generating the control instruction of the building equipment based on the energy-saving strategy information includes:

[0026] The energy-saving control module is also used to obtain Internet of Things device data, and generate control instructions for the building equipment based on the energy-saving strategy information and the Internet of Things device data, wherein the Internet of Things devices include smart meters and sensors.

[0027] In a second aspect, a construction equipment control method based on artificial intelligence is provided, comprising:

[0028] Get user query text;

[0029] Preprocessing the user query text to obtain a preprocessed user query text;

[0030] Inputting the preprocessed user query text into a pre-trained question classification model to obtain the question classification to which the user query text belongs output by the question classification model;

[0031] When the question to which the user query text belongs is classified as a facility and equipment consultation category, querying the facility and equipment knowledge base according to the preprocessed user query text to generate a consultation reply and a technical guidance plan for construction equipment;

[0032] When the problem to which the user query text belongs is classified as a hardware failure insurance policy, querying the facility equipment knowledge base according to the preprocessed user query text to determine a target maintenance engineer;

[0033] When the problem to which the user query text belongs is classified as equipment energy-saving control, the facility equipment knowledge base is queried according to the preprocessed user query text to generate control instructions for building equipment.

[0034] In a third aspect, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned artificial intelligence-based building equipment control method when executing the computer program.

[0035] In a fourth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned artificial intelligence-based building equipment control method is implemented.

[0036] In the scheme implemented by the above-mentioned artificial intelligence-based building equipment control system, method, equipment and medium, the user query text is preprocessed by the question and answer preprocessing module, and the preprocessed user query text is sent to the question classification module so that the question classification module uses the pre-trained question classification model to classify the preprocessed user query text, and then different modules are called to respond according to the problem classification to which the user query text belongs. When the problem classification to which the user query text belongs is a facility equipment consultation category, the facility equipment knowledge base is queried through the question and answer assistant module to generate consultation replies and technical guidance plans about building equipment, providing users with accurate answers and suggestions, avoiding energy waste during the operation of building equipment; when the problem classification to which the user query text belongs is a hardware fault policy category, the facility equipment knowledge base is queried through the fault dispatching module to determine the appropriate maintenance engineer to solve the problem, thereby reducing energy waste caused by equipment failure; when the problem classification to which the user query text belongs is an equipment energy-saving control category, the facility equipment knowledge base is queried through the energy-saving control module to generate control instructions for the building equipment, so as to optimize the operation mode of the building equipment, reduce energy consumption, and achieve energy-saving goals. The above-mentioned AI-based building equipment control system controls different modules to respond by classifying the questions in the user's query text, thereby realizing the control of building equipment according to the user's intention, improving the operating efficiency of building equipment, reducing energy waste, and bringing users a more convenient and efficient user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0038] Figure 1 is a schematic diagram of a building equipment control system based on artificial intelligence in one embodiment of the present invention;

[0039] Figure 2 is a flow chart of a construction equipment control method based on artificial intelligence in one embodiment of the present invention;

[0040] Figure 3 is a schematic diagram of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0041] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0042] An embodiment of the present invention provides an artificial intelligence-based building equipment control system, in which the building equipment in the artificial intelligence-based building equipment control system refers to important components of a building, and may include facilities and equipment such as water supply, drainage, heating, ventilation, air conditioning, electricity, elevators, communications, and building intelligent equipment. The building equipment control system may exist in a variety of terminal devices, including but not limited to personal computers, laptops, smart phones, and tablet computers.

[0043] To facilitate understanding of the embodiments of the present invention, the problem classification model, facility equipment knowledge base and Embedding model involved in an artificial intelligence-based building equipment control system provided in the embodiments of the present invention are first discussed as follows:

[0044] In one embodiment, the training method of the question classification model involved in the embodiment of the present invention is as follows:

[0045] S1. Obtain common problems in construction equipment and mark them to obtain training data sets and verification data sets.

[0046] In this embodiment, common problems in the operation and maintenance of building equipment include air conditioner failure, lights not working, and how to maintain computers. Next, the common problems obtained need to be labeled by field, and the problem categories to which the common problems belong may include facility equipment consultation, hardware fault report, and equipment energy-saving control. Specifically, air conditioner failure and lights not working will be labeled as hardware fault report, and how to maintain computers will be labeled as facility equipment consultation. Next, the labeled data set is divided into a training data set and a validation data set. The training data set is used to train the problem classification model to be trained, and the validation data set is used to evaluate the performance of the problem classification model to be trained.

[0047] S2. Input the training data set into the problem classification model to be trained, and adjust the hyperparameters of the problem classification model to be trained according to the verification data set to obtain a trained problem classification model.

[0048] In this embodiment, the question classification model to be trained is a model obtained by adding one or more fully connected layers based on the pre-trained model, for example, a model obtained by adding one or more fully connected layers based on the BERT pre-trained model (full name, Bidirectional Encoder Representation from Transformer). Specifically, a classification layer can be added above the output layer of the BERT encoder to classify questions. Among them, the classification layer is used to map the vector corresponding to the user query text to the category space, and use the softmax activation function to convert each category in the category space into a probability distribution, and the output layer is used to output the prediction result using the cross entropy loss function.

[0049] As an implementation mode, the present application inputs the training data set into the problem classification model to be trained. Specifically, the batch gradient descent algorithm can be used to train the problem classification model to be trained to optimize the parameters of the problem classification model to be trained. Next, the trained problem classification model is tested using the validation data set to observe the accuracy, recall rate and other indicators of the problem classification model to be trained for new problem classification. If the performance of the problem classification model to be trained is not good, the hyperparameters of the problem classification model to be trained, such as the learning rate, batch size, etc., are adjusted according to the validation results to optimize the performance of the problem classification model to be trained, so as to obtain a trained problem classification model. Among them, the learning rate refers to the step size of the model parameter update, and the appropriate learning rate can be selected according to the characteristics of the task and the data set, for example, 2e-5, the batch size refers to the number of samples used in each iteration, which can be selected according to the hardware conditions and the size of the training data set, for example, set to 32, and the number of iterations refers to the number of iterations in the training process of the training data set, that is, the number of times it is traversed, which can be set as needed, for example, set to 8.

[0050] In one embodiment, the facility equipment knowledge base involved in the embodiment of the present invention is a database that provides professional knowledge related to the operation, maintenance, and energy-saving control of building equipment and detailed information of maintenance engineers in various professional fields. The specific facility equipment knowledge base may include: equipment information, energy-saving strategies, operation guides, operation and maintenance procedures, troubleshooting, maintenance cases, safety specifications, safety standards, manufacturer information, and maintenance engineers' historical work order performance (for example, the number and speed of handling historical problems), professional fields, skill lists, training records, historical problem evaluations, user scores, complaint records, praise records, working hours, vacations, and off-duty information.

[0051] Among them, equipment information includes the model, specifications, and technical parameters of building equipment; energy-saving strategies include specific energy-saving control strategies for building equipment; operating guidelines include operating methods for building equipment, for example, methods for starting and shutting down building equipment; operation and maintenance procedures include components, cycles, methods, and precautions for regular maintenance of building equipment; troubleshooting includes the causes and solutions for common failures of building equipment; maintenance cases include the number and matters of past maintenance of building equipment; safety specifications include safe operation requirements and precautions for building equipment; safety standards include laws, regulations, and industry standards related to construction equipment; and manufacturer information includes after-sales information of building equipment. By setting up the above-mentioned facility and equipment knowledge base, accurate information support is provided for the operation, maintenance, and control of building equipment. It should be noted that the above is only an example, and the specific present invention is not limited thereto.

[0052] In one embodiment, the Embedding model involved in the embodiment of the present invention can map high-dimensional data (such as text) to a low-dimensional space, and represent the input text as a point in a continuous numerical space, and finally obtain an Embedding vector. Among them, the Embedding vector can accurately represent the intrinsic semantics of the natural language text, and the Embedding vectors with similar geometric distances have similar meanings for the corresponding natural language texts. Among them, the Embedding model can be established by Word2Vec, GloVe or FastText algorithm, and is used to calculate the geometric distance between the Embedding vectors corresponding to two text phrases or sentences. Specifically, the Euclidean distance can be used to represent the distance between the two vectors to determine the closest content in the user query text and the facility equipment knowledge base. Exemplarily, in a two-dimensional coordinate system, the Euclidean distance is to calculate the distance of the straight line connecting p to q; in a three-dimensional coordinate system, each vector contains three coordinate points x, y, and z, and the Euclidean distance is the distance between any two points.

[0053] An artificial intelligence-based building equipment control system provided by the present invention will be described in detail below.

[0054] In a first aspect, a building equipment control system based on artificial intelligence provided by the present invention, as Figure 1 described, the building equipment control system includes a question and answer preprocessing module 101, a question classification module 102, a question and answer assistant module 103, a fault dispatch module 104, and an energy-saving control module 105;

[0055] The question and answer preprocessing module is used to obtain the user query text in real time and perform natural language preprocessing. The user query text refers to the user's question text. For example, "The air conditioner is broken." Among them, performing natural language preprocessing on the user query text includes steps such as data cleaning, text tokenization, extracting key information, and spoken language conversion. Specifically, data cleaning includes removing irrelevant content such as special characters, spaces, and punctuation marks in the user query text. For example, removing stop words that contribute little to semantic processing, such as "de", "shi", "zai", etc. Text tokenization includes splitting the user query text into individual words or terms. For example, through natural language processing (NLP) technology, the input user query text, such as "Turn on the air conditioner", is tokenized into "Turn on / air conditioner". Spoken language conversion is to convert the user query text into the corresponding professional terms according to the pre-established spoken language vocabulary mapping table. For example, converting "The air conditioner is broken" to "Air conditioner failure", and "The light is not on" to "Lamp lighting abnormality", etc. Through a series of preprocessing steps, the normalization degree and information quality of the user query text are improved, ensuring the accuracy and effectiveness of subsequent processing.

[0056] The question classification module is used to input the preprocessed user query text into a pre-trained question classification model. The question classification model is pre-trained and can identify the problem classification to which the user query text belongs. The specific training process is as described in steps S1 - S2. To avoid repetition, it will not be elaborated here. Specifically, the question classification model will extract the key features and semantic information in the user query text. For example, in the user query text "The light in the meeting room is not on and needs to be repaired", the question classification model will identify keywords such as "meeting room", "light", "not on", "repair", etc., and make a judgment in combination with the semantic relationship of these keywords to classify this user query text into a preset domain. Among them, the problem classification to which the user query text belongs includes facility equipment consultation category, hardware failure report category, and equipment energy-saving control category. For example, the user query text "The light in the meeting room is not on. Please repair it as soon as possible" will be classified into the hardware failure report category.

[0057] The question classification module is also used to send the pre-processed user query text to different processing modules according to the determined question classification to which the user query text belongs. Specifically, when the question classification to which the user query text belongs is classified as facility and equipment consultation, the question classification module is used to send the pre-processed user query text to the question-answering assistant module; when the question classification to which the user query text belongs is classified as hardware fault insurance policy, the question classification module is used to send the pre-processed user query text to the fault dispatching module; when the question classification to which the user query text belongs is classified as equipment energy-saving control, the question classification module is used to send the pre-processed user query text to the energy-saving control module.

[0058] The question-answering assistant module is used to receive the pre-processed user query text sent by the question classification module, and according to the pre-processed user query text, the vector retrieval algorithm in the Embedding model is used to find the target knowledge item that best matches the user query text in the facility equipment knowledge base, and then generate the building equipment processing plan related to the user query text according to the determined target knowledge item. The application of the question-answering assistant module not only improves the efficiency of building equipment maintenance and troubleshooting, but also reduces the degree of dependence on professionals, so that ordinary users can also achieve rapid response and accurate processing of user query texts through simple query operations, providing users with an efficient and convenient way to solve problems, and further avoiding waste of resources.

[0059] In this step, when the user query text is an operation and maintenance question consultation, the question-answering assistant module will perform semantic similarity search and matching in the facility equipment knowledge base based on the description of the building equipment operation phenomenon in the user query text through the vector retrieval algorithm, thereby retrieving the fault category, possible cause and treatment plan that are most relevant to the user query text phenomenon description, and finally generate a building equipment treatment plan (for example, a fault analysis and treatment report) to guide the user's fault inspection process. When the user query text is a maintenance and energy-saving question consultation, the question-answering assistant module performs semantic similarity search and matching in the facility equipment knowledge base through the vector retrieval algorithm, thereby retrieving the maintenance category, maintenance items, maintenance manufacturers, maintenance strategies, and energy-saving strategies related to the user's query text, and finally generates a consultation reply and technical guidance plan for the maintenance and energy-saving of the equipment throughout its life cycle for the user. For example, when the user asks "how to adjust the brightness of the office lights to reduce energy consumption", the question-answering assistant module will search for relevant lighting control strategies in the facility equipment knowledge base and generate a consultation reply and technical guidance plan on how to adjust the brightness of the office lights to reduce energy consumption.

[0060] The fault dispatching module is used to receive the pre-processed user query text sent by the problem classification module, and search in the facility equipment knowledge base according to the pre-processed user query text through the vector retrieval algorithm in the Embedding model, and select the maintenance engineer whose user query text best matches the maintenance engineer's professional field as a candidate maintenance engineer. For example, for the pre-processed user query text "air conditioner does not work", the fault dispatching module will search all maintenance engineers with the professional field of air conditioning maintenance in the facility equipment knowledge base as candidate maintenance engineers. Among them, the number of candidate maintenance engineers is N, N≥1, N is a positive integer, specifically, N can be pre-set as needed, and the specific present invention does not limit it. Then, the comprehensive score of each candidate maintenance engineer is queried from the facility equipment knowledge base, and the candidate maintenance engineer with the highest comprehensive score is used as the target maintenance engineer. Then, the order is dispatched to the target maintenance engineer for fault handling, thereby accelerating the fault inspection and repair process and avoiding unnecessary energy consumption.

[0061] In this step, the comprehensive score of each candidate maintenance engineer can be calculated as follows:

[0062] The fault dispatching module is also used to search the professional matching, position matching, work efficiency matching, work reputation matching, and workload availability of the determined N candidate maintenance engineers from the facility equipment knowledge base, and then use the weighted average method to calculate the obtained professional matching, position matching, work efficiency matching, work reputation matching, and workload availability to obtain a comprehensive score for each candidate maintenance engineer. In this way, it is ensured that the maintenance engineer finally dispatched is the most suitable candidate, which improves user satisfaction.

[0063] It should be noted that in addition to using the weighted average method to calculate the comprehensive score of each candidate maintenance engineer, the present invention can also obtain the comprehensive score of each candidate maintenance engineer based on the rule-based scoring method. For example, clear scoring rules are set, such as professional matching accounts for 40%, position matching accounts for 20%, work efficiency matching accounts for 20%, work reputation matching accounts for 10%, and workload availability accounts for 10%. According to the preset scoring rules, each matching degree of the candidate maintenance engineer is scored, and the weighted sum is used to obtain the comprehensive score, which is not limited to the specific present invention.

[0064] Optionally, professional matching can be evaluated based on the professional field and skill list of the maintenance engineer; job matching can be evaluated based on the maintenance engineer's job grade, training record, and rewards and commendations; work efficiency matching can be evaluated based on the maintenance engineer's historical work order data, where the historical work order data includes work order category, processing quantity and processing time; work reputation matching can be evaluated based on the maintenance engineer's historical problem evaluation, user scores, complaint records, and praise records; workload availability can be evaluated based on the maintenance engineer's working hours, vacation status, and off-duty status.

[0065] The energy-saving control module is used to receive the pre-processed user query text sent by the question classification module, and according to the pre-processed user query question, search the energy-saving strategy that best matches the user query text in the facility equipment knowledge base through the vector retrieval algorithm in the Embedding model, and generate the control instructions of the building equipment based on the energy-saving strategy information, so as to realize the precise control of the building equipment to achieve the purpose of energy saving. For example, when the pre-processed user query text is "Please increase the air-conditioning temperature of the conference room to 26 degrees to save energy", the energy-saving control module will query the facility equipment knowledge base according to the pre-processed user query text to determine the energy-saving strategy related to the user query text, and based on the determined energy-saving strategy, the energy-saving control module will generate specific building equipment control instructions. These control instructions include the start and stop control instructions of the building equipment related to the user query text, the operating parameters and the execution steps and other energy-saving strategies to control the building equipment to make corresponding adjustments. For example, for a request to adjust the air-conditioning temperature, the control instructions may include "Set the air-conditioning temperature of the conference room to 26 degrees, adjust the wind speed to medium, and enable the energy-saving mode", etc.

[0066] Optionally, the energy-saving control module is also used to obtain data from IoT devices, for example, to obtain IoT device data such as temperature, humidity, carbon dioxide, electricity consumption, passenger flow, and illuminance of the building space in real time through the IoT protocol. Among them, IoT devices include smart meters, temperature sensors, humidity sensors, carbon dioxide sensors, illuminance sensors, and passenger flow sensors. Specifically, IoT devices can be pre-installed in key locations of the building, for example, temperature sensors are installed near air conditioners, and the specific invention is not limited. Then, based on the IoT device data and energy-saving strategies obtained in real time, the energy-saving control module can make more accurate and timely decisions and generate building equipment control instructions that are more in line with actual needs. This can not only improve energy utilization efficiency and reduce energy consumption, but also provide users with a more comfortable and convenient user experience.

[0067] To sum up, in the scheme implemented by the above-mentioned artificial intelligence-based building equipment control system, method, equipment and medium, the user query text is preprocessed by the question and answer preprocessing module, and the preprocessed user query text is sent to the question classification module so that the question classification module uses the pre-trained question classification model to classify the preprocessed user query text, and then different modules are called to respond according to the problem classification of the user query text. When the problem classification of the user query text is a facility equipment consultation category, the facility equipment knowledge base is queried through the question and answer assistant module to generate consultation replies and technical guidance plans about building equipment, providing users with accurate answers and suggestions, avoiding energy waste during the operation of building equipment; when the problem classification of the user query text is a hardware fault policy category, the facility equipment knowledge base is queried through the fault dispatching module to determine the appropriate maintenance engineer to solve the problem, thereby reducing energy waste caused by equipment failure; when the problem classification of the user query text is an equipment energy-saving control category, the facility equipment knowledge base is queried through the energy-saving control module to generate control instructions for the building equipment, so as to optimize the operation mode of the building equipment, reduce energy consumption, and achieve energy-saving goals. The above-mentioned AI-based building equipment control system controls different modules to respond by classifying the questions in the user's query text, thereby realizing the control of building equipment according to the user's intention, improving the operating efficiency of building equipment, reducing energy waste, and bringing users a more convenient and efficient user experience.

[0068] For example, for user query texts of facility and equipment consultation, the question classification module will forward the user query text to the question and answer assistant module, which will generate detailed replies or operation suggestions based on the information in the facility and equipment knowledge base and provide them to the user. For example, for such consultation questions as "How to adjust the air conditioning temperature in the office area?", the question and answer assistant module will search the knowledge base and provide air conditioning operation guides or suggestions. For user query texts of hardware fault report, the question classification module will send the user query text to the fault dispatching module, which will further analyze the fault description and query the facility and equipment knowledge base and the maintenance engineer database to determine the most suitable maintenance engineer to handle the fault. For example, for "The lights in the conference room are not on, please repair them as soon as possible", the fault dispatching module will find a maintenance engineer with relevant maintenance skills and a low current workload, and automatically generate a maintenance work order and dispatch it to the maintenance engineer for processing. For user query texts of equipment energy-saving control, the question classification module will forward the user query text to the energy-saving control module, which will combine the IoT data and the energy-saving strategies in the facility and equipment knowledge base to generate specific building equipment control instructions. For example, for a request to "adjust the air conditioning temperature in the office area to save energy", the energy-saving control module will adjust the air conditioning settings to achieve the energy-saving goal based on real-time temperature, humidity, personnel flow and other data. It should be noted that the above is only an example and does not constitute a limitation of the present invention.

[0069] Second, as Figure 2 As shown, the above-mentioned artificial intelligence-based building equipment control system corresponds to an artificial intelligence-based building equipment control method provided by an embodiment of the present invention. The artificial intelligence-based building equipment control method is applied to the above-mentioned artificial intelligence-based building equipment control system, wherein the building equipment control system includes a question and answer preprocessing module 101, a question classification module 102, a question and answer assistant module 103, a fault dispatching module 104 and an energy-saving control module 105, and the method includes the following steps:

[0070] S10, obtaining user query text;

[0071] S20, preprocessing the user query text to obtain a preprocessed user query text;

[0072] S30, inputting the preprocessed user query text into a pre-trained question classification model to obtain the question classification to which the user query text belongs output by the question classification model;

[0073] S40, when the question to which the user query text belongs is classified as a facility and equipment consultation category, querying the facility and equipment knowledge base according to the preprocessed user query text to generate a consultation reply and a technical guidance plan for construction equipment;

[0074] S50, when the problem to which the user query text belongs is classified as a hardware failure insurance policy category, query the facility equipment knowledge base according to the pre-processed user query text to determine a target maintenance engineer;

[0075] S60: When the question to which the user query text belongs is classified as equipment energy-saving control, query the facility equipment knowledge base according to the preprocessed user query text to generate control instructions for building equipment.

[0076] In summary, in the scheme implemented by the above-mentioned artificial intelligence-based building equipment control system, method, equipment and medium, a user query text is obtained; the user query text is preprocessed to obtain a preprocessed user query text; the preprocessed user query text is input into a pre-trained problem classification model to obtain the problem classification of the user query text output by the problem classification model; when the problem classification of the user query text is a facility equipment consultation category, the facility equipment knowledge base is queried according to the preprocessed user query text to generate a consultation reply and technical guidance plan for the building equipment; when the problem classification of the user query text is a hardware fault insurance policy category, the facility equipment knowledge base is queried according to the preprocessed user query text to determine the target maintenance engineer; when the problem classification of the user query text is an equipment energy-saving control category, the facility equipment knowledge base is queried according to the preprocessed user query text to generate a control instruction for the building equipment. Through the above method, the control of the building equipment according to the user's intention is realized, the operating efficiency of the building equipment is improved, energy waste is reduced, and a more convenient and efficient use experience is brought to the user.

[0077] It should be noted that for the details of the execution of the above-mentioned artificial intelligence-based construction equipment control method, please refer to the description of the aforementioned system embodiment. In order to avoid repetition, the description will not be repeated here.

[0078] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0079] In a third aspect, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 3As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data in the facility equipment knowledge base. The network interface of the computer device is used to communicate with external devices through a network connection. When the computer program is executed by the processor, a building equipment control method based on artificial intelligence is implemented.

[0080] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program:

[0081] Get user query text;

[0082] Preprocessing the user query text to obtain a preprocessed user query text;

[0083] Inputting the preprocessed user query text into a pre-trained question classification model to obtain the question classification to which the user query text belongs output by the question classification model;

[0084] When the question to which the user query text belongs is classified as a facility and equipment consultation category, querying the facility and equipment knowledge base according to the preprocessed user query text to generate a consultation reply and a technical guidance plan for construction equipment;

[0085] When the problem to which the user query text belongs is classified as a hardware failure insurance policy, querying the facility equipment knowledge base according to the preprocessed user query text to determine a target maintenance engineer;

[0086] When the problem to which the user query text belongs is classified as equipment energy-saving control, the facility equipment knowledge base is queried according to the preprocessed user query text to generate control instructions for building equipment.

[0087] In a fourth aspect, a computer-readable storage medium is provided, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the following steps are implemented:

[0088] Get user query text;

[0089] Preprocessing the user query text to obtain a preprocessed user query text;

[0090] Inputting the preprocessed user query text into a pre-trained question classification model to obtain the question classification to which the user query text belongs output by the question classification model;

[0091] When the question to which the user query text belongs is classified as a facility and equipment consultation category, querying the facility and equipment knowledge base according to the preprocessed user query text to generate a consultation reply and a technical guidance plan for construction equipment;

[0092] When the problem to which the user query text belongs is classified as a hardware failure insurance policy, querying the facility equipment knowledge base according to the preprocessed user query text to determine a target maintenance engineer;

[0093] When the problem to which the user query text belongs is classified as equipment energy-saving control, the facility equipment knowledge base is queried according to the preprocessed user query text to generate control instructions for building equipment.

[0094] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0095] Technicians in the corresponding problem category can clearly understand that for the convenience and conciseness of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0096] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A construction equipment control system based on artificial intelligence, characterized in that: The building equipment control system includes a question-answering preprocessing module, a question classification module, a question-answering assistant module, a fault dispatching module, and an energy-saving control module; The question-answer preprocessing module is used to preprocess the acquired user query text and send the preprocessed user query text to the question classification module; The question classification module is used to input the preprocessed user query text into a pre-trained question classification model to obtain the question classification to which the user query text belongs output by the question classification model; When the question to which the user query text belongs is classified as a facility and equipment consultation category, the question classification module is used to send the pre-processed user query text to the question-answering assistant module, so that the question-answering assistant module queries the facility and equipment knowledge base according to the pre-processed user query text to generate a consultation reply and a technical guidance plan for construction equipment; When the problem classification to which the user query text belongs is a hardware fault insurance policy category, the problem classification module is used to send the pre-processed user query text to the fault dispatching module, so that the fault dispatching module queries the facility equipment knowledge base according to the pre-processed user query text to determine the target maintenance engineer; When the question classification to which the user query text belongs is classified as the equipment energy-saving control category, the question classification module is used to send the preprocessed user query text to the energy-saving control module, so that the energy-saving control module queries the facility equipment knowledge base according to the preprocessed user query text and generates control instructions for the building equipment.

2. The construction equipment control system based on artificial intelligence according to claim 1 is characterized in that: The question-answering assistant module queries the facility equipment knowledge base according to the preprocessed user query text, and generates a consultation reply and a technical guidance plan for construction equipment, including: The question-and-answer assistant module is used to query the facility equipment knowledge base based on the preprocessed user query text, determine the target knowledge items corresponding to the user query text, and generate consultation replies and technical guidance plans about the construction equipment based on the target knowledge items.

3. The construction equipment control system based on artificial intelligence according to claim 1 is characterized in that: The fault dispatching module queries the facility equipment knowledge base according to the pre-processed user query text to determine the target maintenance engineer, including: The fault dispatching module is used to query the facility equipment knowledge base according to the preprocessed user query text to determine candidate maintenance engineers, wherein the candidate maintenance engineers are determined based on the preprocessed user query text and the professional fields of maintenance engineers stored in the facility equipment knowledge base, and the number of the candidate maintenance engineers is N, where N≥1, and N is a positive integer; The fault dispatching module is also used to determine a target maintenance engineer according to the comprehensive scores of the N candidate maintenance engineers.

4. The artificial intelligence-based construction equipment control system according to claim 3 is characterized in that: The fault dispatching module is used to determine the target maintenance engineer according to the comprehensive scores of N candidate maintenance engineers, including: The fault dispatch module is also used to obtain the professional matching degree, position matching degree, work efficiency matching degree, work reputation matching degree and workload availability of N candidate maintenance engineers, and determine the corresponding comprehensive score of each candidate maintenance engineer based on the professional matching degree, the position matching degree, the work efficiency matching degree, the work reputation matching degree and the workload availability.

5. The artificial intelligence-based construction equipment control system according to claim 4 is characterized in that: The professional matching degree is obtained based on the professional field and skill list of the maintenance engineer; The job matching degree is obtained based on the job grade, training record, and awards and commendations of the maintenance engineer; The work efficiency matching degree is obtained based on the work order category, processing quantity, and processing time of the historical work orders of the maintenance engineer; The reputation matching degree is obtained based on the maintenance engineer's historical problem evaluation, user ratings, complaint records, and praise records; The workload availability is obtained based on the maintenance engineer's working hours, whether he is on vacation, or whether he is away from work.

6. The construction equipment control system based on artificial intelligence according to claim 1 is characterized in that: The energy-saving control module queries the facility equipment knowledge base according to the preprocessed user query text to generate control instructions for building equipment, including: The energy-saving control module is used to query the facility equipment knowledge base according to the preprocessed user query text, determine the energy-saving strategy information corresponding to the user query text, and generate control instructions for the building equipment based on the energy-saving strategy information.

7. The artificial intelligence-based construction equipment control system according to claim 6, characterized in that: The step of generating a control instruction for the building equipment based on the energy-saving strategy information includes: The energy-saving control module is also used to obtain Internet of Things device data, and generate control instructions for the building equipment based on the energy-saving strategy information and the Internet of Things device data, wherein the Internet of Things devices include smart meters and sensors.

8. A construction equipment control method based on artificial intelligence, characterized in that: include: Get user query text; Preprocessing the user query text to obtain a preprocessed user query text; Inputting the preprocessed user query text into a pre-trained question classification model to obtain the question classification to which the user query text belongs output by the question classification model; When the question to which the user query text belongs is classified as a facility and equipment consultation category, querying the facility and equipment knowledge base according to the preprocessed user query text to generate a consultation reply and a technical guidance plan for construction equipment; When the problem to which the user query text belongs is classified as a hardware failure insurance policy, querying the facility equipment knowledge base according to the preprocessed user query text to determine a target maintenance engineer; When the problem to which the user query text belongs is classified as equipment energy-saving control, the facility equipment knowledge base is queried according to the preprocessed user query text to generate control instructions for building equipment.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the artificial intelligence-based construction equipment control method according to claim 8 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the construction equipment control method based on artificial intelligence according to claim 8 is implemented.