Building equipment data table processing method and device, equipment and medium

Abstract

The embodiment of the invention discloses a processing method and device for a building equipment data table, equipment and a medium. The method comprises the steps that the building equipment data table, a data dictionary and preset cue words are acquired; inputting the building equipment data table and a preset cue word into the question and answer model, and determining an equipment type reasoning result corresponding to the building equipment; and inputting the preset cue word and the data dictionary into the question and answer model, and determining a standard equipment type of the building equipment based on the equipment type reasoning result, the preset cue word and the data dictionary through the question and answer model. According to the technical scheme provided by the invention, the equipment type of the building equipment can be accurately determined, and the processing efficiency and accuracy of the building equipment data table are improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and in particular to a method, device, equipment and medium for processing a building equipment data table. Background Art

[0002] With the rapid development of digital technology, the construction industry is undergoing unprecedented changes. Traditional construction management methods can no longer meet the complex needs of modern construction projects. As an emerging digital solution, digital twin technology provides new possibilities for intelligent management of the entire life cycle of buildings. Digital twin refers to the creation of digital copies of physical entities in virtual space, which can realize the projection of information from the physical world of buildings to the digital world. In the field of construction, the application potential of digital twin technology is huge, but it still faces many challenges. One of the most significant difficulties is that for the implementation of data twin technology, various types of building data need to be integrated in advance.

[0003] Current construction equipment information is usually in the form of spreadsheets, which usually take a long time to generate and maintain. There is no unified recording standard between projects, and the degree of unstructuredness is very high. The use of construction equipment data sheets requires not only personnel to master a large amount of professional knowledge and data dictionary knowledge of equipment and facilities, but also a large amount of manual work to complete tedious sorting and conversion. Therefore, the current method of processing construction equipment data is inaccurate and inefficient. Summary of the invention

[0004] The present invention provides a method, device, equipment and medium for processing a building equipment data table. Through the technical solution of the present application, the equipment type of the building equipment is accurately determined, thereby improving the accuracy and efficiency of the processing of the building equipment data table.

[0005] In a first aspect, an embodiment of the present invention provides a method for processing a building equipment data table, comprising:

[0006] Obtain a building equipment data table, a data dictionary and preset prompt words, wherein the building equipment data table includes equipment parameters corresponding to the building equipment, the preset prompt words are used to prompt the question-answering model to output inference results according to the building equipment data table, and the data dictionary includes standard equipment types and standard parameter formats of the building equipment;

[0007] Input the building equipment data table and the preset prompt words into the question-answering model to determine the equipment type inference result corresponding to the building equipment;

[0008] The preset prompt words and data dictionary are input into the question-answering model, and the standard equipment type of the construction equipment is determined by the question-answering model based on the equipment type inference result, the preset prompt words and the data dictionary.

[0009] In a second aspect, an embodiment of the present invention provides a device for processing a building equipment data table, comprising:

[0010] An acquisition module is used to acquire a building equipment data table, a data dictionary and preset prompt words, wherein the building equipment data table includes equipment parameters corresponding to the building equipment, the preset prompt words are used to prompt the question-answering model to output an inference result according to the building equipment data table, and the data dictionary includes standard equipment types and standard parameter formats of the building equipment;

[0011] A first reasoning module, used to input the building equipment data table and preset prompt words into the question-answering model to determine the equipment type reasoning result corresponding to the building equipment;

[0012] The second reasoning module is used to input the preset prompt words and data dictionary into the question-answering model, and determine the standard equipment type of the construction equipment based on the equipment type reasoning result, preset prompt words and data dictionary through the question-answering model.

[0013] In a third aspect, an embodiment of the present invention provides an electronic device, characterized in that the electronic device includes:

[0014] at least one processor; and,

[0015] a memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for processing a building equipment data table according to any one of the embodiments of the present invention.

[0017] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for processing a building equipment data table described in any one of the embodiments of the present invention when executed.

[0018] The embodiment of the present invention provides a method, device, equipment and medium for processing a building equipment data table, the method comprising: obtaining a building equipment data table, a data dictionary and preset prompt words, wherein the building equipment data table includes equipment parameters corresponding to the building equipment, the preset prompt words are used to prompt a question-answering model to output an inference result according to the building equipment data table, and the data dictionary includes the standard equipment type and standard parameter format of the building equipment; inputting the building equipment data table and the preset prompt words into the question-answering model to determine the equipment type inference result corresponding to the building equipment; inputting the preset prompt words and the data dictionary into the question-answering model, and determining the standard equipment type of the building equipment through the question-answering model based on the equipment type inference result, the preset prompt words and the data dictionary. Specifically, by inputting the building equipment data table and the preset prompt words into the question-answering model, the question-answering model can determine the equipment type inference result inferred by the model itself, and further, by inputting the preset prompt words and the data dictionary into the question-answering model, the question-answering model can output a more accurate equipment type of the building equipment, that is, a standard equipment type. In this way, the equipment type of the building equipment in the building equipment data table can be accurately determined, and the equipment type can be quickly associated with the building equipment, thereby improving the accuracy and efficiency of the building equipment data table processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0020] Figure 1 A flowchart of a method for processing a building equipment data table provided in Embodiment 1 of the present invention;

[0021] Figure 2 A flowchart of a method for processing a building equipment data table provided in Embodiment 2 of the present invention;

[0022] Figure 3 A schematic diagram of the structure of a device for processing a building equipment data table provided in Embodiment 3 of the present invention;

[0023] Figure 4 A schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. DETAILED DESCRIPTION

[0024] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only 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 should fall within the scope of protection of the present invention.

[0025] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0026] It should be noted that the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved in the technical solution of the present disclosure are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0027] Embodiment 1

[0028] Figure 1 A flowchart of a method for processing a building equipment data table provided in Embodiment 1 of the present invention. The method can be applicable to the case where a building equipment data table is processed through a question-and-answer model, and in particular, can be applicable to the case where the content in the building equipment data table is processed into data required for digital twin technology. The method can be executed by a processing device for a building equipment data table, which can be composed of software and / or hardware and configured in a computer or server.

[0029] like Figure 1 As shown, including:

[0030] Step 110: Obtain a building equipment data table, a data dictionary and preset prompt words, wherein the building equipment data table includes equipment parameters corresponding to the building equipment, the preset prompt words are used to prompt the question-answering model to output inference results based on the building equipment data table, and the data dictionary includes standard equipment types and standard parameter formats of the building equipment.

[0031] Among them, the building equipment data table includes equipment parameters corresponding to the building equipment. The equipment parameters may include technical parameters, such as the power and power consumption of the building equipment, etc., and non-technical parameters, which may include the installation location and installation time of the building equipment. The data dictionary is a normative dictionary in the construction field, which includes the normative names of various building equipment, standard equipment types and standard parameter formats of building equipment, wherein the standard equipment type is the normative name of the building equipment type in the data dictionary, which can be the standard name of the construction industry; the standard parameter format is the normative format of each equipment parameter in the building equipment. The question-answering model is a conversational large language model, and various prompt words can be input into the question-answering model to obtain the answer to the reasoning question of the question-answering model. Furthermore, in the present application, the question-answering model is used to output the reasoning results about the building equipment data table based on the building equipment data table and preset prompt words. Furthermore, due to the input word limit of the question-answering model, for a single question, the question-answering model may not be able to directly output the ideal reasoning result. Therefore, in this case, prompt words are continuously added in multiple consecutive question-answering processes to make the reasoning result of the question-answering model more accurate as the prompt words are input, and ultimately achieve the preset purpose, such as determining the equipment type of construction equipment. Exemplarily, the question-answering model can be a large language reasoning model.

[0032] It should be noted that in the embodiments of the present application, different preset prompt words need to be used multiple times. Since the question-answering model itself is a black box model with complex internal computing mechanisms, it is necessary to preset different types of preset prompt words to control the reasoning results of the question-answering model to gradually approach the desired ideal answer. Therefore, the specific content of the prompt words is the key to controlling the reasoning of the question-answering model. Regarding the role of preset prompt words in different question-answering stages, see the following content for details.

[0033] Furthermore, the preset prompt words are also used to prompt the question-answering model to output the inference results and the reasoning reasons and / or reasoning processes corresponding to the reasoning results in a preset format. Specifically, the question-answering model can be required to output the reasoning reasons and / or reasoning processes corresponding to the reasoning results so that the question-answering model can perform self-correction to improve the accuracy of reasoning, and at the same time help staff understand the reasoning process and grasp the reasoning dynamics. Among them, the preset format can be JSON format.

[0034] Specifically, since the construction equipment data sheet is filled in by different staff members, due to individual differences, filling habits and naming habits among the staff members are inconsistent. Therefore, for the processing of the contents of the construction equipment data sheet, the standard equipment type and standard parameter format of the construction equipment can be determined according to the data dictionary, and then through the method of the present application, the standard equipment type of the construction equipment can be accurately determined; the equipment parameters in the construction equipment data sheet can be calibrated to the standardized type for downstream use.

[0035] Step 120: Input the building equipment data table and preset prompt words into the question-answering model to determine the equipment type inference result corresponding to the building equipment.

[0036] Among them, the equipment type reasoning result is the result about the equipment type inferred by the question-answering model based on its internal knowledge and the building equipment data table. It should be noted that due to the limitations of the internal knowledge of the question-answering model, the equipment type reasoning result may be accurate or inaccurate. Therefore, the question-answering model is required to perform self-correction according to the method of this application in order to ultimately achieve the purpose of enabling the question-answering model to infer the ideal answer. The specific method is shown below.

[0037] Optionally, step 120 includes:

[0038] The first prompt word and the building equipment data table are input into the question-answering model, and the data rows of the building equipment data table are identified through the question-answering model, wherein the first prompt word is used to represent the constraint conditions when the question-answering model identifies the table structure of the building equipment data table.

[0039] Among them, different building equipment data tables have different table structures, such as different titles, headers and data row numbers. At the same time, the data about the building equipment is recorded in the data row. Therefore, it is necessary to make the question-answering model identify the data row of the building equipment data table to accurately identify the required building equipment data. Furthermore, due to the differences in the table structures of the various building equipment data tables, when the question-answering model processes a large number of building equipment data tables, there will be omissions of rows, errors in the recognition of field contents in the table, etc. Therefore, it is necessary to use the first prompt word to prompt the question-answering model so that the question-answering model can accurately identify the table structure of the building equipment data table.

[0040] Specifically, the first prompt word includes:

[0041] prompting the question-answering model to avoid missing rows;

[0042] The question-answer model is prompted that the building equipment data table includes at least one table header and / or at least one title.

[0043] Specifically, due to the inherent limitations of the algorithm of the question-answering model, problems such as missing rows and incorrect table header correspondence may occur. Therefore, it is necessary to use the first prompt word to prompt the question-answering model to remind the question-answering model to pay attention to the corresponding possible problems in order to improve the accuracy of reasoning.

[0044] The second prompt word is input into the question-answering model to determine the equipment type inference result of the construction equipment corresponding to the data row, wherein the second prompt word is used to represent the constraint condition when the question-answering model infers the equipment type of the construction equipment.

[0045] Specifically, after the question-answering model determines the table structure of the building equipment data table, it will infer the type of building equipment based on the content of the data row in the table to obtain the equipment type inference result. However, due to the limitation of insufficient internal knowledge and the differences in the content of the data table, the question-answering model may not be able to effectively distinguish which feature information can be used to determine the equipment type, and which feature information is non-critical or irrelevant. Therefore, it is necessary to input a second prompt word to help the question-answering model overcome the above problem.

[0046] Optionally, the second prompt word includes

[0047] Prompting the question-answer model to distinguish the field types of the fields in the data row and determine the type field representing the device type;

[0048] The question-answering model is prompted to perform reasoning based on the type field.

[0049] Among them, different field types represent different field contents. For example, the data table may contain installation time fields, equipment name fields, type fields, and equipment responsible person fields. The type field may include the equipment model field, or some fields for staff to classify types. The type field is a key feature field for reasoning.

[0050] Specifically, through the second prompt word, the question-answering model can accurately distinguish the types of each field, and then use key feature fields such as type fields for focused reasoning to improve the efficiency of the question-answering model in obtaining key information, thereby improving the accuracy of the question-answering model's reasoning.

[0051] Furthermore, the second prompt word may also include prompting that the device type inference result output by the question-answering model should be as specific as possible and should not be overly simplified or one-sided.

[0052] Step 130: input the preset prompt words and data dictionary into the question-answering model, and determine the standard equipment type of the building equipment through the question-answering model based on the equipment type inference result, the preset prompt words and the data dictionary.

[0053] Specifically, since the equipment type inference result is inferred by the question-answering model based on its own knowledge, errors may occur itself, or the inferred type may be correct in the general direction but not detailed enough or does not meet the naming standards of the industry. Therefore, it is necessary to input the preset prompt words and data dictionary into the question-answering model so that the large model can perform re-inference based on the equipment type inference result, preset prompt words and data dictionary to improve the accuracy of the final inference answer, that is, to accurately determine the standard equipment type of construction equipment.

[0054] Exemplarily, for device A, the device type inference result is cooling equipment, and then the data dictionary containing the data associated with device A can be input into the question-answering model. For example, the information about A in the data dictionary is that device A is cooled by liquid during use. At the same time, the standard equipment types of building equipment recorded in the data dictionary include water-cooled equipment or air-cooled equipment. Therefore, the question-answering model can combine the above content to accurately determine that the standard equipment type of device A is water-cooled equipment.

[0055] The embodiment of the present invention provides a method for processing a building equipment data table, including: obtaining a building equipment data table, a data dictionary and preset prompt words, wherein the building equipment data table includes equipment parameters corresponding to the building equipment, the preset prompt words are used to prompt a question-answering model to output an inference result according to the building equipment data table, and the data dictionary includes the standard equipment type and standard parameter format of the building equipment; inputting the building equipment data table and the preset prompt words into the question-answering model to determine the equipment type inference result corresponding to the building equipment; inputting the preset prompt words and the data dictionary into the question-answering model, and determining the standard equipment type of the building equipment through the question-answering model based on the equipment type inference result, the preset prompt words and the data dictionary. Specifically, the equipment type inference result is obtained by performing its own knowledge inference through the question-answering model, and its essence is to narrow the scope of matching types of building equipment through the knowledge of the question-answering model. Furthermore, by inputting the data dictionary into the question-answering model, the question-answering model can be combined with the equipment type inference result and the knowledge of the data dictionary to reason again, so as to perform inference calculation in a smaller and more accurate range. In this way, the accuracy of the question-answering model reasoning can be improved, and then the accuracy of the building equipment data table processing can be improved.

[0056] Embodiment 2

[0057] Figure 2 This is a flowchart of a method for processing a building equipment data table provided in Embodiment 2 of the present invention. Based on the above embodiments, this embodiment further defines a method for determining the standard equipment type of the building equipment, such as Figure 2 As shown, including:

[0058] Step 210: Obtain a building equipment data table, a data dictionary and preset prompt words, wherein the building equipment data table includes equipment parameters corresponding to the building equipment, the preset prompt words are used to prompt the question-answering model to output inference results based on the building equipment data table, and the data dictionary includes standard equipment types and standard parameter formats of the building equipment.

[0059] Step 220: Input the building equipment data table and preset prompt words into the question-answering model to determine the equipment type inference result corresponding to the building equipment.

[0060] Step 230: input the data dictionary and the third prompt word into the question-answering model.

[0061] Among them, the data dictionary also includes equipment data related to construction equipment. The equipment data can be understood to include background knowledge of construction equipment, usage specifications, common abbreviations and other data. The equipment data can supplement the knowledge blind spots of the question-answering model so that the question-answering model can have a more comprehensive understanding of the relevant data of the construction equipment that needs to be inferred, so as to improve the accuracy of determining the type of construction equipment.

[0062] Step 240: Determine the standard equipment type of the building equipment through the question-answer model based on the equipment type inference result, the third prompt word and the data dictionary.

[0063] Among them, the third prompt word is used to prompt the question-answering model to perform reasoning based on the standard equipment type in the data dictionary and the equipment data associated with the building equipment. Specifically, due to the shortcomings of the question-answering model itself, there may be an illusion effect in the reasoning process, that is, a seemingly reasonable answer is output in a serious manner. The answer may be a random noun in the building equipment data table. However, this answer is not the required answer. Therefore, it is necessary to prompt the question-answering model through the third prompt word, and when answering, it is necessary to combine the associated data of the building equipment in the data dictionary and the standard equipment type for reasoning to improve the accuracy of the reasoning results.

[0064] Optionally, after determining the standard equipment type for building equipment, also include:

[0065] By means of the question-answer model, based on the standard equipment type of the building equipment, determining from the data dictionary the equipment parameters corresponding to the standard equipment type and the standard parameter format corresponding to the equipment parameters;

[0066] The device parameters of the data row are calibrated to a standard parameter format.

[0067] Specifically, the building equipment data table also includes equipment parameters. Since different building equipment data tables record the same type of equipment parameters in different ways, such as the date record, 1999.08.04 in table A and 1999-08-04 in table B, the inconsistent data format will cause errors when downstream equipment uses the data. Therefore, the equipment parameters need to be calibrated.

[0068] Specifically, the parameter formats and parameter quantities of different types of building equipment may be different, and the standard parameter format of the equipment parameters corresponding to the standard equipment type can be determined by searching in the data dictionary, so that the format of the equipment parameters in the building parameter data table can be calibrated by the standard parameter format.

[0069] Furthermore, device parameters can be divided into technical parameters and non-technical parameters. Different types of parameters may have different formats. Therefore, the question-answering model can be prompted to make corresponding corrections based on the types of parameters when performing format calibration to improve the accuracy of format calibration.

[0070] The embodiment of the present invention provides a method for processing a building equipment data table. In this embodiment, the data dictionary and the third prompt word are input into the question-answering model; and then the standard equipment type of the building equipment can be determined by the question-answering model based on the equipment type inference result, the third prompt word and the data dictionary. In this way, the reasoning of the question-answering model can not only use its inherent knowledge, but also combine the professional knowledge and related data of the industry about building equipment, so that the accuracy of the reasoning result can be improved, and the reasoning efficiency can be improved at the same time.

[0071] Embodiment 3

[0072] Figure 3 This is a schematic diagram of the structure of a device for processing a building equipment data table provided in Embodiment 3 of the present invention. Figure 3 As shown, the device comprises:

[0073] An acquisition module 310 is used to acquire a building equipment data table, a data dictionary and preset prompt words, wherein the building equipment data table includes equipment parameters corresponding to the building equipment, the preset prompt words are used to prompt the question-answering model to output an inference result according to the building equipment data table, and the data dictionary includes standard equipment types and standard parameter formats of the building equipment;

[0074] A first reasoning module 320, for inputting the building equipment data table and the preset prompt words into the question-answering model to determine the equipment type reasoning result corresponding to the building equipment;

[0075] The second reasoning module 330 is used to input the preset prompt words and data dictionary into the question-answering model, and determine the standard equipment type of the construction equipment based on the equipment type reasoning result, preset prompt words and data dictionary through the question-answering model.

[0076] The embodiment of the present invention provides a device for processing a building equipment data table. By inputting the building equipment data table and preset prompt words into a question-answering model, the device can enable the question-answering model to determine the equipment type inference result inferred by the model itself. Furthermore, by inputting preset prompt words and a data dictionary into the question-answering model, the question-answering model can output a more accurate equipment type of the building equipment, that is, a standard equipment type. In this way, the equipment type of the building equipment in the building equipment data table can be accurately determined, thereby improving the accuracy and efficiency of the building equipment data table processing.

[0077] Optionally, specifically, the preset prompt word includes a first prompt word and a second prompt word.

[0078] The first reasoning module 320 includes:

[0079] A table structure determination unit is used to input the first prompt word and the building equipment data table into the question-answering model, and identify the data rows of the building equipment data table through the question-answering model, wherein the first prompt word is used to represent the constraint conditions when the question-answering model identifies the table structure of the building equipment data table

[0080] A type determination unit is used to input the second prompt word into the question-answering model to determine the equipment type inference result of the construction equipment corresponding to the data row, wherein the second prompt word is used to represent the constraint conditions when the question-answering model infers the equipment type of the construction equipment.

[0081] Specifically, the first prompt word includes: prompting the question-answering model to avoid missing rows; prompting the question-answering model that the building equipment data table includes at least one table header and / or at least one title. The second prompt word includes prompting the question-answering model to distinguish the field type of each field in the data row and determine the type field representing the equipment type; prompting the question-answering model to perform reasoning based on the type field.

[0082] Specifically, the data dictionary also includes equipment data associated with building equipment, and the preset prompt words also include a third prompt word.

[0083] Optionally, the second reasoning module 330 includes:

[0084] An input unit, used for inputting the data dictionary and the third prompt word into the question-answering model;

[0085] An inference unit, configured to determine the standard equipment type of the building equipment based on the equipment type inference result, a third prompt word and a data dictionary through the question-answer model;

[0086] The third prompt word is used to prompt the question-answering model to perform reasoning based on the standard equipment type in the data dictionary and the equipment data associated with the building equipment.

[0087] Optionally, the processing device of the building equipment data table also includes: a format calibration module, which is used to determine, through the question-and-answer model and based on the standard equipment type of the building equipment, from the data dictionary the equipment parameters corresponding to the standard equipment type and the standard parameter format corresponding to the equipment parameters; and calibrate the equipment parameters of the data row to the standard parameter format.

[0088] The apparatus for processing a building equipment data table provided in the embodiment of the present invention can execute the method for processing a building equipment data table provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0089] Embodiment 4

[0090] Figure 4 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0091] like Figure 4 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0092] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0093] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a method for processing a building equipment data table.

[0094] In some embodiments, the processing method of the building equipment data table may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the processing method of the building equipment data table described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the processing method of the building equipment data table in any other appropriate manner (for example, by means of firmware).

[0095] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0096] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0097] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, device, or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0098] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0099] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0100] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

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

[0102] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for processing a building equipment data table, characterized in that: include: Obtain a building equipment data table, a data dictionary and preset prompt words, wherein the building equipment data table includes equipment parameters corresponding to the building equipment, the preset prompt words are used to prompt the question-answering model to output inference results according to the building equipment data table, and the data dictionary includes standard equipment types and standard parameter formats of the building equipment; Input the building equipment data table and the preset prompt words into the question-answering model to determine the equipment type inference result corresponding to the building equipment; The preset prompt words and data dictionary are input into the question-answering model, and the standard equipment type of the construction equipment is determined by the question-answering model based on the equipment type inference result, the preset prompt words and the data dictionary.

2. The method according to claim 1, characterized in that: The preset prompt words include a first prompt word and a second prompt word, and the inputting of the building equipment data table and the preset prompt words into the question-answering model to determine the equipment type inference result corresponding to the building equipment includes: Inputting the first prompt word and the building equipment data table into the question-answering model, and identifying data rows of the building equipment data table through the question-answering model, wherein the first prompt word is used to represent a constraint condition when the question-answering model identifies the table structure of the building equipment data table; The second prompt word is input into the question-answering model to determine the equipment type inference result of the construction equipment corresponding to the data row, wherein the second prompt word is used to represent the constraint condition when the question-answering model infers the equipment type of the construction equipment.

3. The method according to claim 2, characterized in that The first prompt word includes: prompting the question-answering model to avoid missing rows; The question-answer model is prompted that the building equipment data table includes at least one table header and / or at least one title.

4. The method according to claim 2, characterized in that: The second prompt word includes: Prompting the question-answer model to distinguish the field types of the fields in the data row and determine the type field representing the device type; The question-answering model is prompted to perform reasoning based on the type field.

5. The method according to claim 2, characterized in that: The data dictionary also includes equipment data associated with the building equipment, the preset prompt words also include a third prompt word, and the preset prompt words and the data dictionary are input into the question-answering model, and the standard equipment type of the building equipment is determined by the question-answering model based on the equipment type inference result, the preset prompt words and the data dictionary, including: Inputting the data dictionary and the third prompt word into the question-answering model; Determine the standard equipment type of the construction equipment through the question-answer model based on the equipment type reasoning result, the third prompt word and the data dictionary; The third prompt word is used to prompt the question-answering model to perform reasoning based on the standard equipment type in the data dictionary and the equipment data associated with the building equipment.

6. The method according to claim 5, characterized in that After determining the standard equipment types for construction equipment, also include: By means of the question-answer model, based on the standard equipment type of the building equipment, determining from the data dictionary the equipment parameters corresponding to the standard equipment type and the standard parameter format corresponding to the equipment parameters; The device parameters of the data row are calibrated to a standard parameter format.

7. The method according to claim 1, characterized in that The preset prompt words are also used for: The question-answering model is prompted to output the inference result and the inference reason and / or inference process corresponding to the inference result in a preset format.

8. A device for processing a building equipment data table, characterized in that: include: An acquisition module is used to acquire a building equipment data table, a data dictionary and preset prompt words, wherein the building equipment data table includes equipment parameters corresponding to the building equipment, the preset prompt words are used to prompt the question-answering model to output an inference result according to the building equipment data table, and the data dictionary includes standard equipment types and standard parameter formats of the building equipment; A first reasoning module, used for inputting the building equipment data table and the preset prompt words into the question-answering model to determine the equipment type reasoning result corresponding to the building equipment; The second reasoning module is used to input the preset prompt words and data dictionary into the question-answering model, and determine the standard equipment type of the construction equipment based on the equipment type reasoning result, preset prompt words and data dictionary through the question-answering model.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor. The computer program is executed by the at least one processor so that the at least one processor can execute the method for processing a building equipment data table according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for processing a building equipment data table according to any one of claims 1 to 7 when the processor executes the computer instructions.

Images