Intelligent self-service leasing system and leasing method for crane

Abstract

The invention provides an intelligent self-service leasing system and leasing method for a crane, and the method comprises the steps: receiving unformatted leasing demand information which is inputted by a leasing user and is used for leasing the crane, and carrying out the intelligent recognition of the leasing demand information, so as to generate formatted demand information corresponding to the leasing demand information; and converting the formatted demand information into quantitative demand information, generating crane matching parameters based on the quantitative demand information, extracting task scheduling information from the leasing demand information, and executing crane scheduling for responding to the leasing demand information according to the crane matching parameters and the task scheduling information. According to the method, redundant communication type selection time can be saved, the crane type required by project construction can be accurately matched, and the labor cost is reduced while efficient crane leasing is realized.

Description

Technical Field

[0001] The present invention relates to the field of Internet technology, and in particular to an intelligent self-service crane rental system and rental method. Background Art

[0002] A crane, also known as a hoist, is a mechanical device used for vertical lifting or horizontal lifting of heavy objects. It is commonly used in applications such as equipment lifting, emergency rescue, and heavy-duty handling, as well as in construction, road maintenance, bridge construction, and cargo loading and unloading. Cranes come in a variety of different types and specifications, varying in their movement methods, structural forms, and lifting capacities, to accommodate lifting operations in a variety of complex applications. Traditional crane rental services rely on manual labor: customers contact a crane rental company's service personnel and verbally or in writing to provide their rental requirements. The customer or the company's service personnel then selects a crane model, and the company dispatches the appropriate model to the site for construction. This crane rental method is inefficient and time-consuming, making it unsuitable for urgent construction projects. Furthermore, it requires the crane selector to fully understand the specifications, operating capacities, and applicable operating environments of various crane models, placing high demands on the crane selector. Summary of the Invention

[0003] Based on the above problems, the present invention proposes an intelligent self-service crane rental system and rental method, which can save lengthy communication and selection time, accurately match the crane type required for project construction, achieve efficient crane rental, and reduce labor costs.

[0004] In view of this, a first aspect of the present invention proposes an intelligent self-service crane rental system, comprising a self-service crane rental platform, an intelligent analysis engine and a crane management platform;

[0005] The self-service crane rental platform is configured to receive rental demand information for renting a crane input by a rental user and provide the information to the intelligent analysis engine for analysis;

[0006] The intelligent analysis engine is configured to intelligently identify the rental demand information to generate formatted demand information corresponding to the rental demand information, convert the formatted demand information into quantified demand information, generate crane matching parameters based on the quantified demand information, and extract task scheduling information from the rental demand information, the task scheduling information including target operation location and target operation time information of the crane in the rental demand information;

[0007] The crane management platform is configured to execute crane scheduling in response to the rental demand information according to the crane matching parameters and the task scheduling information.

[0008] A second aspect of the present invention provides an intelligent self-service crane rental method, comprising:

[0009] Receiving rental demand information for renting a crane input by a rental user, wherein the rental demand information includes non-formatted text for describing the crane rental demand;

[0010] Intelligently identifying the rental demand information to generate formatted demand information corresponding to the rental demand information;

[0011] converting the formatted demand information into quantified demand information;

[0012] generating crane matching parameters based on the quantified demand information;

[0013] Extracting task scheduling information from the rental demand information, the task scheduling information including target operation location and target operation time information of the crane in the rental demand information;

[0014] Crane scheduling for responding to the rental demand information is performed according to the crane matching parameters and the task scheduling information.

[0015] Furthermore, the step of intelligently identifying the rental demand information to generate formatted demand information corresponding to the rental demand information specifically includes:

[0016] Obtain pre-configured demand keywords that correspond to each demand dimension;

[0017] Dividing the rental demand information into a plurality of demand statements;

[0018] Extract the keywords of each requirement statement;

[0019] The subject words are matched with the demand keywords to establish a corresponding relationship between the demand statements and the demand dimensions.

[0020] Furthermore, after the step of matching the subject words with the demand keywords to establish a corresponding relationship between the demand statements and the demand dimensions, the method further includes:

[0021] Generate a demand dimension list corresponding to the rental demand information, wherein the demand dimension list includes demand dimension names corresponding to the demand statements;

[0022] Integrate the demand statements corresponding to the same demand dimension in the rental demand information into a demand description text;

[0023] The formatted requirement information is generated using the requirement dimension name as a key name and the corresponding requirement description text as a key value.

[0024] Furthermore, the step of converting the formatted demand information into quantified demand information specifically includes:

[0025] Dividing each demand dimension in the formatted demand information into quantitative demand dimensions and non-quantitative demand dimensions;

[0026] performing a normalization process on the quantitative requirement dimension to generate a first quantitative requirement;

[0027] Coding the non-quantitative requirement dimension to generate a second quantitative requirement;

[0028] The first quantitative requirement and the second quantitative requirement are combined into the quantitative requirement information.

[0029] Furthermore, the step of generating crane matching parameters based on the quantitative demand information specifically includes:

[0030] generating a demand data sequence based on the quantitative demand information;

[0031] The demand data sequence is input into a pre-trained crane matching parameter generation model to generate the crane matching parameters.

[0032] Furthermore, before the step of receiving the rental demand information for renting a crane input by the rental user, the method further includes:

[0033] Configure the sorting number for each requirement dimension;

[0034] The step of generating a demand data sequence based on the quantitative demand information specifically includes:

[0035] Generate a null value sequence of a preset length, wherein each numerical element in the null value sequence corresponds to a required dimension according to the sorting number;

[0036] Each quantized value in the quantized requirement information is filled into a corresponding position in the empty value sequence to generate the requirement data sequence.

[0037] Furthermore, the step of extracting task scheduling information from the rental demand information specifically includes:

[0038] Performing semantic recognition on the subject words of each demand statement in the rental demand information to determine whether the subject words of any demand statement are related to the construction location or construction time;

[0039] When the subject word of any demand sentence is related to the construction site, extracting the construction site information from the demand sentence;

[0040] When the subject word of any demand sentence is related to the construction time, extracting the construction time information from the demand sentence;

[0041] The construction location information and / or the construction time information are determined as the task scheduling information.

[0042] Furthermore, the step of executing crane scheduling in response to the rental demand information according to the crane matching parameters and the task scheduling information specifically includes:

[0043] generating a crane list matching the task scheduling information;

[0044] Obtaining specification parameters of each crane in the crane list;

[0045] Calculating the matching degree between the specification parameters and the crane matching parameters;

[0046] Determine the crane whose specification parameters are most similar to the crane matching parameters as the target crane;

[0047] A dispatching task plan for the target crane is generated based on the task scheduling information.

[0048] Furthermore, the step of calculating the matching degree between the specification parameters and the crane matching parameters specifically includes:

[0049] Get the first quantized parameter value pql in the crane matching parameter i and the first non-quantized parameter value pnql j , where i∈[l,n q ],j∈[l,n nq ],n q is the number of quantized parameters in the crane matching parameters, n nq The number of quantized parameters in the crane matching parameters;

[0050] Obtain the first quantization parameter values ​​pql from the specification parameters i and the first non-quantization parameter value pnql j The corresponding second quantization parameter value pq2 i and the second non-quantization parameter value pnq2 j ;

[0051] Calculate the quantized parameter deviation sequence Δp between the specification parameters and the crane matching parameters i and the non-quantized parameter matching sequence σ j ,in:

[0052]

[0053] Based on the quantization parameter deviation sequence Δp i and the non-quantized parameter matching sequence σ jCalculate the matching degree between the specification parameters and the crane matching parameters:

[0054]

[0055] The present invention proposes an intelligent self-service crane rental system and rental method. By receiving non-formatted rental demand information for renting a crane input by a rental user, the rental demand information is intelligently identified to generate formatted demand information corresponding to the rental demand information, the formatted demand information is converted into quantitative demand information, crane matching parameters are generated based on the quantitative demand information, task scheduling information is extracted from the rental demand information, and crane scheduling for responding to the rental demand information is executed according to the crane matching parameters and the task scheduling information. This can save lengthy communication and selection time, accurately match the crane type required for project construction, achieve efficient crane rental, and reduce labor costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 This is a schematic diagram of an intelligent self-service crane rental system provided by one embodiment of the present invention;

[0057] Figure 2 The present invention provides a flowchart of an intelligent self-service crane rental method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0058] In order to more clearly understand the above-mentioned objects, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that, in the absence of conflict, the embodiments of the present application and the features therein can be combined with each other.

[0059] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the scope of protection of the present invention is not limited to the specific embodiments disclosed below.

[0060] In the description of the present invention, the term "plurality" refers to two or more. Unless otherwise specified, the terms "upper" and "lower" are based on the orientations or positional relationships shown in the accompanying drawings and are intended solely to facilitate and simplify the description of the present invention. They are not intended to indicate or imply that the devices or components referred to must have a specific orientation, be constructed, or operate in a specific manner. Therefore, they should not be construed as limiting the present invention. The terms "connected," "mounted," and "fixed," etc., should be interpreted broadly. For example, "connected" can refer to fixed, removable, or integral connections; directly or indirectly through an intermediary. A person of ordinary skill in the art will understand the specific meanings of these terms in the present invention based on the specific circumstances. Furthermore, the terms "first," "second," etc., etc., are used for descriptive purposes only and should not be construed to indicate or imply relative importance or to implicitly specify the number of the technical features indicated. Therefore, a feature designated "first," "second," etc., may explicitly or implicitly include one or more of such features. In the description of the present invention, unless otherwise specified, "plurality" means two or more.

[0061] Throughout this specification, terms such as "one embodiment," "some implementations," and "specific examples" indicate that the specific features, structures, materials, or characteristics described in conjunction with that embodiment or example are included in at least one embodiment or example of the present invention. In this specification, schematic representations of these terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0062] An intelligent self-service crane rental system and rental method according to some embodiments of the present invention will be described below with reference to the accompanying drawings.

[0063] like Figure 1 As shown, in view of this, the first aspect of the present invention proposes an intelligent self-service crane rental system, including a crane self-service rental platform, an intelligent analysis engine and a crane management platform;

[0064] The self-service crane rental platform is configured to receive rental demand information for renting a crane input by a rental user and provide the information to the intelligent analysis engine for analysis;

[0065] The intelligent analysis engine is configured to intelligently identify the rental demand information to generate formatted demand information corresponding to the rental demand information, convert the formatted demand information into quantified demand information, generate crane matching parameters based on the quantified demand information, and extract task scheduling information from the rental demand information, the task scheduling information including target operation location and target operation time information of the crane in the rental demand information;

[0066] The crane management platform is configured to execute crane scheduling in response to the rental demand information according to the crane matching parameters and the task scheduling information.

[0067] Specifically, the self-service crane rental platform is a rental service platform for rental users. The self-service crane rental platform provides a UI (User Interface) operation interface to rental users in the form of a WEB (network) front end or client, so that the rental users can input rental demand information through the self-service crane rental platform.

[0068] The intelligent analysis engine includes artificial intelligence engines for performing semantic recognition, format conversion, quantization processing and parameter matching respectively. The artificial intelligence model used by the artificial intelligence engine can be a third-party artificial intelligence model directly called through an API (Application Program Interface) or a custom model trained using machine learning technology.

[0069] The crane management platform is used to manage and maintain crane data, including crane specification parameter data, status data and work task data, and to dispatch cranes according to rental needs.

[0070] Specifically, due to differences in the weight and volume of the lifting objects, as well as in the operating environment, different construction projects require different crane types and lifting capacity requirements. In the technical solution of the present invention, the unformatted text can be natural language text entered by the user, allowing the user to describe their crane rental needs in a more colloquial manner, without the need for the user to provide the specific crane model or specifications required.

[0071] In some embodiments of the present invention, the crane rental service platform provides a voice input module for receiving user voice and a voice recognition module for converting the user voice into text. Upon receiving a user inputting information regarding a crane rental requirement, the crane rental service platform receives the user's voice data describing the crane rental requirement via the voice input module and converts the voice data into the unformatted text via the voice recognition module.

[0072] The formatted requirement information is a formatted text corresponding to the pre-configured crane rental requirement dimensions. For example, the formatted requirement information may be an XML (Extensible Markup Language) formatted text or a JSON (JavaScript Object Notation) formatted text with each requirement dimension as a tag name or key name.

[0073] The demand dimension is a data dimension that describes the working environment requirements and / or lifting capacity requirements. The demand dimension can be configured according to the needs of actual implementation. For example, the demand dimension can include one or more of the crane's working environment description dimension, the lifting object description dimension, and the crane description dimension. The working environment description dimension can include the type and terrain of the working environment, and can also include the temperature, humidity, wind force, etc. of the working environment. The lifting object description dimension can include the name, type, weight, volume, etc. of the lifting object, and the crane description dimension can include the crane's movement mode, structural form, maximum lifting weight, maximum lifting height, etc.

[0074] In the step of intelligently identifying the rental demand information to generate formatted demand information corresponding to the rental demand information, the description content corresponding to each demand dimension in the formatted demand information is directly extracted from the rental demand information. Therefore, the description content corresponding to each demand dimension in the formatted demand information may be either quantitative or non-quantitative. In the step of converting the formatted demand information into quantitative demand information, the non-quantitative description in the formatted demand information is specifically converted into quantitative description.

[0075] Furthermore, in the step of intelligently identifying the rental demand information to generate formatted demand information corresponding to the rental demand information, the intelligent analysis engine is configured to:

[0076] Obtain pre-configured demand keywords that correspond to each demand dimension;

[0077] Dividing the rental demand information into a plurality of demand statements;

[0078] Extract the keywords of each requirement statement;

[0079] The subject words are matched with the demand keywords to establish a corresponding relationship between the demand statements and the demand dimensions.

[0080] The present invention generates formatted demand information corresponding to the rental demand information by pre-configuring demand keywords corresponding to each demand dimension. In the technical solutions of some embodiments of the present invention, each demand keyword corresponds to a demand dimension. Preferably, in the technical solution of this embodiment, the demand keyword can be the name of the corresponding demand dimension, for example, the demand keyword can be a demand dimension name such as "work location", "lifting object", etc. In the technical solutions of other embodiments of the present invention, a demand dimension is configured with multiple demand keywords, and the demand keyword is a description keyword that describes the specific content of the demand dimension. For example, the demand keyword can be a keyword that describes the specific content of the demand dimension such as "city", "bridge", "container", etc.

[0081] The rental demand information is a text block consisting of multiple sentences, and the demand sentence is a single sentence in the text block, or a series of consecutive sentences. That is, a demand sentence can be a single sentence in the rental demand information that is not separated by any punctuation marks, or a collection of multiple sentences connected by one or more punctuation marks.

[0082] In the technical solutions of some embodiments of the present invention, punctuation marks in the rental demand information may be directly used to perform sentence segmentation on the text block to obtain individual demand sentences.

[0083] In the technical solutions of other embodiments of the present invention, in the step of dividing the rental demand information into a plurality of demand statements, the intelligent analysis engine is configured to:

[0084] Configure semantic similarity threshold;

[0085] Splitting the rental demand information into a first sentence list according to punctuation marks, where the punctuation marks include commas, periods, and semicolons;

[0086] Convert each sentence in the first sentence list into a corresponding semantic vector;

[0087] Calculating the cosine similarity of the semantic vectors of adjacent sentences in the first sentence list;

[0088] Determine a position where the cosine similarity is less than the semantic similarity threshold as a boundary point;

[0089] Splitting the rental demand information into a second sentence list using the boundary point as a segmentation position;

[0090] Each sentence in the second sentence list is determined as the requirement sentence.

[0091] Preferably, in the step of converting each sentence in the first sentence list into a corresponding semantic vector, a text embedding model such as SBERT (Sentence Bidirectional Encoder Representations from Transformers) can be used to generate the semantic vector.

[0092] Similarly, in the step of matching the subject word with the demand keyword to establish a corresponding relationship between the demand statement and the demand dimension, the subject word and the demand keyword are converted into corresponding semantic vectors, their semantic similarity is determined by calculating the cosine similarity, and the demand dimension corresponding to the demand keyword with the greatest semantic similarity to the subject word is determined as the demand dimension corresponding to its demand statement, thereby establishing an association relationship between the two.

[0093] Furthermore, in the step of extracting the subject words of each demand statement, the intelligent analysis engine is configured to:

[0094] Converting the demand statement into a corresponding semantic vector;

[0095] Performing word segmentation processing on the demand statement to obtain several keyword word segments of the demand statement;

[0096] Convert the keyword segmentation into corresponding keyword vectors;

[0097] Calculate the cosine similarity between each keyword vector and the semantic vector;

[0098] The keyword segment with the largest cosine similarity to the semantic vector is determined as the subject word of the demand sentence.

[0099] In the technical solution of the above-mentioned implementation mode, the keyword segmentation does not include stop words, numbers, quantifiers, pronouns, etc. in the demand statement, that is, after the demand statement is segmented, the stop words, numbers, quantifiers, and pronouns in the demand statement are removed to obtain the keyword segmentation.

[0100] Preferably, in the steps of converting the demand statement into the corresponding semantic vector and converting the keyword segmentation into the corresponding keyword vector, text embedding models such as BERT (Bidirectional Encoder Representation from Transformers) and SBERT can be used to generate the semantic vector and the keyword vector.

[0101] Furthermore, after the step of matching the subject words with the demand keywords to establish a correspondence between the demand statements and the demand dimensions, the intelligent analysis engine is configured to:

[0102] Generate a demand dimension list corresponding to the rental demand information, wherein the demand dimension list includes demand dimension names corresponding to the demand statements;

[0103] Integrate the demand statements corresponding to the same demand dimension in the rental demand information into a demand description text;

[0104] The formatted requirement information is generated using the requirement dimension name as a key name and the corresponding requirement description text as a key value.

[0105] Furthermore, in the step of integrating the demand statements corresponding to the same demand dimension in the rental demand information into a demand description text, the intelligent analysis engine is configured to:

[0106] The demand dimension list is traversed, and the demand dimension corresponding to each demand dimension name in the traversed demand dimension list is determined as a target demand dimension, so as to perform the following processing on the target demand dimension:

[0107] determining one or more demand statements corresponding to the target demand dimension in the rental demand information as target demand statements;

[0108] When there is only one demand statement corresponding to the target demand dimension in the rental demand information, determining the target demand statement as the demand description text;

[0109] When there is more than one demand statement corresponding to the target demand dimension in the rental demand information, the target demand statements are merged into the demand description text.

[0110] In the technical solution of the above-mentioned embodiment, the formatted requirement information is composed of the requirement dimensions in the requirement dimension list. More specifically, the requirement dimension list includes several requirement dimension names, which are the requirement dimensions corresponding to the rental requirements described in the rental requirement information. The formatted requirement information includes a number of key-value pairs equal to the number of requirement dimensions in the requirement dimension list, with each key-value pair corresponding to a requirement dimension in the requirement dimension list. Each key-value pair consists of a key name and a key value, where the key name in a key-value pair is the name of the corresponding requirement dimension, and the key value is the corresponding requirement description text.

[0111] Furthermore, in the step of converting the formatted demand information into quantitative demand information, the intelligent analysis engine is configured to:

[0112] Dividing each demand dimension in the formatted demand information into quantitative demand dimensions and non-quantitative demand dimensions;

[0113] performing a normalization process on the quantitative requirement dimension to generate a first quantitative requirement;

[0114] Coding the non-quantitative requirement dimension to generate a second quantitative requirement;

[0115] The first quantitative requirement and the second quantitative requirement are combined into the quantitative requirement information.

[0116] Specifically, in the formatted requirement information, requirement dimensions that use quantified values ​​as the requirement description content are quantitative requirement dimensions. For example, if the lifting weight is 5 tons and the lifting height is 30 meters, the corresponding lifting weight and lifting height requirement dimensions are quantitative requirement dimensions. Requirement dimensions that use non-quantified value text as the requirement description content are non-quantitative requirement dimensions.

[0117] Furthermore, in the step of performing standardization processing on the quantitative requirement dimension to generate the first quantitative requirement, the intelligent analysis engine is configured to:

[0118] Converting the text-formatted values ​​in the requirement description text of the quantitative requirement dimension into digital format;

[0119] The numerical value in the quantitative requirement dimension is converted into a numerical value of a pre-configured standard unit, where the standard unit includes a standard length unit, a standard mass unit, and a standard volume unit.

[0120] Furthermore, before the step of coding the non-quantitative requirement dimension to generate the second quantitative requirement, the intelligent analysis engine is configured to:

[0121] Configure a digital code for each demand keyword in each non-quantitative demand dimension. The digital code can be the sequential number of the demand keyword in the corresponding non-quantitative demand dimension. For example, if a non-quantitative demand dimension contains 5 demand keywords, the digital code sequence of these 5 demand keywords is one of the 5 values ​​1 to 5.

[0122] In the technical solution of the above embodiment, the step of coding the non-quantitative demand dimension to generate the second quantitative demand is specifically to represent the demand keywords in the non-quantitative demand dimension with corresponding digital codes in the second quantitative demand.

[0123] Furthermore, in the step of generating crane matching parameters based on the quantitative demand information, the intelligent analysis engine is configured to:

[0124] generating a demand data sequence based on the quantitative demand information;

[0125] The demand data sequence is input into a pre-trained crane matching parameter generation model to generate the crane matching parameters.

[0126] Specifically, the crane matching parameter generation model is a pre-trained convolutional neural network model, which is obtained by deep learning training using demand data and crane parameter data of historical crane rental projects as sample data.

[0127] Furthermore, before the step of receiving rental demand information for renting a crane input by a rental user, the intelligent analysis engine is configured to:

[0128] Extracting rental demand data and crane parameter data from historical crane rental projects, wherein the crane parameter data is parameter data of cranes actually arranged in the historical crane rental projects;

[0129] Build a convolutional neural network framework and configure convolutional neural network training parameters;

[0130] Arranging the rental demand data into a demand data sequence as an input data sample;

[0131] Arranging the crane parameter data into crane matching parameters as output data samples;

[0132] Based on the input data samples and the output data samples, the crane matching parameter generation model is trained under the convolutional neural network framework in a supervised learning training mode.

[0133] Furthermore, before the step of receiving rental demand information for renting a crane input by a rental user, the intelligent analysis engine is configured to:

[0134] Configure the sorting number for each requirement dimension;

[0135] The step of generating a demand data sequence based on the quantitative demand information specifically includes:

[0136] Generate a null value sequence of a preset length, wherein each numerical element in the null value sequence corresponds to a required dimension according to the sorting number;

[0137] Each quantized value in the quantized requirement information is filled into a corresponding position in the empty value sequence to generate the requirement data sequence.

[0138] Specifically, the sorting number is a unique number corresponding to each requirement dimension, and can be a pure text number or a combination of numbers and letters. The sorting number of each requirement dimension does not overlap with the sorting number of any other requirement dimension. The requirement dimensions can be sorted in descending or ascending order according to the sorting number.

[0139] The required data sequence is a complete data sequence that includes all required dimensions, that is, the required data sequence has a fixed data length (that is, the number of data elements in the data sequence), and its data length is the same as the total number of required dimensions. The null value sequence is the initial state of the required data sequence before being filled with values, and its length is the same as the length of the required data sequence, that is, the preset length is the total number of required dimensions, and each numerical element in the null value sequence is a null value (which can also be configured as 0).

[0140] In the technical solution of the above embodiment, for demand dimensions not covered by the rental demand information, the corresponding positions are filled with a default filler number, which can be 0 or any other pre-configured value. For demand dimensions covered by the rental demand information, they are normalized and written into the corresponding positions of the demand data sequence.

[0141] Furthermore, in the step of extracting task scheduling information from the rental demand information, the intelligent analysis engine is configured to:

[0142] Performing semantic recognition on the subject words of each demand statement in the rental demand information to determine whether the subject words of any demand statement are related to the construction location or construction time;

[0143] When the subject word of any demand sentence is related to the construction site, extracting the construction site information from the demand sentence;

[0144] When the subject word of any demand sentence is related to the construction time, extracting the construction time information from the demand sentence;

[0145] The construction location information and / or the construction time information are determined as the task scheduling information.

[0146] Specifically, an existing NER (Named Entity Recognition) model can be used to identify whether the subject words of a requirement statement are related to time or location, thereby determining whether any subject words of the requirement statement are related to the construction location or construction time. In other embodiments, a self-trained keyword classification model can also be used to classify the subject words of the requirement statement to determine whether any subject words of the requirement statement are related to the construction location or construction time.

[0147] Furthermore, in the step of executing crane scheduling in response to the rental demand information based on the crane matching parameters and the task scheduling information, the intelligent analysis engine is configured to:

[0148] generating a crane list matching the task scheduling information;

[0149] Obtaining specification parameters of each crane in the crane list;

[0150] Calculating the matching degree between the specification parameters and the crane matching parameters;

[0151] Determine the crane whose specification parameters are most similar to the crane matching parameters as the target crane;

[0152] A dispatching task plan for the target crane is generated based on the task scheduling information.

[0153] In the technical solutions of some embodiments of the present invention, the cranes in the crane list are a list of cranes that are idle within the construction time range and located at a crane rental station closest to the construction site.

[0154] Furthermore, in the step of calculating the matching degree between the specification parameters and the crane matching parameters, the intelligent analysis engine is configured to:

[0155] Get the first quantized parameter value pql in the crane matching parameter i and the first non-quantized parameter value pnql j , where i∈[l,n q ],j∈[l,n nq ],n q is the number of quantized parameters in the crane matching parameters, n nq The number of quantized parameters in the crane matching parameters;

[0156] Obtain the first quantization parameter values ​​pql from the specification parameters i and the first non-quantization parameter value pnql j The corresponding second quantization parameter value pq2j and the second non-quantization parameter value pnq2 j ;

[0157] Calculate the quantized parameter deviation sequence Δp between the specification parameters and the crane matching parameters i and the non-quantized parameter matching sequence σ j ,in:

[0158]

[0159] Based on the quantization parameter deviation sequence Δp i and the non-quantized parameter matching sequence σ j Calculate the matching degree between the specification parameters and the crane matching parameters:

[0160]

[0161] Specifically, the crane matching parameters are a parameter table containing several crane specification parameters, the parameter type of the crane matching parameters is the same as the parameter type of the crane specification parameters, or the parameter type of the crane matching parameters is a subset of the parameter type of the crane specification parameters, that is, each parameter in the crane matching parameters is a specification parameter of the crane.

[0162] It should be known that the crane matching parameters and the specification parameters are also composed of quantified specification parameters and non-quantitative specification parameters, among which the quantified specification parameters include the crane's own weight, power size, main arm length and maximum lifting weight, etc., and the non-quantitative specification parameters are represented by digital codes. Taking the movement mode of the crane as an example, the movement mode of the truck crane can be represented as 1, the movement mode of the crawler crane can be represented as 2, the movement mode of the truck crane can be represented as 3, etc.

[0163] In the technical solution of the above embodiment, the number of parameters in the crane matching parameters is represented as n p , then it satisfies n p =n q +n nq The first quantization parameter value pql i is the i-th quantized parameter in the crane matching parameter, and the second quantized parameter value pq2 i The first quantization parameter value pql i The corresponding specification parameters, that is, when the i value is the same, pql i and pq2 i It is the numerical value of the same quantitative specification parameter of the crane.

[0164] like Figure 2As shown, the second aspect of the present invention provides an intelligent self-service crane rental method, comprising:

[0165] Receiving rental demand information for renting a crane input by a rental user, wherein the rental demand information includes non-formatted text for describing the crane rental demand;

[0166] Intelligently identifying the rental demand information to generate formatted demand information corresponding to the rental demand information;

[0167] converting the formatted demand information into quantified demand information;

[0168] generating crane matching parameters based on the quantified demand information;

[0169] Extracting task scheduling information from the rental demand information, the task scheduling information including target operation location and target operation time information of the crane in the rental demand information;

[0170] Crane scheduling for responding to the rental demand information is performed according to the crane matching parameters and the task scheduling information.

[0171] Specifically, due to differences in the weight and volume of the lifting objects, as well as in the operating environment, different construction projects require different crane types and lifting capacity requirements. In the technical solution of the present invention, the unformatted text can be natural language text entered by the user, allowing the user to describe their crane rental needs in a more colloquial manner, without the need for the user to provide the specific crane model or specifications required.

[0172] In some embodiments of the present invention, the crane rental service platform provides a voice input module for receiving user voice and a voice recognition module for converting the user voice into text. Upon receiving a user inputting information regarding a crane rental requirement, the crane rental service platform receives the user's voice data describing the crane rental requirement via the voice input module and converts the voice data into the unformatted text via the voice recognition module.

[0173] The formatted requirement information is a formatted text corresponding to the pre-configured crane rental requirement dimensions. For example, the formatted requirement information may be an XML (Extensible Markup Language) formatted text or a JSON (JavaScript Object Notation) formatted text with each requirement dimension as a tag name or key name.

[0174] The demand dimension is a data dimension that describes the working environment requirements and / or lifting capacity requirements. The demand dimension can be configured according to the needs of actual implementation. For example, the demand dimension can include one or more of the crane's working environment description dimension, the lifting object description dimension, and the crane description dimension. The working environment description dimension can include the type and terrain of the working environment, and can also include the temperature, humidity, wind force, etc. of the working environment. The lifting object description dimension can include the name, type, weight, volume, etc. of the lifting object, and the crane description dimension can include the crane's movement mode, structural form, maximum lifting weight, maximum lifting height, etc.

[0175] In the step of intelligently identifying the rental demand information to generate formatted demand information corresponding to the rental demand information, the description content corresponding to each demand dimension in the formatted demand information is directly extracted from the rental demand information. Therefore, the description content corresponding to each demand dimension in the formatted demand information may be either quantitative or non-quantitative. In the step of converting the formatted demand information into quantitative demand information, the non-quantitative description in the formatted demand information is specifically converted into quantitative description.

[0176] Furthermore, the step of intelligently identifying the rental demand information to generate formatted demand information corresponding to the rental demand information specifically includes:

[0177] Obtain pre-configured demand keywords that correspond to each demand dimension;

[0178] Dividing the rental demand information into a plurality of demand statements;

[0179] Extract the keywords of each requirement statement;

[0180] The subject words are matched with the demand keywords to establish a corresponding relationship between the demand statements and the demand dimensions.

[0181] The present invention generates formatted demand information corresponding to the rental demand information by pre-configuring demand keywords corresponding to each demand dimension. In the technical solutions of some embodiments of the present invention, each demand keyword corresponds to a demand dimension. Preferably, in the technical solution of this embodiment, the demand keyword can be the name of the corresponding demand dimension, for example, the demand keyword can be a demand dimension name such as "work location", "lifting object", etc. In the technical solutions of other embodiments of the present invention, a demand dimension is configured with multiple demand keywords, and the demand keyword is a description keyword that describes the specific content of the demand dimension. For example, the demand keyword can be a keyword that describes the specific content of the demand dimension such as "city", "bridge", "container", etc.

[0182] The rental demand information is a text block consisting of multiple sentences, and the demand sentence is a single sentence in the text block, or a series of consecutive sentences. That is, a demand sentence can be a single sentence in the rental demand information that is not separated by any punctuation marks, or a collection of multiple sentences connected by one or more punctuation marks.

[0183] In the technical solutions of some embodiments of the present invention, punctuation marks in the rental demand information may be directly used to perform sentence segmentation on the text block to obtain individual demand sentences.

[0184] In some other embodiments of the present invention, the step of dividing the rental demand information into a plurality of demand statements specifically includes:

[0185] Configure semantic similarity threshold;

[0186] Splitting the rental demand information into a first sentence list according to punctuation marks, where the punctuation marks include commas, periods, and semicolons;

[0187] Convert each sentence in the first sentence list into a corresponding semantic vector;

[0188] Calculating the cosine similarity of the semantic vectors of adjacent sentences in the first sentence list;

[0189] Determine a position where the cosine similarity is less than the semantic similarity threshold as a boundary point;

[0190] Splitting the rental demand information into a second sentence list using the boundary point as a segmentation position;

[0191] Each sentence in the second sentence list is determined as the requirement sentence.

[0192] Preferably, in the step of converting each sentence in the first sentence list into a corresponding semantic vector, a text embedding model such as SBERT (Sentence Bidirectional Encoder Representations from Transformers) can be used to generate the semantic vector.

[0193] Similarly, in the step of matching the subject word with the demand keyword to establish a corresponding relationship between the demand statement and the demand dimension, the subject word and the demand keyword are converted into corresponding semantic vectors, their semantic similarity is determined by calculating the cosine similarity, and the demand dimension corresponding to the demand keyword with the greatest semantic similarity to the subject word is determined as the demand dimension corresponding to its demand statement, thereby establishing an association relationship between the two.

[0194] Furthermore, the steps of extracting the subject words of each demand statement specifically include:

[0195] Converting the demand statement into a corresponding semantic vector;

[0196] Performing word segmentation processing on the demand statement to obtain several keyword word segments of the demand statement;

[0197] Convert the keyword segmentation into corresponding keyword vectors;

[0198] Calculate the cosine similarity between each keyword vector and the semantic vector;

[0199] The keyword segment with the largest cosine similarity to the semantic vector is determined as the subject word of the demand sentence.

[0200] In the technical solution of the above-mentioned implementation mode, the keyword segmentation does not include stop words, numbers, quantifiers, pronouns, etc. in the demand statement, that is, after the demand statement is segmented, the stop words, numbers, quantifiers, and pronouns in the demand statement are removed to obtain the keyword segmentation.

[0201] Preferably, in the steps of converting the demand statement into the corresponding semantic vector and converting the keyword segmentation into the corresponding keyword vector, text embedding models such as BERT (Bidirectional Encoder Representation from Transformers) and SBERT can be used to generate the semantic vector and the keyword vector.

[0202] Furthermore, after the step of matching the subject words with the demand keywords to establish a corresponding relationship between the demand statements and the demand dimensions, the method further includes:

[0203] Generate a demand dimension list corresponding to the rental demand information, wherein the demand dimension list includes demand dimension names corresponding to the demand statements;

[0204] Integrate the demand statements corresponding to the same demand dimension in the rental demand information into a demand description text;

[0205] The formatted requirement information is generated using the requirement dimension name as a key name and the corresponding requirement description text as a key value.

[0206] Furthermore, the step of integrating the demand statements corresponding to the same demand dimension in the rental demand information into a demand description text specifically includes:

[0207] The demand dimension list is traversed, and the demand dimension corresponding to each demand dimension name in the traversed demand dimension list is determined as a target demand dimension, so as to perform the following processing on the target demand dimension:

[0208] determining one or more demand statements corresponding to the target demand dimension in the rental demand information as target demand statements;

[0209] When there is only one demand statement corresponding to the target demand dimension in the rental demand information, determining the target demand statement as the demand description text;

[0210] When there is more than one demand statement corresponding to the target demand dimension in the rental demand information, the target demand statements are merged into the demand description text.

[0211] In the technical solution of the above-mentioned embodiment, the formatted requirement information is composed of the requirement dimensions in the requirement dimension list. More specifically, the requirement dimension list includes several requirement dimension names, which are the requirement dimensions corresponding to the rental requirements described in the rental requirement information. The formatted requirement information includes a number of key-value pairs equal to the number of requirement dimensions in the requirement dimension list, with each key-value pair corresponding to a requirement dimension in the requirement dimension list. Each key-value pair consists of a key name and a key value, where the key name in a key-value pair is the name of the corresponding requirement dimension, and the key value is the corresponding requirement description text.

[0212] Furthermore, the step of converting the formatted demand information into quantified demand information specifically includes:

[0213] Dividing each demand dimension in the formatted demand information into quantitative demand dimensions and non-quantitative demand dimensions;

[0214] performing a normalization process on the quantitative requirement dimension to generate a first quantitative requirement;

[0215] Coding the non-quantitative requirement dimension to generate a second quantitative requirement;

[0216] The first quantitative requirement and the second quantitative requirement are combined into the quantitative requirement information.

[0217] Specifically, in the formatted requirement information, requirement dimensions that use quantified values ​​as the requirement description content are quantitative requirement dimensions. For example, if the lifting weight is 5 tons and the lifting height is 30 meters, the corresponding lifting weight and lifting height requirement dimensions are quantitative requirement dimensions. Requirement dimensions that use non-quantified value text as the requirement description content are non-quantitative requirement dimensions.

[0218] Furthermore, the step of performing standardization processing on the quantitative requirement dimension to generate the first quantitative requirement includes:

[0219] Converting the text-formatted values ​​in the requirement description text of the quantitative requirement dimension into digital format;

[0220] The numerical value in the quantitative requirement dimension is converted into a numerical value of a pre-configured standard unit, where the standard unit includes a standard length unit, a standard mass unit, and a standard volume unit.

[0221] Furthermore, before the step of coding the non-quantitative requirement dimension to generate the second quantitative requirement, the method further includes:

[0222] Configure a digital code for each demand keyword in each non-quantitative demand dimension. The digital code can be the sequential number of the demand keyword in the corresponding non-quantitative demand dimension. For example, if a non-quantitative demand dimension contains 5 demand keywords, the digital code sequence of these 5 demand keywords is one of the 5 values ​​1 to 5.

[0223] In the technical solution of the above embodiment, the step of coding the non-quantitative demand dimension to generate the second quantitative demand is specifically to represent the demand keywords in the non-quantitative demand dimension with corresponding digital codes in the second quantitative demand.

[0224] Furthermore, the step of generating crane matching parameters based on the quantitative demand information specifically includes:

[0225] generating a demand data sequence based on the quantitative demand information;

[0226] The demand data sequence is input into a pre-trained crane matching parameter generation model to generate the crane matching parameters.

[0227] Specifically, the crane matching parameter generation model is a pre-trained convolutional neural network model, which is obtained by deep learning training using demand data and crane parameter data of historical crane rental projects as sample data.

[0228] Furthermore, before the step of receiving the rental demand information for renting a crane input by the rental user, the method further includes:

[0229] Extracting rental demand data and crane parameter data from historical crane rental projects, wherein the crane parameter data is parameter data of cranes actually arranged in the historical crane rental projects;

[0230] Build a convolutional neural network framework and configure convolutional neural network training parameters;

[0231] Arranging the rental demand data into a demand data sequence as an input data sample;

[0232] Arranging the crane parameter data into crane matching parameters as output data samples;

[0233] Based on the input data samples and the output data samples, the crane matching parameter generation model is trained under the convolutional neural network framework in a supervised learning training mode.

[0234] Furthermore, before the step of receiving the rental demand information for renting a crane input by the rental user, the method further includes:

[0235] Configure the sorting number for each requirement dimension;

[0236] The step of generating a demand data sequence based on the quantitative demand information specifically includes:

[0237] Generate a null value sequence of a preset length, wherein each numerical element in the null value sequence corresponds to a required dimension according to the sorting number;

[0238] Each quantized value in the quantized requirement information is filled into a corresponding position in the empty value sequence to generate the requirement data sequence.

[0239] Specifically, the sorting number is a unique number corresponding to each requirement dimension, and can be a pure text number or a combination of numbers and letters. The sorting number of each requirement dimension does not overlap with the sorting number of any other requirement dimension. The requirement dimensions can be sorted in descending or ascending order according to the sorting number.

[0240] The required data sequence is a complete data sequence that includes all required dimensions, that is, the required data sequence has a fixed data length (that is, the number of data elements in the data sequence), and its data length is the same as the total number of required dimensions. The null value sequence is the initial state of the required data sequence before being filled with values, and its length is the same as the length of the required data sequence, that is, the preset length is the total number of required dimensions, and each numerical element in the null value sequence is a null value (which can also be configured as 0).

[0241] In the technical solution of the above embodiment, for demand dimensions not covered by the rental demand information, the corresponding positions are filled with a default filler number, which can be 0 or any other pre-configured value. For demand dimensions covered by the rental demand information, they are normalized and written into the corresponding positions of the demand data sequence.

[0242] Furthermore, the step of extracting task scheduling information from the rental demand information specifically includes:

[0243] Performing semantic recognition on the subject words of each demand statement in the rental demand information to determine whether the subject words of any demand statement are related to the construction location or construction time;

[0244] When the subject word of any demand sentence is related to the construction site, extracting the construction site information from the demand sentence;

[0245] When the subject word of any demand sentence is related to the construction time, extracting the construction time information from the demand sentence;

[0246] The construction location information and / or the construction time information are determined as the task scheduling information.

[0247] Specifically, an existing NER (Named Entity Recognition) model can be used to identify whether the subject words of a requirement statement are related to time or location, thereby determining whether any subject words of the requirement statement are related to the construction location or construction time. In other embodiments, a self-trained keyword classification model can also be used to classify the subject words of the requirement statement to determine whether any subject words of the requirement statement are related to the construction location or construction time.

[0248] Furthermore, the step of executing crane scheduling in response to the rental demand information according to the crane matching parameters and the task scheduling information specifically includes:

[0249] generating a crane list matching the task scheduling information;

[0250] Obtaining specification parameters of each crane in the crane list;

[0251] Calculating the matching degree between the specification parameters and the crane matching parameters;

[0252] Determine the crane whose specification parameters are most similar to the crane matching parameters as the target crane;

[0253] A dispatching task plan for the target crane is generated based on the task scheduling information.

[0254] In the technical solutions of some embodiments of the present invention, the cranes in the crane list are a list of cranes that are idle within the construction time range and located at a crane rental station closest to the construction site.

[0255] Furthermore, the step of calculating the matching degree between the specification parameters and the crane matching parameters specifically includes:

[0256] Get the first quantized parameter value pql in the crane matching parameter i and the first non-quantized parameter value pnql j , where i∈[l,n q ],j∈[l,n nq ],n q is the number of quantized parameters in the crane matching parameters, n nq The number of quantized parameters in the crane matching parameters;

[0257] Obtain the first quantization parameter values ​​pql from the specification parameters i and the first non-quantization parameter value pnql j The corresponding second quantization parameter value pq2 i and the second non-quantization parameter value pnq2 j ;

[0258] Calculate the quantized parameter deviation sequence Δp between the specification parameters and the crane matching parameters i and the non-quantized parameter matching sequence σ j ,in:

[0259]

[0260] Based on the quantization parameter deviation sequence Δp i and the non-quantized parameter matching sequence σ j Calculate the matching degree between the specification parameters and the crane matching parameters:

[0261]

[0262] Specifically, the crane matching parameters are a parameter table containing several crane specification parameters, the parameter type of the crane matching parameters is the same as the parameter type of the crane specification parameters, or the parameter type of the crane matching parameters is a subset of the parameter type of the crane specification parameters, that is, each parameter in the crane matching parameters is a specification parameter of the crane.

[0263] It should be known that the crane matching parameters and the specification parameters are also composed of quantified specification parameters and non-quantitative specification parameters, among which the quantified specification parameters include the crane's own weight, power size, main arm length and maximum lifting weight, etc., and the non-quantitative specification parameters are represented by digital codes. Taking the movement mode of the crane as an example, the movement mode of the truck crane can be represented as 1, the movement mode of the crawler crane can be represented as 2, the movement mode of the truck crane can be represented as 3, etc.

[0264] In the technical solution of the above embodiment, the number of parameters in the crane matching parameters is represented as n p , then it satisfies n p =n q +n nq The first quantization parameter value pql i is the i-th quantized parameter in the crane matching parameter, and the second quantized parameter value pq2 i The first quantization parameter value pql i The corresponding specification parameters, that is, when the i value is the same, pql i and pq2 i It is the numerical value of the same quantitative specification parameter of the crane.

[0265] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus comprising the element.

[0266] While embodiments of the present invention have been described above, these embodiments do not exhaustively describe all details and do not limit the invention to the specific embodiments described. Obviously, many modifications and variations are possible based on the above description. These embodiments are selected and described in detail in this specification in order to better explain the principles and practical applications of the present invention, thereby enabling those skilled in the art to better utilize the present invention and its modifications. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. An intelligent self-service crane rental system, characterized in that: Including a self-service crane rental platform, an intelligent analysis engine and a crane management platform; The self-service crane rental platform is configured to receive rental demand information for renting a crane input by a rental user and provide the information to the intelligent analysis engine for analysis; The intelligent analysis engine is configured to intelligently identify the rental demand information to generate formatted demand information corresponding to the rental demand information, convert the formatted demand information into quantified demand information, generate crane matching parameters based on the quantified demand information, and extract task scheduling information from the rental demand information, the task scheduling information including target operation location and target operation time information of the crane in the rental demand information; The crane management platform is configured to execute crane scheduling in response to the rental demand information according to the crane matching parameters and the task scheduling information.

2. An intelligent self-service crane rental method, characterized in that: include: Receiving rental demand information for renting a crane input by a rental user, wherein the rental demand information includes non-formatted text for describing the crane rental demand; Intelligently identifying the rental demand information to generate formatted demand information corresponding to the rental demand information; converting the formatted demand information into quantified demand information; generating crane matching parameters based on the quantified demand information; Extracting task scheduling information from the rental demand information, the task scheduling information including target operation location and target operation time information of the crane in the rental demand information; Crane scheduling for responding to the rental demand information is performed according to the crane matching parameters and the task scheduling information.

3. The intelligent self-service crane rental method according to claim 2 is characterized in that: The steps of intelligently identifying the rental demand information to generate formatted demand information corresponding to the rental demand information specifically include: Obtain pre-configured demand keywords that correspond to each demand dimension; Dividing the rental demand information into a plurality of demand statements; Extract the keywords of each requirement statement; The subject words are matched with the demand keywords to establish a corresponding relationship between the demand statements and the demand dimensions.

4. The intelligent self-service crane rental method according to claim 3 is characterized in that: After the step of matching the subject words with the demand keywords to establish a corresponding relationship between the demand statements and the demand dimensions, the method further includes: Generate a demand dimension list corresponding to the rental demand information, wherein the demand dimension list includes demand dimension names corresponding to the demand statements; Integrate the demand statements corresponding to the same demand dimension in the rental demand information into a demand description text; The formatted requirement information is generated using the requirement dimension name as a key name and the corresponding requirement description text as a key value.

5. The intelligent self-service crane rental method according to claim 3 is characterized in that: The step of converting the formatted demand information into quantified demand information specifically includes: Dividing each demand dimension in the formatted demand information into quantitative demand dimensions and non-quantitative demand dimensions; performing a normalization process on the quantitative requirement dimension to generate a first quantitative requirement; Coding the non-quantitative requirement dimension to generate a second quantitative requirement; The first quantitative requirement and the second quantitative requirement are combined into the quantitative requirement information.

6. The intelligent self-service crane rental method according to claim 5, characterized in that: The step of generating crane matching parameters based on the quantitative demand information specifically includes: generating a demand data sequence based on the quantitative demand information; The demand data sequence is input into a pre-trained crane matching parameter generation model to generate the crane matching parameters.

7. The intelligent self-service crane rental method according to claim 6, characterized in that: Before the step of receiving rental demand information for renting a crane input by a rental user, the method further includes: Configure the sorting number for each requirement dimension; The step of generating a demand data sequence based on the quantitative demand information specifically includes: Generate a null value sequence of a preset length, wherein each numerical element in the null value sequence corresponds to a required dimension according to the sorting number; Each quantized value in the quantized requirement information is filled into a corresponding position in the empty value sequence to generate the requirement data sequence.

8. The intelligent self-service crane rental method according to claim 3 is characterized in that: The step of extracting task scheduling information from the rental demand information specifically includes: Performing semantic recognition on the subject words of each demand statement in the rental demand information to determine whether the subject words of any demand statement are related to the construction location or construction time; When the subject word of any demand sentence is related to the construction site, extracting the construction site information from the demand sentence; When the subject word of any demand sentence is related to the construction time, extracting the construction time information from the demand sentence; The construction location information and / or the construction time information are determined as the task scheduling information.

9. The intelligent self-service crane rental method according to claim 8, characterized in that: The step of executing crane scheduling for responding to the rental demand information according to the crane matching parameters and the task scheduling information specifically includes: generating a crane list matching the task scheduling information; Obtaining specification parameters of each crane in the crane list; Calculating the matching degree between the specification parameters and the crane matching parameters; Determine the crane whose specification parameters are most similar to the crane matching parameters as the target crane; A dispatching task plan for the target crane is generated based on the task scheduling information.

10. The intelligent self-service crane rental method according to claim 9, characterized in that: The step of calculating the matching degree between the specification parameters and the crane matching parameters specifically includes: Get the first quantized parameter value pql in the crane matching parameter i and the first non-quantized parameter value pnql j , where i∈[l,n q ],j∈[l,n nq ],n q is the number of quantized parameters in the crane matching parameters, n nq The number of quantized parameters in the crane matching parameters; Obtain the first quantization parameter values ​​pql from the specification parameters i and the first non-quantization parameter value pnql j The corresponding second quantization parameter value pq2 i and the second non-quantization parameter value pnq2 j ; Calculate the quantized parameter deviation sequence Δp between the specification parameters and the crane matching parameters i and the non-quantized parameter matching sequence σ j ,in: Based on the quantization parameter deviation sequence Δp i and the non-quantized parameter matching sequence σ j Calculate the matching degree between the specification parameters and the crane matching parameters:

Images