A method and system for processing complex quotation orders

Abstract

The present application discloses a method and system for processing complex quotation orders, which have beneficial effects: a data storage structure based on JSONB is adopted, which can store various types of detection parameters and detection times, can easily cope with multi-dimensional parameter changes, and has high scalability and adaptability; a complete data structure is established to facilitate query and processing, which not only improves management efficiency, but also provides convenient support for quotation formulation and order processing; customized according to customer needs and product characteristics, through flexible adjustment of the combination of detection items and times, to provide personalized quotation solutions to meet their specific needs, with broad market prospects; through intelligent algorithms and data management, the detection cost can be effectively controlled and the accuracy of the quotation is improved; comprehensive data support is provided, so that various needs and changes can be efficiently and accurately responded to in the processing of complex quotation orders, and comprehensive data management capabilities are possessed, with obvious advantages.

Description

Technical Field

[0001] The present invention mainly relates to the field of data processing technology, and in particular to a method and system for processing complex quotation orders. Background Art

[0002] In the electrical appliance testing industry, the formulation of testing quotations involves multiple influencing factors, including but not limited to testing standards, testing items, testing parameters, and the number of tests. These factors are intertwined, forming an intricate network of influences. It is precisely because of the diversity and complexity of electrical products and the diversity of testing needs that the quotation formulation process is very difficult and uncertain. Even experienced industry experts sometimes find it difficult to accurately formulate quotations based on the specific needs of customers. Among them, the most important factors affecting the quotation are as follows:

[0003] (1) Testing standards. Different electrical products need to follow different testing standards, which may come from national standards, industry standards or customer-defined standards. For each standard, there are specific testing requirements and procedures, and its influencing factors need to be considered in the quotation.

[0004] (2) Test items and parameters. The test items and parameters of electrical products may cover multiple aspects such as electrical performance, safety performance, and environmental adaptability. The testing of each item and parameter requires corresponding equipment and human resources, which will directly affect the formulation of the quotation.

[0005] (3) Number of tests. This is one of the important factors affecting the quotation. Some electrical products may need to be tested multiple times to ensure that they meet the standards and requirements. Each test will increase the cost, thus affecting the final quotation.

[0006] In general, in the electrical testing industry, there are many challenges and difficulties in the quotation-making process. The existing technical processing methods are not intelligent enough and require a large amount of manual operation. They are highly complex and costly, and accuracy and efficiency cannot be guaranteed.

[0007] Therefore, how to design a highly accurate and efficient order quotation processing method that can adapt to the diversity and complexity of the electrical industry is a technical problem to be solved. Summary of the invention

[0008] Based on this, it is necessary to provide a method and system for processing complex quotation orders to address existing problems.

[0009] In a first aspect, an embodiment of the present application provides a method for processing a complex quotation order, comprising the following steps:

[0010] Obtaining a current quotation order, and determining its order detection information according to the current quotation order;

[0011] Determine the product type corresponding to the current quotation order according to the order detection information;

[0012] Matching the corresponding order inspection standard from the inspection standard library according to the product type;

[0013] Determine the inspection combination corresponding to the current quotation order according to the order inspection standard;

[0014] Perform a preset number of detection parameter matching and deduplication on the detection combination to obtain a detection parameter list set;

[0015] After average calibration is performed on all detection parameter lists of the detection parameter list set, a calibrated detection parameter list is obtained;

[0016] The calibration detection parameter list is input into the pre-trained long short-term memory (LSTM) network to generate a final order quotation.

[0017] Preferably, before obtaining the current quotation order, the detection standard library is first established; the detection standard library is a data storage structure based on JSONB.

[0018] Preferably, the detection standard library is established by the following steps:

[0019] Acquire multiple historical quotation orders for the product to be quoted, and identify the product attribute and attribute value of each of the historical quotation orders;

[0020] Matching the detection criteria of each of the historical quotation orders according to the product attributes and attribute values ​​of each of the historical quotation orders;

[0021] The product attributes and attribute values ​​of all historical quotation orders and their corresponding testing standards constitute the testing standard library.

[0022] Preferably, the long short-term memory (LSTM) network is obtained by:

[0023] Acquire a plurality of historical order data, wherein the plurality of historical order data includes product attributes and attribute values ​​and order quotations of a plurality of historical orders;

[0024] Train an LSTM network based on product attributes and attribute values ​​of the multiple historical orders and order quotations;

[0025] If there is new historical order data, the LSTM network is updated according to the new historical order data and the prediction results obtained by using the LSTM network within a preset time period.

[0026] Preferably, the order testing information includes customer information, product information, sample information and testing requirements.

[0027] Preferably, determining the product type corresponding to the current quotation order according to the order detection information comprises the following steps:

[0028] Extract product type features from the order detection information;

[0029] Perform keyword matching from a pre-stored product type database according to the product type keyword;

[0030] When the matching probability between the product type keyword and the specific product type in the product type database exceeds a preset threshold, the match is successful; otherwise, the above steps are repeated.

[0031] Preferably, determining the detection combination corresponding to the current quotation order according to the order detection standard comprises the following steps:

[0032] According to the terms and test requirements of the order test standard, the test combination of the current quotation order is determined, and the test combination includes test items and required test times.

[0033] Preferably, performing a preset number of detection parameter matching and deduplication on the detection combination to obtain a detection parameter list set comprises the following steps:

[0034] Perform parameter matching and deduplication on each test item of the test combination, so that each dimension of each test item is characterized by a single test parameter;

[0035] Saving the preset detection parameters of each detection item of the detection combination obtained each time to obtain a detection parameter list;

[0036] The above steps are repeated for a preset number of times to obtain the detection parameter list set consisting of the preset number of detection parameter lists.

[0037] Preferably, after averaging and calibrating all detection parameter lists of the detection parameter list set, obtaining a calibrated detection parameter list comprises the following steps:

[0038] Taking an arithmetic average of the parameters of the same dimension in each detection parameter list in the detection parameter list set to obtain an average value of the parameters of the same dimension in the detection parameter list;

[0039] The average value of all dimensional parameters in all detection parameter lists constitutes the calibration detection parameter list.

[0040] In a second aspect, an embodiment of the present application provides a system for processing complex quotation orders, including:

[0041] An acquisition unit, which acquires a current quotation order and determines its order detection information according to the current quotation order;

[0042] A first determining unit, determining a product type corresponding to the current quotation order according to the order detection information;

[0043] A matching unit, matching the order inspection standard corresponding to the inspection standard library according to the product type;

[0044] A second determining unit determines a detection combination corresponding to the current quotation order according to the order detection standard;

[0045] The processing unit performs detection parameter matching and deduplication on the detection combination for a preset number of times to obtain a detection parameter list set;

[0046] A calibration unit, which performs average calibration on all detection parameter lists of the detection parameter list set to obtain a calibrated detection parameter list;

[0047] The generating unit inputs the calibration detection parameter list into a pre-trained long short-term memory (LSTM) network to generate a final order quotation.

[0048] Compared with the prior art, the present invention has the following beneficial effects:

[0049] (1) Flexibility and scalability: The JSONB-based data storage structure can flexibly store various types of detection parameters and their corresponding detection times without the need to define a complex table structure in advance. The present invention can easily cope with multi-dimensional parameter changes in detection items, parameters, and times, thereby making the present invention highly scalable and adaptable.

[0050] (2) High data management efficiency: A complete data structure has been established, including product information, testing standards, testing combinations, testing parameters, etc., to achieve systematic management of key data in the electrical testing industry, which is convenient for efficient query and processing. The present invention not only improves the efficiency of data management, but also provides convenient support for quotation formulation and order processing.

[0051] (3) High integration: It provides services customized to the specific needs of market customers and product characteristics. The present invention can provide customers with personalized quotation plans to meet their specific needs by flexibly adjusting the combination of test items and frequency, thereby improving user satisfaction and competitiveness and having broad market application prospects.

[0052] (4) High reliability: The present invention can quickly and accurately formulate testing quotations through a complete data structure and flexible quotation customization capabilities, and can effectively control testing costs and improve the accuracy and competitiveness of quotations through intelligent algorithms and data management.

[0053] (5) Data comprehensiveness: The present invention provides comprehensive data support, including product information, testing standards, project parameters and other information, so that various demands and changes can be efficiently and accurately responded to in complex quotation order processing. It has comprehensive and detailed data management capabilities, which has obvious advantages over the existing technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] By referring to the following drawings, the exemplary embodiments of the present invention can be more completely understood. The drawings are used to provide a further understanding of the embodiments of the present application, and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present invention and do not constitute a limitation of the present invention. In the drawings, the same reference numerals generally represent the same parts or steps.

[0055] Figure 1 A flowchart of a method for processing a complex quotation order provided according to an exemplary embodiment of the present application;

[0056] Figure 2 A structural schematic diagram of a complex quotation order processing system provided by an exemplary embodiment of the present application is shown. DETAILED DESCRIPTION

[0057] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0058] In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and "third" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance.

[0059] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0060] In addition, the technical features involved in the different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0061] An embodiment of the present application provides a data persistence method for an online debugging platform of a projection device, which is described below in conjunction with the accompanying drawings.

[0062] Reference Figure 1 , which shows a method for processing a complex quotation order provided by some embodiments of the present application, comprising the following steps:

[0063] S101: Obtain the current quotation order, and determine its order detection information according to the current quotation order;

[0064] Specifically, before obtaining the current quotation order, a detection standard library is first established; the detection standard library is a data storage structure based on JSONB.

[0065] Specifically, JSONB (JSON with Binary Data) is a binary format for storing JSON data. It is an extension of the JSON type, designed specifically for processing binary data, especially when large objects or complex structures need to be stored. JSONB provides the following key features based on JSON:

[0066] Binary format: JSONB stores JSON data in binary format, which helps reduce storage space requirements and improves the efficiency of I / O operations.

[0067] Self-descriptive: The data stored in the JSONB data type contains information about the data structure, which means that the database itself knows the data type of the value corresponding to each key, which is a manifestation of self-descriptiveness.

[0068] Support for complex data structures: JSONB allows the storage of nested JSON objects, which makes it possible to represent complex data structures such as tabular data, object arrays, etc.

[0069] Optimized storage and query: JSONB optimizes the storage of JSON data, reduces duplicate key-value pairs, and can use the database's built-in functions and indexes to quickly retrieve data when querying.

[0070] Integrated SQL support: JSONB is tightly integrated with SQL, and you can use the SQL query language to retrieve and manipulate JSON data, including complex queries such as nested queries, key path queries, etc.

[0071] Performance improvement: Compared to JSON in text format, JSONB generally has better performance when storing and querying because it reduces the need for text parsing and can operate directly on binary data.

[0072] Specifically, in this embodiment, the establishment of the standard library is based on the following principles: (1) Comprehensiveness: covering all relevant national standards, industry standards and special standards; (2) Accuracy: the accuracy of standard information is crucial and it is updated regularly to reflect the latest changes in testing regulations; (3) Ease of use: providing maintenance functions to facilitate user understanding and use, such as through classification and search functions; (4) Consistency: a unified interface to ensure the consistency of application of standards at different times and between different users.

[0073] Specifically, the standard library is established in the following way:

[0074] Obtain multiple historical quotation orders for the product being quoted, and identify the product attributes and attribute values ​​of each historical quotation order;

[0075] Match the detection criteria of each historical quotation order according to the product attributes and attribute values ​​of each historical quotation order;

[0076] The product attributes and attribute values ​​of all historical quotation orders and their corresponding testing standards constitute the testing standard library.

[0077] In this embodiment, the product attributes specifically include: according to the dimensions of the type of electrical product, market requirements, standard requirements, product use, etc. The attribute value is the specific numerical value corresponding to the attribute or a representative value customized in the early stage according to the needs.

[0078] At the same time, due to the differences in versions, different versions of standards can also be tracked according to the versions used, and their validity periods and historical versions used can be marked.

[0079] S102: Determine the product type corresponding to the current quotation order according to the order detection information;

[0080] In this embodiment, the order testing information includes customer information, product information, sample information and testing requirements. Step S102 specifically includes:

[0081] Extract product type features from order detection information;

[0082] Perform keyword matching from a pre-stored product type database based on product type keywords;

[0083] When the matching probability between the product type keyword and the specific product type in the product type database exceeds a preset threshold, the match is successful; otherwise, the above steps are repeated.

[0084] Specifically, text matching or processing can utilize natural language processing technology to extract key information from the standard text, such as standard number, scope of application, standard qualification, release date, scope of application, etc.

[0085] S103: Matching the corresponding order inspection standard from the inspection standard library according to the product type;

[0086] S104: Determine the inspection combination corresponding to the current quotation order according to the order inspection standard;

[0087] Specifically, in this embodiment, according to the terms and test requirements of the order test standard, the test combination of the current quotation order is determined, and the test combination includes test items and the number of test requirements. Specifically, test items and test combinations: according to the test standard selected by the user, the system displays the test items or test combinations in the set sorting order. The test combination is a user-preset combination based on the test standard. The user selects the test items or test combinations according to the quotation requirements.

[0088] S105: performing a preset number of detection parameter matching and deduplication on the detection combination to obtain a detection parameter list set;

[0089] Specifically, step S105 includes:

[0090] Perform parameter matching and deduplication on each test item of the test combination, so that each dimension of each test item is represented by a single test parameter;

[0091] Save the preset detection parameters of each detection item of each detection combination obtained each time, and obtain a detection parameter list;

[0092] The above steps are repeated for a preset number of times to obtain the detection parameter list set consisting of the preset number of detection parameter lists.

[0093] The preset number of times can be customized according to the calculation accuracy, for example, set to 100 times, or 1000 times, and can be set based on experience as long as it is reasonable.

[0094] S106: After average calibration of all detection parameter lists in the detection parameter list set, a calibrated detection parameter list is obtained;

[0095] Specifically, step S106 includes:

[0096] Perform arithmetic averaging on the parameters of the same dimension in each detection parameter list in the detection parameter list set to obtain the average value of the parameters of the same dimension in the detection parameter list;

[0097] The average value of all dimension parameters in all detection parameter lists constitutes the calibration detection parameter list.

[0098] Specifically, arithmetic mean generally refers to finding the average value. For example, there are 10 parameter lists in the parameter list set, and the same dimension parameter detection times exist in each list. The detection times of 5 tables are 10, the detection times of 3 tables are 20, and the detection times of 2 tables are 50. Then after arithmetic averaging, the detection times in the calibration detection parameter list is (5*10+3*20+2*50) / 10=21.

[0099] S107: Input the calibration detection parameter list into the pre-trained long short-term memory (LSTM) network to generate a final order quotation.

[0100] Specifically, step S107 includes:

[0101] Acquire multiple historical order data, where the multiple historical order data include product attributes and attribute values ​​and order quotations of multiple historical orders;

[0102] The LSTM network is trained based on the product attributes and attribute values ​​of multiple historical orders and order quotations;

[0103] In this embodiment, product attributes and attribute values ​​may change over time, so this embodiment adopts the LSTM algorithm to train and obtain an LSTM network.

[0104] If there is new historical order data, the LSTM network is updated based on the new historical order data and the prediction results obtained using the LSTM network within the preset time period.

[0105] In this embodiment, the LSTM algorithm is used to process important events with relatively long intervals and delays in the time series. Due to the large number of projects, the time interval can be set to one quarter (three months).

[0106] For example, a base model is first trained based on the historical order data of the first quarter of 2020, that is, the LSTM network of the first quarter; then, when the LSTM network is trained based on the historical order data of the second quarter of 2020, the prediction results obtained by using the LSTM network of the first quarter are used as a reference. For the third quarter of 2023, its predicted price L will be affected by the previous quarterly models, with the most recent quarter (the second quarter of 2023) having the greatest impact.

[0107] The embodiment of the present invention predicts the quotation of the current order according to the product attributes and attribute values ​​of the current quotation order, using an LSTM network pre-trained according to historical order data, so as to obtain the most appropriate quotation, which can improve the accuracy and work efficiency of order quotation.

[0108] Compared with the prior art, the present invention has the following beneficial effects:

[0109] (1) Flexibility and scalability: The JSONB-based data storage structure can flexibly store various types of detection parameters and their corresponding detection times without the need to define a complex table structure in advance. The present invention can easily cope with multi-dimensional parameter changes in detection items, parameters, and times, thereby making the present invention highly scalable and adaptable.

[0110] (2) High data management efficiency: A complete data structure has been established, including product information, testing standards, testing combinations, testing parameters, etc., to achieve systematic management of key data in the electrical testing industry, which is convenient for efficient query and processing. The present invention not only improves the efficiency of data management, but also provides convenient support for quotation formulation and order processing.

[0111] (3) High integration: It provides services customized to the specific needs of market customers and product characteristics. The present invention can provide customers with personalized quotation plans to meet their specific needs by flexibly adjusting the combination of test items and frequency, thereby improving user satisfaction and competitiveness and having broad market application prospects.

[0112] (4) High reliability: The present invention can quickly and accurately formulate testing quotations through a complete data structure and flexible quotation customization capabilities, and can effectively control testing costs and improve the accuracy and competitiveness of quotations through intelligent algorithms and data management.

[0113] (5) Data comprehensiveness: The present invention provides comprehensive data support, including product information, testing standards, project parameters and other information, so that various demands and changes can be efficiently and accurately responded to in complex quotation order processing. It has comprehensive and detailed data management capabilities, which has obvious advantages over the existing technology.

[0114] In the above embodiment, a method is provided, and correspondingly, the present application also provides a system. The system provided in the embodiment of the present application can implement the above method, and the system can be implemented by software, hardware, or a combination of software and hardware. For example, the system may include integrated or separate functional modules or units to perform the corresponding steps in the above methods.

[0115] In some implementations of the embodiments of the present application, the system 20 provided in the embodiments of the present application is based on the same inventive concept as the method provided in the aforementioned embodiments of the present application and has the same beneficial effects.

[0116] like Figure 2 As shown, the system 20 may include:

[0117] The acquisition unit 201 acquires the current quotation order and determines its order detection information according to the current quotation order;

[0118] A first determining unit 202 determines the product type corresponding to the current quotation order according to the order detection information;

[0119] A matching unit 203 matches the order inspection standard corresponding to the inspection standard library according to the product type;

[0120] A second determining unit 204 determines a detection combination corresponding to the current quotation order according to the order detection standard;

[0121] The processing unit 205 performs a preset number of detection parameter matching and deduplication on the detection combination to obtain a detection parameter list set;

[0122] A calibration unit 206 performs average calibration on all detection parameter lists of the detection parameter list set to obtain a calibrated detection parameter list;

[0123] The generating unit 207 inputs the calibration detection parameter list into a pre-trained long short-term memory (LSTM) network to generate a final order quotation.

[0124] It should be noted that the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0125] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0126] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0127] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0128] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0129] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0130] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application, and they should all be included in the scope of the claims and specification of the present application.

Claims

1. A method for processing a complex quotation order, characterized in that: The steps include: Obtaining a current quotation order, and determining its order detection information according to the current quotation order; Determine the product type corresponding to the current quotation order according to the order detection information; Matching the corresponding order inspection standard from the inspection standard library according to the product type; Determine the inspection combination corresponding to the current quotation order according to the order inspection standard; Perform a preset number of detection parameter matching and deduplication on the detection combination to obtain a detection parameter list set; After average calibration is performed on all detection parameter lists of the detection parameter list set, a calibrated detection parameter list is obtained; Input the calibration detection parameter list into the pre-trained long short-term memory (LSTM) network to generate a final order quotation; Before obtaining the current quotation order, the detection standard library is first established; the detection standard library is based on the data storage structure of JSONB; Wherein, the detection standard library is established through the following steps: Acquire multiple historical quotation orders for the product to be quoted, and identify the product attribute and attribute value of each of the historical quotation orders; Matching the detection criteria of each of the historical quotation orders according to the product attributes and attribute values ​​of each of the historical quotation orders; The product attributes and attribute values ​​of all historical quotation orders and their corresponding testing standards constitute the testing standard library; Determining the detection combination corresponding to the current quotation order according to the order detection standard includes the following steps: Determine the testing combination of the current quotation order according to the terms and testing requirements of the order testing standards, wherein the testing combination includes testing items and required testing times; Wherein, determining the detection combination corresponding to the current quotation order according to the order detection standard includes: The method of performing a preset number of detection parameter matching and deduplication on the detection combination to obtain a detection parameter list set includes the following steps: Perform parameter matching and deduplication on each test item of the test combination, so that each dimension of each test item is characterized by a single test parameter; Saving the preset detection parameters of each detection item of the detection combination obtained each time to obtain a detection parameter list; Repeat the above steps for a preset number of times to obtain the detection parameter list set consisting of the preset number of detection parameter lists; The step of obtaining a calibrated detection parameter list after averaging all detection parameter lists of the detection parameter list set comprises the following steps: Taking an arithmetic average of the parameters of the same dimension in each detection parameter list in the detection parameter list set to obtain an average value of the parameters of the same dimension in the detection parameter list; The average value of all dimensional parameters in all detection parameter lists constitutes the calibration detection parameter list.

2. A method for processing a complex quotation order according to claim 1, characterized in that: The long short-term memory LSTM network is obtained by: Acquire a plurality of historical order data, wherein the plurality of historical order data includes product attributes and attribute values ​​and order quotations of a plurality of historical orders; Train an LSTM network based on product attributes and attribute values ​​of the multiple historical orders and order quotations; If there is new historical order data, the LSTM network is updated according to the new historical order data and the prediction results obtained by using the LSTM network within a preset time period.

3. A method for processing a complex quotation order according to claim 2, characterized in that: The order testing information includes customer information, product information, sample information and testing requirements.

4. A method for processing a complex quotation order according to claim 3, characterized in that: Determining the product type corresponding to the current quotation order according to the order detection information includes: Extract product type features from the order detection information; Perform keyword matching from a pre-stored product type database according to the product type keyword; When the matching probability between the product type keyword and the specific product type in the product type database exceeds a preset threshold, the match is successful; otherwise, the above steps are repeated.

5. A system for processing complex quotation orders, characterized in that: include: An acquisition unit, which acquires a current quotation order and determines its order detection information according to the current quotation order; A first determining unit, determining a product type corresponding to the current quotation order according to the order detection information; A matching unit, matching the order inspection standard corresponding to the inspection standard library according to the product type; A second determining unit determines a detection combination corresponding to the current quotation order according to the order detection standard; The processing unit performs detection parameter matching and deduplication on the detection combination for a preset number of times to obtain a detection parameter list set; A calibration unit, which performs average calibration on all detection parameter lists of the detection parameter list set to obtain a calibrated detection parameter list; A generating unit, inputting the calibration detection parameter list into a pre-trained long short-term memory (LSTM) network to generate a final order quotation; Before obtaining the current quotation order, the detection standard library is first established; the detection standard library is based on the data storage structure of JSONB; Wherein, the detection standard library is established through the following steps: Acquire multiple historical quotation orders for the product to be quoted, and identify the product attribute and attribute value of each of the historical quotation orders; Matching the detection criteria of each of the historical quotation orders according to the product attributes and attribute values ​​of each of the historical quotation orders; The product attributes and attribute values ​​of all historical quotation orders and their corresponding testing standards constitute the testing standard library; Determining the detection combination corresponding to the current quotation order according to the order detection standard includes the following steps: Determine the testing combination of the current quotation order according to the terms and testing requirements of the order testing standards, wherein the testing combination includes testing items and required testing times; Wherein, determining the detection combination corresponding to the current quotation order according to the order detection standard includes: The method of performing a preset number of detection parameter matching and deduplication on the detection combination to obtain a detection parameter list set includes the following steps: Perform parameter matching and deduplication on each test item of the test combination, so that each dimension of each test item is characterized by a single test parameter; Saving the preset detection parameters of each detection item of the detection combination obtained each time to obtain a detection parameter list; Repeat the above steps for a preset number of times to obtain the detection parameter list set consisting of the preset number of detection parameter lists; The step of obtaining a calibrated detection parameter list after averaging all detection parameter lists of the detection parameter list set comprises the following steps: Taking an arithmetic average of the parameters of the same dimension in each detection parameter list in the detection parameter list set to obtain an average value of the parameters of the same dimension in the detection parameter list; The average value of all dimensional parameters in all detection parameter lists constitutes the calibration detection parameter list.

Images