A method and device for improving supply chain efficiency based on big data

Abstract

The present invention relates to the field of data processing technology, and in particular to a method and device for improving supply chain efficiency based on big data, detecting supply data provided by a customer intention platform, processing the supply data, and obtaining the customer's transaction intention and supply chain scenario; comparing the best simulated transaction object in a knowledge base according to the transaction intention, and deciding a transaction security channel according to the supply chain scenario, and replying the best simulated transaction object to the customer intention platform through the transaction security channel; detecting the response data obtained by the customer based on the reply in real time, and applying the response data, predicting the simulated transaction object and the simulated transaction channel in real time; calling the real-time predicted simulated transaction object and the simulated transaction channel, and sharing and publishing the call record in a multi-source supply chain. The present invention can provide a more efficient, safe and reliable transaction environment to both supply and demand parties, comprehensively protect the rights and interests of both parties, and ensure the sustainable development of the transaction supply chain.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method and device for improving supply chain efficiency based on big data. Background Art

[0002] At present, the popularization of supply chain financial services has provided social enterprises or individuals with more trading options for metal-related services. Supply chain financial services include providing transactions of many financial targets and evaluation services for buyers and sellers. Suppliers can display the trading targets they provide through relevant trading platforms, and demanders can also choose suitable targets on the platform for trading.

[0003] However, the current financial trading platform also has shortcomings and deficiencies. For example, there are many branches in the supply chain, and the security of the trading channels cannot be guaranteed. Therefore, it is necessary to build a more fair, efficient and secure trading supply chain system. A good trading supply chain system should be able to provide a more efficient, secure and reliable trading environment for both supply and demand parties, comprehensively protect the rights and interests of both parties, and also ensure the sustainable development of the trading supply chain. Summary of the invention

[0004] To achieve the above object, the present invention provides the following technical solutions:

[0005] According to a first aspect of the present invention, the present invention claims protection for a supply chain efficiency improvement device based on big data, comprising:

[0006] The supply data processing unit detects the supply data provided by the customer intention platform and processes the supply data to obtain the customer's transaction intention and supply chain scenario;

[0007] The simulation unit compares the best simulated transaction object in the knowledge base according to the transaction intention, decides the transaction security channel according to the supply chain scenario, and replies to the customer intention platform through the transaction security channel to obtain the best simulated transaction object;

[0008] The application prediction unit detects the response data obtained by the customer based on the reply in real time, and applies the response data to predict the simulated transaction object and simulated transaction channel in real time;

[0009] The shared publishing unit calls the real-time prediction simulation transaction object and the simulation transaction channel, and publishes the call record in a multi-source supply chain sharing manner.

[0010] Further, a data processing unit is provided, comprising:

[0011] A data source providing unit accesses the session window according to the customer intent platform and presents the supply data provided by the customer intent platform in the session window;

[0012] A first supply data processing unit processes the supply data to obtain branch supply data;

[0013] The second supply data processing unit identifies and analyzes the branch supply data to obtain the customer's transaction intention and supply chain scenario.

[0014] Further, a data processing unit is provided, comprising:

[0015] The data detection submodule detects the supply data and determines the transaction instruction information associated with the supply data;

[0016] The instruction information processing submodule performs standardization processing on the transaction instruction information to obtain the first transaction instruction information, and at the same time, performs segmentation processing on the first transaction instruction information and extracts the instruction segment of the voice transaction instruction according to the processing record;

[0017] The algorithm configuration submodule applies the instruction segment of the voice trading instruction, determines the reference cutting features of the instruction segment of the voice trading instruction, and configures the invalid trading instruction recognition algorithm through the reference cutting features of the instruction segment of the voice trading instruction;

[0018] Instruction filtering submodule:

[0019] Providing the first transaction instruction information to the transaction instruction invalidation identification algorithm for cutting feature identification, backing up the transaction instruction information in the first transaction instruction information that is inconsistent with the reference cutting feature through identification records, and determining the abnormal transaction instruction segment through the backup records;

[0020] The invalid instructions associated with the abnormal transaction instruction segment are screened to obtain second transaction instruction information, wherein the second transaction instruction information is the branch supply data.

[0021] Further, a data processing unit is provided, comprising:

[0022] The transaction string adjustment submodule detects the branch supply data, adjusts the branch supply data into a string description, and divides the string description into a plurality of substring descriptions by a pause mark of the string description in the string description;

[0023] The key sentence processing submodule collects the key sentences of the substring description, and corresponds the key sentences of each substring description to the uninterrupted feature space, and obtains the features of the key sentences in each substring description through the corresponding records;

[0024] The keyword feature decision submodule calculates the first keyword relationship between the key sentences in each substring description based on the features of the key sentences in each substring description, and decides the keyword features of each substring description;

[0025] The transaction intention collection submodule determines the second keyword relationship between each substring description through the keyword features of each substring description, and determines the customer's transaction intention through the second keyword relationship;

[0026] The supply chain scenario decision submodule provides the customer's transaction intention and branch supply data to the preset supply chain identification algorithm for processing, and obtains the customer's supply chain scenario based on the processing records.

[0027] Furthermore, the simulation unit comprises:

[0028] Transaction details comparison unit:

[0029] Collect the acquired transaction intentions and adjust the transaction intentions into transaction strings;

[0030] Segment and feature annotate transaction strings based on natural language parsing solutions, and extract entity data from transaction strings and focus on executing transaction behaviors based on segmentation and feature annotation records;

[0031] According to the entity data, the historical key executed transaction behaviors in the transaction string are string-associated, and the decision transaction intention and intent are recorded according to the string association, and the knowledge base is traversed according to the transaction intention and intent to obtain the best simulation transaction object;

[0032] Response Unit:

[0033] Analyze the supply chain scenarios to determine the customer's current supply chain preference and supply chain strength, and determine the customer's supply chain scenario category based on the supply chain preference. At the same time, determine the trust index of the customer's supply chain preference based on the supply chain strength.

[0034] According to the supply chain scenario category and trust index, the target transaction security channel is retrieved from the preset strategy library, and the best simulated transaction object is responded to the customer intention platform based on the target transaction security channel;

[0035] The prediction unit reviews the customer's real-time supply chain scenario based on the response acquisition record, and determines the change characteristics of the customer's supply chain scenario based on the review record, and updates and adjusts the target transaction security channel based on the supply chain change characteristics;

[0036] Packaging and logging unit:

[0037] Collect the full simulation data transaction details of the customer over time according to the update adjustment record, and perform multi-source encapsulation of the full simulation data transaction details according to the multi-category encapsulation key;

[0038] Log cache is performed on the full simulation data after multi-source packaging, and the log cache records are backed up according to customer identity.

[0039] Furthermore, the prediction unit comprises:

[0040] The record collection submodule collects the customer's supply chain scenario and supply chain change characteristics. When the customer's supply chain scenario is an unfamiliar scenario, the dynamic trend and dynamic quantity of the customer's supply chain are determined based on the supply chain change characteristics.

[0041] The transaction details decision submodule decides the timing of supply chain planning intervention, supply chain planning direction and supply chain planning transaction details based on supply chain dynamic trends and supply chain dynamic quantities;

[0042] The planning submodule conducts supply chain scenario planning for customers based on the timing of supply chain planning intervention, supply chain planning direction and supply chain planning transaction details, and responds based on the simultaneous updates of the supply chain scenario planning.

[0043] Furthermore, a prediction unit is applied, comprising:

[0044] The data capture unit collects response data of different customers according to the reply acquisition records, and performs clustering processing on the response data to obtain a multi-branch sub-response instruction set;

[0045] The risk decision unit predicts each sub-response instruction set in the multiple branch sub-response instruction sets according to the prediction index, obtains the operation effect of each branch, and makes a decision on the prediction task according to the difference between the operation effect of each branch and the preset reference condition;

[0046] Prediction Unit:

[0047] The important coefficients of each branch are determined based on the supply chain scenario simulation mechanism, and the response data is cyclically applied based on the important coefficients and prediction tasks;

[0048] Make real-time predictions on simulated transaction objects and simulated transaction channels based on cyclic application records.

[0049] Furthermore, the shared publishing unit includes:

[0050] Calling unit:

[0051] Collect real-time forecast records of simulated transaction objects and simulated transaction channels, and obtain supply chain scenario simulation mechanisms based on real-time forecast records;

[0052] The supply chain scenario simulation mechanism is called as a page string according to the execution page, and a data update interface is reserved for the page content to obtain the shareable execution content;

[0053] Supply chain sharing unit:

[0054] The shared environment of the shareable executable content is published in multiple categories according to the operating conditions of multiple sources, and the shared supply chain of the shareable executable content is opened according to the multi-category publication records;

[0055] Share and apply sharable executable content across multiple sources based on open records.

[0056] Furthermore, the risk decision unit includes:

[0057] The sub-response instruction set detection sub-module detects the sub-response instruction set associated with each branch, and collects the important coefficients associated with each branch. At the same time, the response value of the reply record is calculated through the sub-response instruction set associated with each branch and the important coefficients associated with each branch, and the response value is used to determine whether to make real-time predictions on the simulated transaction objects and simulated transaction channels, including:

[0058] First parsing module:

[0059] Detecting the sub-response instruction set associated with each branch, and detecting the important coefficient associated with each branch;

[0060] The response value of the record is obtained by calculating the reply through the sub-response instruction set associated with each branch and the importance coefficient associated with each branch;

[0061] ;

[0062] in, Get the recorded response value for the reply; is the branch sequence number value; is the total number of branches; is the sequence number value of the sub-response data in the sub-response instruction set under the i-th branch; is the total number of sub-response instruction sets under the i-th branch; is the jth sub-response data value under the i-th branch; is the important coefficient of the i-th branch; is the fault tolerance coefficient of the i-th branch, and its value range is (0, 1); is a constant, and its value range is ;

[0063] The second analysis module determines whether the response value performs real-time prediction on the simulated transaction object and the simulated transaction channel through the following formula;

[0064] ;

[0065] in, is the preset response threshold; To judge the value, that is:

[0066] if =a, it is determined that no real-time prediction will be performed on the simulated transaction object and simulated transaction channel;

[0067] if = b, it is determined to be informed;

[0068] if =c, it is determined to make real-time predictions on the simulated transaction objects and simulated transaction channels.

[0069] According to a second aspect of the present invention, the present invention claims protection for a method for improving supply chain efficiency based on big data, which is applied to the device for improving supply chain efficiency based on big data, comprising:

[0070] Step 1: Detect the supply data provided by the customer intention platform and process the supply data to obtain the customer's transaction intention and supply chain scenario;

[0071] Step 2: Compare the best simulated transaction object in the knowledge base based on the transaction intention, decide on the transaction security channel based on the supply chain scenario, and reply to the customer intention platform through the transaction security channel to obtain the best simulated transaction object;

[0072] Step 3: Real-time detection of response data obtained by the customer based on the reply, and application of the response data to predict the simulated transaction object and simulated transaction channel in real time;

[0073] Step 4: Call the real-time prediction simulation transaction object and the simulation transaction channel, and publish the call record for multi-source supply chain sharing.

[0074] The present invention relates to the field of data processing technology, and in particular to a method and device for improving supply chain efficiency based on big data, detecting supply data provided by a customer intention platform, processing the supply data, and obtaining the customer's transaction intention and supply chain scenario; comparing the best simulated transaction object in a knowledge base according to the transaction intention, and deciding a transaction security channel according to the supply chain scenario, and replying the best simulated transaction object to the customer intention platform through the transaction security channel; detecting the response data obtained by the customer based on the reply in real time, and applying the response data, predicting the simulated transaction object and the simulated transaction channel in real time; calling the real-time predicted simulated transaction object and the simulated transaction channel, and sharing and publishing the call record in a multi-source supply chain. The present invention can provide a more efficient, safe and reliable transaction environment to both supply and demand parties, comprehensively protect the rights and interests of both parties, and ensure the sustainable development of the transaction supply chain. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] Figure 1 A structural module diagram of a supply chain efficiency improvement device based on big data claimed in an embodiment of the present invention;

[0076] Figure 2 A second structural module diagram of a supply chain efficiency improvement device based on big data as claimed in an embodiment of the present invention;

[0077] Figure 3 A workflow diagram of a method for improving supply chain efficiency based on big data as claimed in an embodiment of the present invention. DETAILED DESCRIPTION

[0078] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. According to the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0079] The terms "first", "second" and "third" in the present invention are only for illustrative purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features. Therefore, the features defined as "first", "second" and "third" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "multiple" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined. All directional indications (such as up, down, left, right, front, back...) in the embodiments of the present invention only explain the relative position relationship, movement, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture is dynamic, the directional indication is also dynamic accordingly. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, device, product or equipment that includes a series of steps or units is not limited to the listed steps or units, but optionally also includes steps or units that are not listed, or optionally also includes other steps or units inherent to these processes, methods, products or equipment.

[0080] Reference to an "embodiment" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiment may be included in at least one embodiment of the present invention. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0081] Example 1

[0082] A supply chain efficiency improvement device based on big data, such as Figure 1 As shown, including:

[0083] The supply data processing unit detects the supply data provided by the customer intention platform and processes the supply data to obtain the customer's transaction intention and supply chain scenario;

[0084] The simulation unit compares the best simulated transaction object in the knowledge base according to the transaction intention, decides the transaction security channel according to the supply chain scenario, and replies to the customer intention platform through the transaction security channel to obtain the best simulated transaction object;

[0085] The application prediction unit detects the response data obtained by the customer based on the reply in real time, and applies the response data to predict the simulated transaction object and simulated transaction channel in real time;

[0086] The shared publishing unit calls the real-time prediction simulation transaction object and the simulation transaction channel, and publishes the call record in a multi-source supply chain sharing manner.

[0087] In this specific implementation, the supply data may be transaction data provided by the platform based on customer intent.

[0088] In this specific implementation method, the transaction intention is the customer's transaction goal, and the supply chain scenario may include the customer's: first-time supply chain entity and business, multiple supply chain entities and businesses, multiple supply chain entities' new supply chain business, and new supply chain entities' multiple supply chain businesses.

[0089] In this specific implementation method, the supply data is processed based on a large algorithm to process natural data sources, thereby obtaining transaction intentions and supply chain scenarios.

[0090] In this specific implementation, the response data may be multi-dimensional responses including but not limited to customer satisfaction with the transaction, transaction response rate, and transaction response accuracy.

[0091] Embodiment 2:

[0092] Based on Example 1, this example provides a supply chain efficiency improvement device based on big data, such as Figure 2 As shown, the data processing unit is supplied, including:

[0093] A data source providing unit accesses the session window according to the customer intent platform and presents the supply data provided by the customer intent platform in the session window;

[0094] A first supply data processing unit processes the supply data to obtain branch supply data;

[0095] The second supply data processing unit identifies and analyzes the branch supply data to obtain the customer's transaction intention and supply chain scenario.

[0096] In this specific implementation, the data processing for the supply data may be a screening process such as denoising the supply data, thereby obtaining the branch supply data, thereby ensuring the accuracy of identifying the branch supply data.

[0097] The working principle and beneficial effects of the above technical solution are: accessing the session window through the customer intention platform, and effectively detecting the supply data in the session window, and processing the supply data so that the obtained branch supply data can be made more accurate, thereby ensuring the accuracy of identifying the branch supply data, thereby improving the accuracy of obtaining the customer's transaction intentions and supply chain scenarios.

[0098] Embodiment 3:

[0099] Based on Example 2, this embodiment provides a supply chain efficiency improvement device based on big data, and a supply data processing unit includes:

[0100] The data detection submodule detects the supply data and determines the transaction instruction information associated with the supply data;

[0101] The instruction information processing submodule performs standardization processing on the transaction instruction information to obtain the first transaction instruction information, and at the same time, performs segmentation processing on the first transaction instruction information and extracts the instruction segment of the voice transaction instruction according to the processing record;

[0102] The algorithm configuration submodule applies the instruction segment of the voice trading instruction, determines the reference cutting features of the instruction segment of the voice trading instruction, and configures the invalid trading instruction recognition algorithm through the reference cutting features of the instruction segment of the voice trading instruction;

[0103] Instruction filtering submodule:

[0104] Providing the first transaction instruction information to the transaction instruction invalidation identification algorithm for cutting feature identification, backing up the transaction instruction information in the first transaction instruction information that is inconsistent with the reference cutting feature through identification records, and determining the abnormal transaction instruction segment through the backup records;

[0105] The invalid instructions associated with the abnormal transaction instruction segment are screened to obtain second transaction instruction information, wherein the second transaction instruction information is the branch supply data.

[0106] In this specific implementation method, the reference cutting feature can be the cutting feature of the instruction segment obtained after identifying the voice transaction instruction, which is used to implement the configuration of the invalid transaction instruction recognition algorithm. The invalid transaction instruction recognition algorithm is used to identify the first transaction instruction information and back up and extract the transaction instruction information in the first transaction instruction information that is inconsistent with the reference cutting feature.

[0107] In this specific implementation manner, the first transaction instruction information may be obtained by standardizing the transaction instruction information.

[0108] In this specific implementation manner, the second transaction instruction information may be transaction instruction information obtained after invalidating the first transaction instruction information.

[0109] In this specific implementation method, the second transaction instruction information is the branch supply data.

[0110] The working principle and beneficial effects of the above technical solution are: by standardizing the transaction instruction information, the first transaction instruction information is obtained, thereby laying the foundation for denoising the first transaction instruction information, and by configuring the invalid transaction instruction identification algorithm, the abnormal transaction instruction segment of the first transaction instruction information can be identified, and the invalid instructions can be effectively screened through the identification records, and then the second transaction instruction information, namely the branch supply data, is obtained, which improves the intelligence of the transaction instruction denoising and, at the same time, ensures the accuracy of identifying the branch supply data.

[0111] Embodiment 4:

[0112] Based on Example 2, this embodiment provides a supply chain efficiency improvement device based on big data, and a supply data processing unit includes:

[0113] The transaction string adjustment submodule detects the branch supply data, adjusts the branch supply data into a string description, and divides the string description into a plurality of substring descriptions by a pause mark of the string description in the string description;

[0114] The key sentence processing submodule collects the key sentences of the substring description, and corresponds the key sentences of each substring description to the uninterrupted feature space, and obtains the features of the key sentences in each substring description through the corresponding records;

[0115] The keyword feature decision submodule calculates the first keyword relationship between the key sentences in each substring description based on the features of the key sentences in each substring description, and decides the keyword features of each substring description;

[0116] The transaction intention collection submodule determines the second keyword relationship between each substring description through the keyword features of each substring description, and determines the customer's transaction intention through the second keyword relationship;

[0117] The supply chain scenario decision submodule provides the customer's transaction intention and branch supply data to the preset supply chain identification algorithm for processing, and obtains the customer's supply chain scenario based on the processing records.

[0118] The working principle and beneficial effects of the above technical solution are: by determining the key sentences in the substring description and performing feature space correspondence, the features of the key sentences in the substring description can be effectively obtained, the first keyword relationship between the key sentences in each substring description can be determined, and then the keyword features of each substring description can be effectively determined, so that the second keyword relationship between each substring description is determined through the keyword features of each substring description, and the customer's transaction intention is effectively determined through the second keyword relationship, thereby improving the accuracy and effectiveness of obtaining the customer's transaction intention.

[0119] Embodiment 5:

[0120] Based on Example 1, this embodiment provides a supply chain efficiency improvement device based on big data, and the simulation unit includes:

[0121] Transaction details comparison unit:

[0122] Collect the acquired transaction intentions and adjust the transaction intentions into transaction strings;

[0123] Segment and feature annotate transaction strings based on natural language parsing solutions, and extract entity data from transaction strings and focus on executing transaction behaviors based on segmentation and feature annotation records;

[0124] According to the entity data, the historical key executed transaction behaviors in the transaction string are string-associated, and the decision transaction intention and intent are recorded according to the string association, and the knowledge base is traversed according to the transaction intention and intent to obtain the best simulation transaction object;

[0125] Response Unit:

[0126] Analyze the supply chain scenarios to determine the customer's current supply chain preference and supply chain strength, and determine the customer's supply chain scenario category based on the supply chain preference. At the same time, determine the trust index of the customer's supply chain preference based on the supply chain strength.

[0127] According to the supply chain scenario category and trust index, the target transaction security channel is retrieved from the preset strategy library, and the best simulated transaction object is responded to the customer intention platform based on the target transaction security channel;

[0128] The prediction unit reviews the customer's real-time supply chain scenario based on the response acquisition record, and determines the change characteristics of the customer's supply chain scenario based on the review record, and updates and adjusts the target transaction security channel based on the supply chain change characteristics;

[0129] Packaging and logging unit:

[0130] Collect the full simulation data transaction details of the customer over time according to the update adjustment record, and perform multi-source encapsulation of the full simulation data transaction details according to the multi-category encapsulation key;

[0131] Log cache is performed on the full simulation data after multi-source packaging, and the log cache records are backed up according to customer identity.

[0132] The working principle and beneficial effects of the above technical solution are: by parsing the acquired transaction intentions, accurate and effective decisions can be made on the customer's transaction intentions and intentions, so that the best simulated transaction objects can be compared from the knowledge base through the transaction intentions and intentions, ensuring the accuracy and reliability of the responses to customers. Secondly, the customer's supply chain scenario is parsed to lock the customer's supply chain tendency and supply chain strength, which is also convenient for deciding the customer's transaction security channel through the supply chain tendency and supply chain strength, and the best simulated transaction object is obtained through the transaction security channel to the customer intention platform, satisfying the customer's supply chain response intention. Finally, the customer's real-time supply chain scenario is reviewed, and the customer's transaction security channel is updated and adjusted through the review records, ensuring that the transaction details and supply chain scenarios are effectively adjusted in time through the customer's intentions, and the customer's full simulation data transaction details are encapsulated and log cached, thereby improving the management effect of the supply chain scenario simulation device.

[0133] Embodiment 6:

[0134] Based on Example 5, this embodiment provides a supply chain efficiency improvement device based on big data, the prediction unit includes:

[0135] The record collection submodule collects the customer's supply chain scenario and supply chain change characteristics. When the customer's supply chain scenario is an unfamiliar scenario, the dynamic trend and dynamic quantity of the customer's supply chain are determined based on the supply chain change characteristics.

[0136] The transaction details decision submodule decides the timing of supply chain planning intervention, supply chain planning direction and supply chain planning transaction details based on supply chain dynamic trends and supply chain dynamic quantities;

[0137] The planning submodule conducts supply chain scenario planning for customers based on the timing of supply chain planning intervention, supply chain planning direction and supply chain planning transaction details, and responds based on the simultaneous updates of the supply chain scenario planning.

[0138] In this specific implementation, the supply chain dynamic trend may be the dynamic direction of the customer's supply chain category, for example, it may be different situations such as changing from unfamiliar dynamics to familiar dynamics or no dynamics in an unfamiliar scenario.

[0139] In this specific implementation, the supply chain dynamics may be the specific degree of dynamics occurring in the customer's supply chain, for example, the specific degree of dynamics changing from unfamiliar to familiar.

[0140] In this specific implementation method, the timing of supply chain planning intervention can be to process the customer's supply chain scenario through a large algorithm. When the customer's supply chain scenario has always been unfamiliar or has changed from unfamiliar to less familiar, the specific time data for supply chain scenario planning intervention for the customer is provided.

[0141] In this specific implementation method, supply chain scenario planning can be to respond to customers in an encouraging and comforting manner when the customer's supply chain scenario is always unfamiliar.

[0142] The working principle and beneficial effects of the above technical solution are: by processing the customer's supply chain scenario and supply chain change characteristics, the customer's supply chain dynamic trend and supply chain dynamic quantity are locked. Secondly, the supply chain planning intervention timing, supply chain planning direction and supply chain planning transaction details are determined through the supply chain dynamic trend and supply chain dynamic quantity, so as to realize timely and effective planning of the customer's supply chain scenario, thereby improving the customer experience and the intelligence of the supply chain scenario response.

[0143] Embodiment 7:

[0144] Based on Example 1, this embodiment provides a supply chain efficiency improvement device based on big data, an application prediction unit, including:

[0145] The data capture unit collects response data of different customers according to the reply acquisition records, and performs clustering processing on the response data to obtain a multi-branch sub-response instruction set;

[0146] The risk decision unit predicts each sub-response instruction set in the multiple branch sub-response instruction sets according to the prediction index, obtains the operation effect of each branch, and makes a decision on the prediction task according to the difference between the operation effect of each branch and the preset reference condition;

[0147] Prediction Unit:

[0148] The important coefficients of each branch are determined based on the supply chain scenario simulation mechanism, and the response data is cyclically applied based on the important coefficients and prediction tasks;

[0149] Make real-time predictions on simulated transaction objects and simulated transaction channels based on cyclic application records.

[0150] In this specific implementation, clustering processing may be to classify the customer's response data.

[0151] In this specific implementation, the multi-branch sub-response data may be data transaction details of various categories obtained after classifying the customer's response data, including the accuracy of the simulated transaction object and the relevance of the response method.

[0152] In this specific implementation, the preset reference conditions are set in advance.

[0153] In this specific implementation method, the prediction task can be a project that predicts supply chain scenario simulation by responding to data decisions, etc.

[0154] In this specific implementation, the important coefficient represents the degree of influence of different branches on the supply chain scenario simulation effect.

[0155] The working principle and beneficial effects of the above technical solution are: by processing the response data of different customers, accurate and effective decisions can be made on the operating effect of each branch in the supply chain scenario simulation device; secondly, the prediction task is locked by the difference between the operating effect and the preset reference conditions; finally, the response data is cyclically applied through the prediction task and important coefficients to achieve real-time prediction of the simulated transaction objects and simulated transaction channels, thereby ensuring the stability and reliability of the simulated transaction objects and simulated transaction channels, and at the same time, improving the effect of supply chain scenario simulation.

[0156] Embodiment 8:

[0157] Based on Example 1, this embodiment provides a supply chain efficiency improvement device based on big data, a shared publishing unit, including:

[0158] Calling unit:

[0159] Collect real-time forecast records of simulated transaction objects and simulated transaction channels, and obtain supply chain scenario simulation mechanisms based on real-time forecast records;

[0160] The supply chain scenario simulation mechanism is called as a page string according to the execution page, and a data update interface is reserved for the page content to obtain the shareable execution content;

[0161] Supply chain sharing unit:

[0162] The shared environment of the shareable executable content is published in multiple categories according to the operating conditions of multiple sources, and the shared supply chain of the shareable executable content is opened according to the multi-category publication records;

[0163] Share and apply sharable executable content across multiple sources based on open records.

[0164] In this specific implementation method, the supply chain scenario simulation mechanism can be a supply chain scenario simulation system that is finally predicted and obtained, that is, a supply chain scenario simulation mechanism that can be applied.

[0165] In this specific implementation method, the execution page is set in advance and represents a solution for calling the supply chain scenario simulation mechanism.

[0166] In this specific implementation manner, the sharable executable content may be the finally acquired application content that can be shared on different platforms.

[0167] In this specific implementation, the operating condition requirements may be the operating environment of different platforms and the requirements for the data format, etc.

[0168] The working principle and beneficial effects of the above technical solution are: through the real-time prediction and recording of simulated transaction objects and simulated transaction channels, the decision-making supply chain scenario simulation mechanism is established, and the supply chain scenario simulation mechanism is called through the execution page to achieve accurate and effective decision-making on shareable execution content; secondly, the shared environment of different platforms is published according to the operating conditions of different platforms, and the shared supply chain of shareable execution content is opened, ensuring that the supply chain scenario simulation mechanism can run stably on different platforms.

[0169] Embodiment 9:

[0170] Based on Example 7, this embodiment provides a supply chain efficiency improvement device based on big data, a risk decision unit, including:

[0171] The sub-response instruction set detection sub-module detects the sub-response instruction set associated with each branch, and collects the important coefficients associated with each branch. At the same time, the response value of the reply record is calculated through the sub-response instruction set associated with each branch and the important coefficients associated with each branch, and the response value is used to determine whether to make real-time predictions on the simulated transaction objects and simulated transaction channels, including:

[0172] First parsing module:

[0173] Detecting the sub-response instruction set associated with each branch, and detecting the important coefficient associated with each branch;

[0174] The response value of the record is obtained by calculating the reply through the sub-response instruction set associated with each branch and the importance coefficient associated with each branch;

[0175] ;

[0176] in, Get the recorded response value for the reply; is the branch sequence number value; is the total number of branches; is the sequence number value of the sub-response data in the sub-response instruction set under the i-th branch; is the total number of sub-response instruction sets under the i-th branch; is the jth sub-response data value under the i-th branch; is the important coefficient of the i-th branch; is the fault tolerance coefficient of the i-th branch, and its value range is (0, 1); is a constant, and its value range is ;

[0177] The second analysis module determines whether the response value performs real-time prediction on the simulated transaction object and the simulated transaction channel through the following formula;

[0178] ;

[0179] in, is the preset response threshold; To judge the value, that is:

[0180] if =a, it is determined that no real-time prediction will be performed on the simulated transaction object and simulated transaction channel;

[0181] if = b, it is determined to be informed;

[0182] if =c, it is determined to make real-time predictions on the simulated transaction objects and simulated transaction channels.

[0183] In this specific implementation, the response threshold is set in advance.

[0184] In this specific implementation, the notification may include sending a warning text message to the administrator.

[0185] In this specific implementation, a, b, and c are different forms of determining the acquired value w.

[0186] The working principle and beneficial effects of the above technical solution are: by detecting the sub-response instruction set associated with each branch and collecting the important coefficients associated with each branch, at the same time, the response value of the reply acquisition record is calculated through the sub-response instruction set associated with each branch and the important coefficients associated with each branch, and the response value is effectively used to determine whether to make real-time predictions on the simulated transaction objects and simulated transaction channels, which is conducive to real-time grasp of the simulation response scenario, thereby improving the intelligent control of real-time predictions on simulated transaction objects and simulated transaction channels.

[0187] Embodiment 10:

[0188] This embodiment provides a method for improving supply chain efficiency based on big data. Figure 3 As shown, including:

[0189] Step S1: Detect the supply data provided by the customer intention platform and process the supply data to obtain the customer's transaction intention and supply chain scenario;

[0190] Step S2: compare the best simulated transaction object in the knowledge base according to the transaction intention, decide on the transaction security channel according to the supply chain scenario, and reply to the customer intention platform through the transaction security channel to obtain the best simulated transaction object;

[0191] Step S3: Real-time detection of response data obtained by the customer based on the reply, and application of the response data to predict the simulated transaction object and simulated transaction channel in real time;

[0192] Step S4: Call the real-time prediction simulation transaction object and the simulation transaction channel, and publish the call record for multi-source supply chain sharing.

[0193] The working principle and beneficial effects of the above technical solution are: by automating the processing of supply data provided by the customer intent platform, reducing dependence on manual supply chain scenarios, significantly reducing service costs, and improving the response rate of intelligent supply chain scenarios, thereby improving customer experience, increasing customer satisfaction and loyalty, and by real-time detection of response data obtained by customers based on replies, and applying the response data, real-time prediction of simulated transaction objects and simulated transaction channels can adapt to market changes and customer evolution, and through multi-source supply chain sharing and publishing, customers can enjoy convenient services in different devices and environments. By judging customer supply chain scenarios and associating simulated transaction channels, transactions can be made more humane and customer communication experience can be standardized. In summary, this solution can not only improve the operational efficiency of the enterprise, but also improve the service quality and customer satisfaction of the enterprise in a highly competitive market.

[0194] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection presented or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0195] In addition, each functional unit in each embodiment of the present invention 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. The above integrated unit may be implemented in the form of hardware or in the form of a software functional unit. The above is only an implementation mode of the present invention, and does not limit the patent range of the present invention. Any equivalent structure or equivalent process transformation made using the transaction details of the present invention specification and drawings, or directly or indirectly used in other related technical fields, are also included in the patent protection range of the present invention.

[0196] The specific implementation methods of the invention are described in detail above, but they are only examples, and the invention is not limited to the specific implementation methods described above. For those skilled in the art, any equivalent modification or substitution of the invention is also within the scope of the invention, so the equalization, modification, improvement, etc. made without departing from the spirit and principle of the invention should be included in the scope of the invention.

Claims

1. A supply chain efficiency improvement device based on big data, characterized in that: include: The supply data processing unit detects the supply data provided by the customer intention platform and processes the supply data to obtain the customer's transaction intention and supply chain scenario; The simulation unit compares the best simulated transaction object in the knowledge base according to the transaction intention, decides the transaction security channel according to the supply chain scenario, and replies to the customer intention platform through the transaction security channel to obtain the best simulated transaction object; The application prediction unit detects the response data obtained by the customer based on the reply in real time, and applies the response data to predict the simulated transaction object and simulated transaction channel in real time; The sharing and publishing unit calls the real-time prediction simulation transaction object and the simulation transaction channel, and publishes the call record in a multi-source supply chain sharing manner; Application prediction unit, including: The data capture unit collects response data of different customers according to the reply acquisition records, and performs clustering processing on the response data to obtain a multi-branch sub-response instruction set; The risk decision unit predicts each sub-response instruction set in the multiple branch sub-response instruction sets according to the prediction index, obtains the operation effect of each branch, and makes a decision on the prediction task according to the difference between the operation effect of each branch and the preset reference condition; Prediction Unit: The important coefficients of each branch are determined based on the supply chain scenario simulation mechanism, and the response data is cyclically applied based on the important coefficients and prediction tasks; Make real-time predictions on simulated transaction objects and simulated transaction channels based on cycle application records; Risk decision-making unit, including: The sub-response instruction set detection sub-module detects the sub-response instruction set associated with each branch, and collects the important coefficients associated with each branch. At the same time, the response value of the reply record is calculated through the sub-response instruction set associated with each branch and the important coefficients associated with each branch, and the response value is used to determine whether to make real-time predictions on the simulated transaction objects and simulated transaction channels, including: First parsing module: Detecting the sub-response instruction set associated with each branch, and detecting the important coefficient associated with each branch; The response value of the record is obtained by calculating the reply through the sub-response instruction set associated with each branch and the importance coefficient associated with each branch; Where V is the response value of the reply acquisition record; i is the branch number value; n is the total number of branches; j is the total number of branches; i is the sequence number value of the sub-response data in the sub-response instruction set under the i-th branch; m i is the total number of sub-response instruction sets under the i-th branch; is the jth sub-response data value under the i-th branch; μ i is the important coefficient of the i-th branch; σ i is the fault tolerance coefficient of the i-th branch, and its value range is (0, 1); ρ is a constant, and its value range is (1*10 4 , 3*10 4 ); The second analysis module determines whether the response value performs real-time prediction on the simulated transaction object and the simulated transaction channel through the following formula; Among them, V 阈值 is the preset response threshold; w is the judgment acquisition value, that is: If w = a, it is determined that no real-time prediction is performed on the simulated transaction object and the simulated transaction channel; If w = b, it is determined to notify; If w=c, it is determined to make a real-time prediction on the simulated transaction object and the simulated transaction channel.

2. A supply chain efficiency improvement device based on big data as claimed in claim 1, characterized in that: Supply of data processing units including: A data source providing unit accesses the session window according to the customer intent platform and presents the supply data provided by the customer intent platform in the session window; A first supply data processing unit processes the supply data to obtain branch supply data; The second supply data processing unit identifies and analyzes the branch supply data to obtain the customer's transaction intention and supply chain scenario.

3. The supply chain efficiency improvement device based on big data as claimed in claim 2, characterized in that: Supply of data processing units including: The data detection submodule detects the supply data and determines the transaction instruction information associated with the supply data; The instruction information processing submodule performs standardization processing on the transaction instruction information to obtain the first transaction instruction information, and at the same time, performs segmentation processing on the first transaction instruction information and extracts the instruction segment of the voice transaction instruction according to the processing record; The algorithm configuration submodule applies the instruction segment of the voice trading instruction, determines the reference cutting features of the instruction segment of the voice trading instruction, and configures the invalid trading instruction recognition algorithm through the reference cutting features of the instruction segment of the voice trading instruction; Instruction filtering submodule: Providing the first transaction instruction information to the transaction instruction invalidation identification algorithm for cutting feature identification, backing up the transaction instruction information in the first transaction instruction information that is inconsistent with the reference cutting feature through identification records, and determining the abnormal transaction instruction segment through the backup records; The invalid instructions associated with the abnormal transaction instruction segment are screened to obtain second transaction instruction information, wherein the second transaction instruction information is the branch supply data.

4. The supply chain efficiency improvement device based on big data as claimed in claim 2, characterized in that: Supply of data processing units including: The transaction string adjustment submodule detects the branch supply data, adjusts the branch supply data into a string description, and divides the string description into a plurality of substring descriptions by a pause mark of the string description in the string description; The key sentence processing submodule collects the key sentences of the substring description, and corresponds the key sentences of each substring description to the uninterrupted feature space, and obtains the features of the key sentences in each substring description through the corresponding records; The keyword feature decision submodule calculates the first keyword relationship between the key sentences in each substring description based on the features of the key sentences in each substring description, and decides the keyword features of each substring description; The transaction intention collection submodule determines the second keyword relationship between each substring description through the keyword features of each substring description, and determines the customer's transaction intention through the second keyword relationship; The supply chain scenario decision submodule provides the customer's transaction intention and branch supply data to the preset supply chain identification algorithm for processing, and obtains the customer's supply chain scenario based on the processing records.

5. The supply chain efficiency improvement device based on big data as claimed in claim 1, characterized in that: Simulation unit, including: Transaction details comparison unit: Collect the acquired transaction intentions and adjust the transaction intentions into transaction strings; Segment and feature annotate transaction strings based on natural language parsing solutions, and extract entity data from transaction strings and focus on executing transaction behaviors based on segmentation and feature annotation records; According to the entity data, the historical key executed transaction behaviors in the transaction string are string-associated, and the decision transaction intention and intent are recorded according to the string association, and the knowledge base is traversed according to the transaction intention and intent to obtain the best simulation transaction object; Response Unit: Analyze the supply chain scenarios to determine the customer's current supply chain preference and supply chain strength, and determine the customer's supply chain scenario category based on the supply chain preference. At the same time, determine the trust index of the customer's supply chain preference based on the supply chain strength. According to the supply chain scenario category and trust index, the target transaction security channel is retrieved from the preset strategy library, and the best simulated transaction object is responded to the customer intention platform based on the target transaction security channel; The prediction unit reviews the customer's real-time supply chain scenario based on the response acquisition record, and determines the change characteristics of the customer's supply chain scenario based on the review record, and updates and adjusts the target transaction security channel based on the supply chain change characteristics; Packaging and logging unit: Collect the full simulation data transaction details of the customer over time according to the update adjustment record, and perform multi-source encapsulation of the full simulation data transaction details according to the multi-category encapsulation key; Log cache is performed on the full simulation data after multi-source packaging, and the log cache records are backed up attributably based on customer identity.

6. The supply chain efficiency improvement device based on big data as claimed in claim 5, characterized in that: Prediction unit, including: The record collection submodule collects the customer's supply chain scenario and supply chain change characteristics. When the customer's supply chain scenario is an unfamiliar scenario, the dynamic trend and dynamic quantity of the customer's supply chain are determined based on the supply chain change characteristics. The transaction details decision submodule decides the timing of supply chain planning intervention, supply chain planning direction and supply chain planning transaction details based on supply chain dynamic trends and supply chain dynamic quantities; The planning submodule conducts supply chain scenario planning for customers based on the timing of supply chain planning intervention, supply chain planning direction and supply chain planning transaction details, and responds based on the simultaneous updates of the supply chain scenario planning.

7. The supply chain efficiency improvement device based on big data as claimed in claim 1, characterized in that: Shared publishing unit, including: Calling unit: Collect real-time forecast records of simulated transaction objects and simulated transaction channels, and obtain supply chain scenario simulation mechanisms based on real-time forecast records; The supply chain scenario simulation mechanism is called as a page string according to the execution page, and a data update interface is reserved for the page content to obtain the shareable execution content; Supply chain sharing unit: The shared environment of the shareable executable content is published in multiple categories according to the operating conditions of multiple sources, and the shared supply chain of the shareable executable content is opened according to the multi-category publication records; Share and apply sharable executable content across multiple sources based on open records.

8. A method for improving supply chain efficiency based on big data, applied to a device for improving supply chain efficiency based on big data as described in any one of claims 1 to 7, characterized in that: include: Step 1: Detect the supply data provided by the customer intention platform and process the supply data to obtain the customer's transaction intention and supply chain scenario; Step 2: Compare the best simulated transaction object in the knowledge base based on the transaction intention, decide on the transaction security channel based on the supply chain scenario, and reply to the customer intention platform through the transaction security channel to obtain the best simulated transaction object; Step 3: Real-time detection of response data obtained by the customer based on the reply, and application of the response data to predict the simulated transaction object and simulated transaction channel in real time; Step 4: Call the real-time prediction simulation transaction object and the simulation transaction channel, and publish the call record for multi-source supply chain sharing.

Images