Digital consultation management method and system based on edge computing and related equipment

Abstract

The invention relates to the technical field of edge computing, and discloses a digital consultation management method and system based on edge computing and related equipment, and the method comprises the steps: collecting consultation operation data of an enterprise in real time through an edge computing architecture; wherein the consultation operation data comprises sales data of an enterprise, client feedback data and supply chain data; performing preprocessing and lightweight analysis on the consultation operation data on the edge node, and determining an analysis result; the analysis results corresponding to the edge nodes are integrated, and dynamic consultation suggestions are determined; and returning the dynamic consultation suggestions to each edge node to optimize a local strategy. According to the invention, the cloud dependence is reduced through the edge computing architecture, the consultation response speed is obviously improved, and a feedback mechanism is adopted to ensure that the strategy is continuously optimized.

Description

Technical Field

[0001] This disclosure relates to the field of edge computing technology, and in particular to digital consulting management methods, systems and related equipment based on edge computing. Background Technology

[0002] Business consulting refers to a service activity in which business management experts use scientific methods to identify problems in business management based on investigation and analysis, propose specific improvement plans, and guide their implementation to help businesses improve their operations and management.

[0003] However, traditional enterprise consulting relies on centralized cloud processing, resulting in slow real-time decision response and difficulty in meeting high-frequency business needs. Summary of the Invention

[0004] To overcome the problem that traditional enterprise consulting relies on centralized cloud processing, resulting in slow real-time decision response and difficulty in meeting high-frequency business needs, this disclosure provides a digital consulting management method, system and related equipment based on edge computing.

[0005] Firstly, in order to solve the aforementioned technical problems, this disclosure provides a digital consulting management method based on edge computing, including:

[0006] The consulting and operational data of enterprises are collected in real time through an edge computing architecture; the consulting and operational data includes the enterprise's sales data, customer feedback data, and supply chain data.

[0007] Preprocessing and lightweight analysis of consulting operation data at edge nodes to determine the analysis results;

[0008] The analysis results corresponding to each edge node are integrated to determine dynamic consultation recommendations;

[0009] Dynamic consultation suggestions are sent back to each edge node to optimize local strategies.

[0010] Secondly, this disclosure provides a digital consulting management system based on edge computing, including:

[0011] The consulting operations data collection module is used to collect enterprise consulting operations data in real time through an edge computing architecture; the consulting operations data includes the enterprise's sales data, customer feedback data, and supply chain data.

[0012] The analysis results determination module is used to preprocess and perform lightweight analysis on consulting operation data at edge nodes to determine the analysis results;

[0013] The Dynamic Consultation Recommendation Determination Module is used to integrate the analysis results corresponding to each edge node and determine the dynamic consultation recommendations.

[0014] The local optimization module is used to send dynamic consultation suggestions back to each edge node to optimize local strategies.

[0015] Thirdly, this disclosure provides a digital consulting management system based on edge computing, including: a distributed data acquisition module, edge computing nodes, a central management platform, and a feedback module, wherein:

[0016] Distributed data acquisition is used to collect real-time consulting and operational data from enterprises.

[0017] Edge computing nodes are used for preprocessing and lightweight analysis of consulting and operational data;

[0018] The central management platform is used to integrate the analysis results corresponding to each edge node;

[0019] The feedback module is used to send the results of the central management platform integration back to each edge node to optimize local strategies.

[0020] Fourthly, this disclosure provides a computing device including a memory, a processor, and a program stored on the memory and running on the processor, wherein the processor executes the program to implement the steps of the edge computing-based digital consulting management method described above.

[0021] Fifthly, this disclosure provides a computer-readable storage medium storing instructions that, when executed on a terminal device, cause the terminal device to perform the steps of the edge computing-based digital consulting management method described above.

[0022] The beneficial effects of this disclosure are: It collects consulting and operational data through an edge computing architecture, performs lightweight analysis on edge nodes, determines the analysis results, integrates the results from the edge nodes to determine dynamic consulting recommendations, and finally sends these recommendations back to each edge node to optimize local strategies. This disclosure reduces cloud dependency through an edge computing architecture, significantly improves consulting response speed, and employs a feedback mechanism to ensure continuous optimization of the strategy. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the present disclosure will be further described below in conjunction with the accompanying drawings and embodiments.

[0024] Figure 1 This is a flowchart illustrating the edge computing-based digital consulting management method according to an embodiment of the present disclosure.

[0025] Figure 2 This is a schematic diagram of the structure of a digital consulting management system based on edge computing, according to an embodiment of the present disclosure.

[0026] Figure 3 This is a schematic diagram of the structure of a computing device according to an embodiment of the present disclosure. Detailed Implementation

[0027] The following embodiments are further explanations and supplements to this disclosure and do not constitute any limitation on this disclosure.

[0028] The following describes, in conjunction with the accompanying drawings, a digital consulting management method, system, and related equipment based on edge computing according to embodiments of the present disclosure.

[0029] like Figure 1 As shown, this disclosure provides a digital consulting management method based on edge computing, including:

[0030] S1. Real-time collection of enterprise consulting and operational data through edge computing architecture; whereby consulting and operational data includes enterprise sales data, customer feedback data, and supply chain data.

[0031] S2. Perform preprocessing and lightweight analysis on consulting operation data at edge nodes to determine the analysis results.

[0032] S3. Integrate the analysis results corresponding to each edge node to determine dynamic consultation recommendations.

[0033] S4. Send dynamic consultation suggestions back to each edge node to optimize local strategies.

[0034] In this embodiment, consulting operation data is collected through an edge computing architecture, and lightweight analysis is performed on edge nodes to determine the analysis results. These results are then integrated to determine dynamic consulting recommendations, which are finally transmitted back to each edge node to optimize local strategies. This disclosure reduces cloud dependence through an edge computing architecture, significantly improves consulting response speed, and employs a feedback mechanism to ensure continuous optimization of the strategy.

[0035] Optionally, enterprise consulting and operational data can be collected in real time through an edge computing architecture, including:

[0036] The Master node monitors the task scheduling of the enterprise's private cloud or server, and stores the consulting and operational data generated by the private cloud or server in the database.

[0037] Access consulting and operational data stored in the database via Slave nodes;

[0038] The Master node is deployed on the enterprise's private cloud or server and is configured with load balancing, while the Slave node is deployed in the enterprise's database.

[0039] In this embodiment, the consulting operation data mainly includes three categories: sales data, customer feedback data, and supply chain data, among which:

[0040] (1) Sales data

[0041] Sales performance: sales revenue, gross profit margin, average order value, conversion rate, and repurchase rate.

[0042] Operational efficiency: order processing time, inventory turnover rate, equipment utilization rate.

[0043] Market performance: market share, competitor pricing monitoring, and marketing activities.

[0044] Profitability: Revenue, net profit, cash flow.

[0045] Cost structure: raw material costs, labor costs, and marketing expenses as a percentage of total cost.

[0046] (2) Customer feedback data

[0047] Feedback data: NPS score, complaint rate, customer service conversation records.

[0048] (3) Supply chain data

[0049] Procurement management: supplier on-time delivery rate, procurement cost fluctuations.

[0050] Inventory optimization: safety stock level, stockout rate, and percentage of slow-moving items.

[0051] Logistics efficiency: delivery time, transportation costs, and abnormal receipt rate.

[0052] In this embodiment, the Master node monitors task scheduling, and the Slave node crawls the consulting and operation data. The crawling methods include web crawling and log parsing, and it supports horizontal scaling.

[0053] In this embodiment, enterprises can build an efficient and reliable edge computing architecture to comprehensively acquire consulting and operational data and support business decisions. Moreover, the edge computing architecture covers data assets across the entire business chain, providing support for refined operations and intelligent decision-making.

[0054] Optionally, real-time collection of enterprise consulting and operational data through edge computing architecture also includes:

[0055] The master node periodically checks the liveness of the slave nodes;

[0056] When a slave node fails, the failed slave node is switched to a standby node.

[0057] In this embodiment, the Master node periodically checks the Slave node, thereby avoiding overload caused by Slave node failure and improving the response speed of the entire system.

[0058] Optionally, preprocessing and lightweight analysis of consulting operation data can be performed at edge nodes to determine the analysis results, including:

[0059] At each edge node, the consulting operation data is preprocessed to determine the preprocessed data; the preprocessing includes noise reduction, data format standardization, and removal of outlier data.

[0060] At each edge node, an anomaly detection model is used to perform anomaly analysis on the preprocessed data to identify anomalous data.

[0061] At each edge node, the preprocessed data is analyzed using a predictive model to predict sales trends for a preset time period in the future.

[0062] At each edge node, the preprocessed data is classified and analyzed using a classification model to determine the type of customer feedback;

[0063] Among them, the anomaly detection model, prediction model and classification model are all lightweight models, and the analysis results include abnormal data, sales trends and customer feedback types.

[0064] In this embodiment, the abnormal data mainly targets anomalies in sales and supply chain data, such as low supplier on-time delivery rates, slow delivery times, high transportation costs, and low sales volume. Anomaly detection models such as Isolation Forest, which are based on decision trees, can be used. For example:

[0065] Isolation forests recursively divide data into multiple sub-regions by randomly selecting features and split values. Outlier data, which differs significantly from most data, can usually be isolated with only a few splits, while normal data requires more splits to be isolated. The algorithm calculates the average path length required for each data point to be isolated, and the shorter the path, the more likely it is to be an outlier.

[0066] When training an anomaly detection model, parameters need to be set, as follows:

[0067] Number of trees: determines the complexity of the anomaly detection model (usually 50-200 trees, the more trees, the more stable the results).

[0068] Contamination rate: The percentage of outliers in the preset data (this needs to be combined with business experience; for example, setting it to 1% means that 1% of the data is expected to be outliers).

[0069] Subsampling size: The number of samples used per tree (automatically selected by default, which can speed up training).

[0070] Training process: The anomaly detection model constructs multiple isolation trees by randomly dividing the feature space, and each tree attempts to isolate data points using the shortest path.

[0071] Anomaly scoring: The anomaly detection model calculates an anomaly score (usually between -1 and 1) for each data point. The closer the score is to -1, the higher the probability of an anomaly.

[0072] Threshold setting: Set thresholds according to business needs (e.g., mark points with scores <-0.5 as abnormal), or determine dynamic thresholds through historical data statistics.

[0073] By inputting sales data into a trained anomaly detection model, orders with high transportation costs can be identified; these high-cost orders are considered anomaly data.

[0074] In this embodiment, the sales trend mainly refers to sales data, such as the sales trend within the next month. The prediction model can use a time series analysis model, as illustrated by the following example:

[0075] Time series analysis is a statistical method that uses patterns (such as trends, seasonality, and periodicity) in sales data to predict future values.

[0076] When training a time series analysis model, parameters need to be set, as follows:

[0077] ARIMA: Determine p, d, q through ACF / PACF graph or grid search.

[0078] Prophet: Adjusts the priority of change points and seasonal smoothing parameters.

[0079] Training: Fit the parameters of the time series analysis model (such as the MLE estimate of ARIMA) and evaluate the time series analysis model using MAE (mean absolute error), RMSE (root mean square error), and MAPE (mean absolute percentage error) metrics.

[0080] By inputting the sales figures for the past month into a time series analysis model, the sales trend for the next month can be obtained.

[0081] In this embodiment, customer feedback types mainly refer to customer feedback data, such as positive reviews, negative reviews, or general feedback. A classification model is used to categorize customer feedback, allowing for the systematic extraction of key information from customer feedback and assisting businesses in optimizing their products or services. For example:

[0082] When training a classification model, a clear training strategy needs to be defined, as follows:

[0083] Cross-validation:

[0084] Time series data: Divide the training set and test set in chronological order (to avoid data crossing).

[0085] For standard data: 5-fold cross-validation is used to ensure model generalization.

[0086] Overparameter tuning:

[0087] Grid search: Combines and optimizes key parameters such as learning rate and regularization coefficient.

[0088] Bayesian optimization: quickly approximates the optimal parameters using a Gaussian process (suitable for large-scale searches).

[0089] After training, the classification model is evaluated using F1-Score (balancing precision and recall) and AUC-ROC (evaluating the model's discriminative ability).

[0090] By inputting customer reviews into a classification model, we can obtain the customer's emotional tags, which are the types of customer feedback.

[0091] Optionally, the analysis results corresponding to each edge node are integrated to determine dynamic consultation recommendations, including:

[0092] By integrating abnormal data, sales trends, and customer feedback types, and combining them with a rules engine, dynamic consultation recommendations are determined.

[0093] In this embodiment, the rule engine can build a rule base, which is based on predefined logical rules for business scenarios. For example:

[0094] (1) If the customer feedback type transmitted from the edge computing node is negative review rate higher than 50%, the suggestion to "train employees service quality" will be triggered.

[0095] (2) If the sales trend transmitted from the edge computing node shows that the sales volume will continue to increase in the next month, then the "emergency replenishment" suggestion will be triggered.

[0096] (3) If the abnormal data transmitted from the edge computing node is a high-cost transportation order, the suggestion to "change the courier company" will be triggered.

[0097] This embodiment achieves efficient data collection and preprocessing through edge nodes. Combined with cross-platform integration, intelligent algorithms, and dynamic visualization technology, enterprises can build a closed loop of "perception-analysis-decision-making." Ultimately, it outputs dynamic consulting suggestions to assist in operational optimization, customer experience improvement, and risk management, thereby driving digital transformation.

[0098] Optionally, dynamic consultation suggestions can be fed back to each edge node to optimize local strategies, including:

[0099] Each edge node compares the received dynamic consultation suggestions with local rules;

[0100] If the dynamic consultation advice is consistent with the local rules, then the local rules shall continue to be followed;

[0101] If the dynamic consultation suggestion is inconsistent with the local rules, the dynamic consultation suggestion shall be executed.

[0102] In this embodiment, the edge nodes perform semantic matching between local rules and dynamic consultation suggestions to identify conflicts. When a conflict occurs, the dynamic consultation suggestions are used first.

[0103] In this embodiment, local rules are continuously updated and optimized through edge nodes. After operating locally using the optimized local rules, the collected consultation and operation data is analyzed and uploaded to generate new dynamic consultation suggestions, which are then sent back to the edge nodes to continuously optimize the local rules. For example:

[0104] If a high-cost order triggers a "change courier company" suggestion, the company will adopt the suggestion. The edge node will continuously collect the company's transportation costs and perform lightweight analysis. After integrating the analysis results, if no high transportation costs are found, the company will continue to use the courier company. If high transportation costs are found, a new dynamic consultation suggestion will be generated to "change courier company" until the transportation costs are controlled within a reasonable range.

[0105] This embodiment utilizes feedback-driven optimization, where dynamic consultation suggestions can be efficiently transmitted back to edge nodes, enabling continuous optimization of local strategies. The system needs to balance real-time performance, security, and resource efficiency, combining technologies such as containerization and federated learning to ultimately form a closed loop of "perception-decision-execution-improvement," facilitating intelligent enterprise operations.

[0106] like Figure 2 As shown, this disclosure provides a digital consulting management system based on edge computing, including:

[0107] The consulting operations data collection module is used to collect enterprise consulting operations data in real time through an edge computing architecture; the consulting operations data includes the enterprise's sales data, customer feedback data, and supply chain data.

[0108] The analysis results determination module is used to preprocess and perform lightweight analysis on consulting operation data at edge nodes to determine the analysis results;

[0109] The Dynamic Consultation Recommendation Determination Module is used to integrate the analysis results corresponding to each edge node and determine the dynamic consultation recommendations.

[0110] The local optimization module is used to send dynamic consultation suggestions back to each edge node to optimize local strategies.

[0111] Optionally, consult the operational data collection module, specifically for:

[0112] The Master node monitors the task scheduling of the enterprise's private cloud or server, and stores the consulting and operational data generated by the private cloud or server in the database.

[0113] Access consulting and operational data stored in the database via Slave nodes;

[0114] The Master node is deployed on the enterprise's private cloud or server and is configured with load balancing, while the Slave node is deployed on the enterprise's database.

[0115] Optionally, the consultation and operation data collection module is also used for:

[0116] The master node periodically checks the liveness of the slave nodes;

[0117] When a slave node fails, the failed slave node is switched to a standby node.

[0118] Optionally, the analysis result determination module is specifically used for:

[0119] At each edge node, the consulting operation data is preprocessed to determine the preprocessed data; the preprocessing includes noise reduction, data format standardization, and removal of outlier data.

[0120] At each edge node, an anomaly detection model is used to perform anomaly analysis on the preprocessed data to identify anomalous data.

[0121] At each edge node, the preprocessed data is analyzed using a predictive model to predict sales trends for a preset time period in the future.

[0122] At each edge node, the preprocessed data is classified and analyzed using a classification model to determine the type of customer feedback;

[0123] Among them, the anomaly detection model, prediction model and classification model are all lightweight models, and the analysis results include abnormal data, sales trends and customer feedback types.

[0124] Optionally, the dynamic consultation suggestion determination module is specifically used for:

[0125] By integrating abnormal data, sales trends, and customer feedback types, and combining them with a rules engine, dynamic consultation recommendations are determined.

[0126] Optionally, the local optimization module is specifically used for:

[0127] Each edge node compares the received dynamic consultation suggestions with local rules;

[0128] If the dynamic consultation advice is consistent with the local rules, then the local rules shall continue to be followed;

[0129] If the dynamic consultation suggestion is inconsistent with the local rules, the dynamic consultation suggestion shall be executed.

[0130] This disclosure provides a digital consulting management system based on edge computing, including:

[0131] The system comprises a distributed data acquisition module, edge computing nodes, a central management platform, and a feedback module, among which:

[0132] The distributed data acquisition module is used to collect enterprise consulting and operational data in real time.

[0133] Edge computing nodes are used for preprocessing and lightweight analysis of consulting and operational data;

[0134] The central management platform is used to integrate the analysis results corresponding to each edge node;

[0135] The feedback module is used to send the results of the central management platform integration back to each edge node to optimize local strategies.

[0136] A computing device according to an embodiment of this disclosure includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the aforementioned digital consulting management method based on edge computing. That is, a computing device according to an embodiment of this disclosure may include, but is not limited to: a processor and a memory; the memory is used to store the computer program; the processor is used to execute the digital consulting management method based on edge computing shown in any embodiment of this disclosure by calling the computer program.

[0137] In one alternative embodiment, a computing device is provided, such as Figure 3 As shown, Figure 3 The computing device 4000 shown includes a processor 4001 and a memory 4003. The processor 4001 and the memory 4003 are connected, for example, via a bus 4002. Optionally, the computing device 4000 may further include a transceiver 4004, which can be used for data interaction between the computing device and other computing devices, such as sending and / or receiving data. It should be noted that in practical applications, the transceiver 4004 is not limited to one type, and the structure of this computing device 4000 does not constitute a limitation on the embodiments of this disclosure.

[0138] Processor 4001 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute the various exemplary logic blocks, modules, and circuits described in connection with this disclosure. Processor 4001 may also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0139] Bus 4002 may include a path for transmitting information between the aforementioned components. Bus 4002 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Bus 4002 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 3 The bus 4002 is represented by only one thick line, but this does not mean that there is only one bus or one type of bus.

[0140] The memory 4003 may be ROM (Read Only Memory) or other types of static storage devices capable of storing static information and instructions, RAM (Random Access Memory) or other types of dynamic storage devices capable of storing information and instructions, or EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto.

[0141] The memory 4003 stores application code (computer program) that executes the present invention, and its execution is controlled by the processor 4001. The processor 4001 executes the application code stored in the memory 4003 to implement the content shown in the foregoing method embodiments.

[0142] The computing device can also be a terminal device, which can be any device that can install applications, including at least one of smartphones, tablets, laptops, desktop computers, smart speakers, smartwatches, smart TVs, and smart in-vehicle devices.

[0143] It should be noted that, Figure 3 The computing device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0144] This disclosure provides an embodiment of a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the aforementioned edge computing-based digital consulting management method.

[0145] Alternatively, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CD-ROM), magnetic tape, a floppy disk, and an optical data storage device, etc.

[0146] In an exemplary embodiment, a computer program product or computer program is also provided, which includes computer instructions stored in a computer-readable storage medium. A processor of a computing device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computing device to perform the aforementioned edge computing-based digital consulting management method.

[0147] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0148] It should be understood that the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of methods and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0149] The computer-readable storage medium provided in this disclosure can be, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EEPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0150] The computer-readable storage medium described above carries one or more programs, which, when executed by the computing device, cause the computing device to perform the method shown in the above embodiments.

[0151] The above description is merely a preferred embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

[0152] It should be noted that the terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and represent a limitation on a specific order or sequence. Where appropriate, the order of use for similar objects can be interchanged so that the embodiments of this application described herein can be implemented in an order other than that shown or described.

[0153] Those skilled in the art will recognize that this disclosure can be implemented as a system, method, or computer program product. Therefore, this disclosure can be implemented in the following forms: it can be entirely hardware, entirely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software, generally referred to herein as a "circuit," "module," or "system." Furthermore, in some embodiments, this disclosure can also be implemented as a computer program product contained in one or more computer-readable media, which includes computer-readable program code.

[0154] Although embodiments of the present disclosure have been shown and described above, it is to be understood that the above embodiments are exemplary and should not be construed as limiting the present disclosure. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present disclosure.

Claims

1. A digital consulting management method based on edge computing, characterized in that, include: The consulting and operational data of enterprises are collected in real time through an edge computing architecture; wherein, the consulting and operational data includes the enterprise's sales data, customer feedback data, and supply chain data; The consulting operation data is preprocessed and lightweighted at the edge nodes to determine the analysis results; The analysis results corresponding to each edge node are integrated to determine dynamic consultation recommendations; The dynamic consultation suggestions are sent back to each edge node to optimize the local strategy.

2. The method according to claim 1, characterized in that, The real-time collection of enterprise consulting and operational data through edge computing architecture includes: The Master node monitors the task scheduling of the enterprise's private cloud or server, and stores the consulting and operational data generated by the private cloud or server in the database. Access consulting and operational data stored in the database via Slave nodes; The Master node is deployed on the enterprise's private cloud or server and is configured with load balancing, while the Slave node is deployed in the enterprise's database.

3. The method according to claim 2, characterized in that, The method of collecting enterprise consulting and operational data in real time through edge computing architecture also includes: The master node periodically checks the liveness of the slave nodes; When the Slave node fails, the failed Slave node will be switched to a standby node.

4. The method according to claim 1, characterized in that, The preprocessing and lightweight analysis of the consulting operation data at the edge nodes, and the determination of the analysis results, include: At each edge node, the consulting operation data is preprocessed to determine the preprocessed data; wherein, the preprocessing includes noise reduction, data format standardization, and removal of outlier data; At each edge node, an anomaly detection model is used to perform anomaly analysis on the preprocessed data to identify anomalous data. At each edge node, the preprocessed data is analyzed using a predictive model to predict sales trends for a preset time period in the future. At each edge node, the preprocessed data is classified and analyzed using a classification model to determine the type of customer feedback; The anomaly detection model, the prediction model, and the classification model are all lightweight models, and the analysis results include the abnormal data, the sales trend, and the customer feedback type.

5. The method according to claim 4, characterized in that, The process of integrating the analysis results corresponding to each edge node to determine dynamic consultation recommendations includes: By integrating the abnormal data, sales trends, and customer feedback types, and combining them with a rules engine, dynamic consultation recommendations are determined.

6. The method according to claim 1, characterized in that, The step of sending the dynamic consultation suggestions back to each of the edge nodes to optimize the local strategy includes: Each edge node compares the received dynamic consultation suggestions with local rules; If the dynamic consultation suggestion is consistent with the local rule, then the local rule continues to be executed; If the dynamic consultation suggestion is inconsistent with the local rules, then the dynamic consultation suggestion is executed.

7. A digital consulting management system based on edge computing, characterized in that, include: The consulting operations data collection module is used to collect enterprise consulting operations data in real time through an edge computing architecture; wherein, the consulting operations data includes the enterprise's sales data, customer feedback data, and supply chain data; The analysis result determination module is used to preprocess and perform lightweight analysis on the consulting operation data at the edge nodes to determine the analysis results; The dynamic consultation suggestion determination module is used to integrate the analysis results corresponding to each edge node and determine the dynamic consultation suggestion. The local optimization module is used to send the dynamic consultation suggestions back to each of the edge nodes to optimize the local strategy.

8. A digital consulting management system based on edge computing, characterized in that: include: The system comprises a distributed data acquisition module, edge computing nodes, a central management platform, and a feedback module, among which: The distributed data acquisition module is used to collect enterprise consulting and operational data in real time. The edge computing node is used for preprocessing and lightweight analysis of the consulting operation data; The central management platform is used to integrate the analysis results corresponding to each of the edge nodes; The feedback module is used to send the results of the integration by the central management platform back to each edge node to optimize local strategies.

9. A computing device, comprising a memory, a processor, and a program stored in the memory and running on the processor, characterized in that, The processor executes the program to implement the steps of the edge computing-based digital consulting management method as described in any one of claims 1-6.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions that, when executed on a terminal device, cause the terminal device to perform the steps of the edge computing-based digital consulting management method as described in any one of claims 1-6.

Images