Enterprise digital transformation demand intelligent processing method, system and equipment based on large model, and medium

Abstract

The invention provides an enterprise digital transformation demand intelligent processing method, system and device based on a large model and a medium, and belongs to the technical field of data processing.The method comprises the steps that enterprise digital transformation demands are responded, the large model is used for analysis, and enterprise characteristic parameters and demand implementation paths are determined; querying a pre-constructed resource knowledge graph according to the enterprise characteristic parameters and the demand implementation path, and performing service resource matching; the enterprise characteristic parameters comprise industry attributes and scales; according to a matching result, determining steps needing to be implemented in stages, associating service providers and service parameters of the service resources with the demand resources and risk points and optimization suggestions in the transformation process, and generating a digital transformation solution; and responding to the feedback of the enterprise to the solution, and optimizing the demand content analysis process and the service resource matching process of the large model. According to the invention, through combination of the large model and the knowledge graph, intelligent processing of enterprise digital transformation demands is realized.

Description

Technical Field

[0001] The present application belongs to the field of data processing technology, and specifically relates to a method, system, device and medium for intelligently processing enterprise digital transformation needs based on a large model. Background Art

[0002] Digital transformation is crucial for enhancing enterprise competitiveness and improving product quality. Current information service systems in the industry provide enterprises with resource connection, diagnostic and evaluation services, and assist in their digital transformation. However, existing information service systems have the following issues: First, information is fragmented, making it difficult to accurately match business needs. Current information service systems often rely on traditional keyword matching or categorized search methods, making it difficult to accurately understand business needs. For example, if a company requests "improving production efficiency," the information service system may return a large amount of irrelevant information, resulting in inefficient screening.

[0003] Second, service efficiency is low. Existing information service systems lack dynamic analysis capabilities and are unable to generate personalized solutions based on business characteristics such as industry and scale. For example, if a small and medium-sized enterprise requires a digital diagnosis, the platform typically provides a standardized diagnostic questionnaire that cannot be customized based on the company's industry or scale, resulting in a lack of targeted diagnostic results. Existing public service platforms for small and medium-sized enterprises have significant shortcomings in terms of accurate information matching and personalized services.

[0004] In summary, the existing information service systems for enterprise digital transformation have problems such as low matching between supply and demand, poor service resource knowledge integration capabilities, limited intelligent processing levels, and lack of precise processing capabilities. An intelligent processing method is urgently needed to improve processing efficiency and accuracy. Summary of the Invention

[0005] In a first aspect, an embodiment of the present application provides a method for intelligently processing enterprise digital transformation needs based on a large model, comprising the following steps: S1. Respond to the digital transformation needs of enterprises and analyze them using a large model to determine the enterprise's characteristic parameters and the path to fulfilling these needs. This path includes determining the type of needs, identifying key links, and determining the required resource tags. S2. Query the pre-built resource knowledge graph to match service resources based on the enterprise's characteristic parameters and demand implementation path; the enterprise characteristic parameters include industry attributes and scale; S3. Based on the matching results, determine the phased implementation steps, the service providers and service parameters for the required resources and associated service resources, as well as the risk points and optimization suggestions during the transformation process, and generate a digital transformation solution. S4. Respond to enterprise feedback on solutions and optimize the large model demand content parsing process and service resource matching process.

[0006] Furthermore, the specific steps of step S1 are as follows: S11. Receive digital transformation requirements submitted by enterprises in text format; S12. Identify the industry attributes, scale, and historical data of the enterprise as enterprise characteristic parameters through the large model; S13. Identify entities in digital transformation requirements through the big model and determine the classification of the required types; S14. Use the large model to identify the key links corresponding to the transformation points in the digital transformation requirements, and determine the resource tags required for digital transformation of the key links; S15. Integrate the demand types, key links, and demand resource tags of digital transformation requirements into a structured demand form.

[0007] Furthermore, the specific steps of step S2 are as follows: S21. Based on the required resource tags in the structured requirement form, search the resource knowledge graph, select the related service providers, and filter them using enterprise characteristic parameters; S22. Obtaining historical service cases of the service provider obtained through screening and filtering; S23. Input the text of the digital transformation requirements and the service provider's historical service cases into the big model, extract the text feature vectors through the big model, calculate the cosine similarity, and retain the historical service cases whose cosine similarity exceeds the similarity threshold; S24. Obtain the ratings of the service providers of the retained historical service cases, the service provider's quote for the service resource, and the response time. Then, combine the cosine similarity to perform a weighted ranking of each historical service case to obtain a comprehensive score. S25. Filter the service resources corresponding to the top N historical service cases as candidate resources based on the comprehensive scores.

[0008] Furthermore, step S3 is as follows: S31. Based on the service parameters of the candidate service resources and the enterprise's characteristic parameters, determine the phased implementation steps for digital transformation needs, including the goals, tasks, and timelines for each phase; S32. Establish a relationship between the demand resources and candidate service resources, determine the service provider and service parameters, including service content, quotation and cycle; S33. Analyze risk points in the digital transformation process based on a large-scale model and provide optimization suggestions for each risk point. S34. Integrate the phased implementation steps, service providers and service parameters of demand resources and service resources, as well as risk points and optimization suggestions into a digital transformation solution, and present it to the enterprise in a visual form.

[0009] Furthermore, the specific steps of step S4 are as follows: S41. Receive enterprise feedback on digital transformation solutions, including selected solutions, user satisfaction with the solutions, implementation issues, and improvement suggestions; S42. Input the feedback information into the big model, analyze the feedback content through the big model, and extract key features; S43. Adjust the parameters and weights of the large model in the process of demand content analysis and service resource matching based on the extracted key features; S44. Use the adjusted parameters and weights to optimize the training of the large model.

[0010] Furthermore, the method further comprises the following steps: S5. Connect to the enterprise production system through API, collect enterprise digitalization level data in real time, use large models combined with industry benchmark parameters to conduct digital scoring for each production link, conduct root cause analysis for weak production links with low digital scores, generate digital transformation demand text, and then execute steps S1-S4 to recommend solutions.

[0011] Furthermore, the digitalization level data includes equipment networking rate, sensor coverage rate, ERP / MES system coverage rate, data interface openness, data utilization rate and business process digitalization ratio.

[0012] Furthermore, step S2 also includes the following steps: Pre-built Neo4j graph database; Collect service provider information and store it as service provider nodes in the Neo4j graph database; Collect solution information and store it as solution nodes in the Neo4j graph database; Establish an association between service provider nodes and solution nodes to generate a resource knowledge graph.

[0013] Furthermore, the service provider information includes the industry adaptability and scale range of the service provider; the solution information includes the application cases and implementation cycle of the solution.

[0014] In a second aspect, the embodiments of the present application further provide a system for intelligently processing enterprise digital transformation needs based on a large model, including: The demand realization path determination module is used to respond to the digital transformation needs of enterprises and use large models to analyze and determine the enterprise's characteristic parameters and demand realization path; the demand realization path includes determining the demand type, identifying key links, and determining the demand resource tags; The service resource matching module is used to query the pre-built resource knowledge graph and match service resources based on enterprise characteristic parameters and demand implementation paths; the enterprise characteristic parameters include industry attributes and scale; The solution generation module is used to determine the steps that need to be implemented in stages, the service providers and service parameters of the required resources and service resources, as well as the risk points and optimization suggestions during the transformation process based on the matching results, and generate digital transformation solutions; The large model optimization module is used to respond to enterprise feedback on solutions and optimize the large model's demand content parsing process and service resource matching process.

[0015] In a third aspect, an embodiment of the present application further provides an electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the steps of the method for intelligently processing enterprise digital transformation needs based on a large model as described in the first aspect are implemented.

[0016] In a fourth aspect, an embodiment of the present application further provides a storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the method for intelligently processing enterprise digital transformation needs based on a large model as described in the first aspect are implemented.

[0017] It can be seen from the above technical solutions that this application has the following advantages: The intelligent processing method, system, equipment and medium for enterprise digital transformation needs based on big models provided in this application can achieve accurate grasp and efficient response to needs through the analysis and intelligent matching of big models, provide personalized, high-quality solutions, and improve the success rate of enterprise digital transformation; through resource knowledge graphs and comprehensive scoring, improve the matching accuracy and resource utilization of service resources, and reduce the cost of enterprise digital transformation; evaluate and provide optimization suggestions for risk points of solutions, identify and respond to potential risks in advance, and reduce uncertainty in the digital transformation process; optimize and train big models based on enterprise feedback, continuously improve service quality and matching accuracy, and adapt to the ever-changing needs of enterprises; through real-time collection and analysis of enterprise production system data, realize digital evaluation and optimization suggestions for each link of production, and provide data support for enterprise digital transformation. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solution of the present application, the following is a brief introduction to the drawings required for the description. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0019] Figure 1 This is a flow chart of the method for intelligently processing enterprise digital transformation needs based on a large model of the present invention.

[0020] Figure 2 Schematic diagram of the intelligent processing system for enterprise digital transformation needs based on a large model of the present invention. DETAILED DESCRIPTION

[0021] The specific steps of the method for intelligently processing enterprise digital transformation needs based on a large model will be described in detail below, and various embodiments of the present disclosure will be described in more detail. The present disclosure may have various embodiments, and adjustments and changes may be made therein. However, it should be understood that there is no intention to limit the various embodiments of the present disclosure to the specific embodiments disclosed herein, but rather that the present disclosure should be understood to cover all adjustments, equivalents, and / or alternatives that fall within the spirit and scope of the various embodiments of the present disclosure.

[0022] For example, digital transformation is a key means of driving enterprises to improve their competitiveness and product quality. Although there are currently some information service systems on the market that provide resource docking and diagnostic assessment services to assist enterprises in their digital transformation, these systems still have many shortcomings, as follows: On the one hand, information matching is not accurate enough. Most existing information service systems rely on traditional keyword matching or classification retrieval methods, which makes it difficult to accurately understand the actual needs of enterprises. For example, when an enterprise proposes the demand of "improving production efficiency", the system may return a large amount of information that is irrelevant to the demand, resulting in inefficiency in the enterprise's screening of valid information. On the other hand, the service lacks personalization. These systems generally lack dynamic analysis capabilities and are unable to generate personalized solutions based on the industry attributes, scale and other characteristics of the enterprise. For example, when small and medium-sized enterprises conduct digital diagnosis, the platform usually provides a unified diagnostic questionnaire, but cannot be personalized according to the specific situation of the enterprise, making the diagnostic results lack of pertinence.

[0023] In summary, existing information service systems have significant deficiencies in supply-demand matching, service resource knowledge integration, intelligent processing capabilities, and precise processing capabilities, failing to meet the diverse needs of enterprises' digital transformation. Therefore, an intelligent processing approach is urgently needed to improve the accuracy of information matching and the personalization of services, thereby enhancing overall processing efficiency and quality, and better supporting enterprises' digital transformation.

[0024] In response to the above problems, this embodiment provides a method for intelligently processing enterprise digital transformation needs based on a big model. By combining the big model with the knowledge graph, it realizes the intelligent processing of enterprise digital transformation needs, improves the accuracy of demand analysis and the efficiency of resource matching; reduces the uncertainty in the transformation process by implementing path design and risk analysis in stages; utilizes real-time data collection and feedback optimization to enable the information service system to continuously iterate and upgrade to adapt to the dynamic needs of the enterprise.

[0025] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0026] See also Figure 1 The figure is a flowchart of a method for intelligently processing enterprise digital transformation needs based on a large model in a specific embodiment. The method includes the following steps: S1. Respond to the digital transformation needs of enterprises and analyze them using a large model to determine the enterprise's characteristic parameters and the path to fulfilling these needs. This path includes determining the type of needs, identifying key links, and determining the required resource tags. It should be noted that by parsing demand texts through a large model, enterprise characteristics and demand paths are automatically extracted, avoiding the inefficiency and bias of manual analysis; defining demand types and key links, providing guidance for resource matching and solutions, and reducing blind transformation; S2. Query the pre-built resource knowledge graph to match service resources based on the enterprise's characteristic parameters and demand implementation path; the enterprise characteristic parameters include industry attributes and scale; It should be noted that the association query based on the knowledge graph can quickly locate service providers that meet the enterprise characteristics and demand tags, which is more efficient than traditional database retrieval. Service providers are filtered based on enterprise characteristic parameters to ensure that the matching results match the actual needs of the enterprise. S3. Based on the matching results, determine the phased implementation steps, the service providers and service parameters for the required resources and associated service resources, as well as the risk points and optimization suggestions during the transformation process, and generate a digital transformation solution. It should be noted that by breaking down the transformation process into manageable sub-goals through phased implementation, the risk of one-time investment is reduced. Restrictions on service providers, quotations, and cycles facilitate comparison and decision-making by enterprises. By analyzing risk points in the transformation process and proposing optimization suggestions, enterprises can take risk prevention measures in advance, thus reducing the potential risks of digital transformation. S4. Respond to enterprise feedback on solutions and optimize the large model's demand content parsing process and service resource matching process; It should be noted that optimizing and training large models based on enterprise feedback can continuously improve the performance and accuracy of the models, thereby better adapting to the diverse needs of different types of enterprises; by analyzing enterprise feedback, problems in the service process can be discovered and improved in a timely manner, service quality can be improved, and enterprise satisfaction and trust can be enhanced.

[0027] This embodiment uses the semantic understanding ability of the large model to accurately parse the demand text, avoiding the subjectivity and errors of manual interpretation; combining enterprise characteristic parameters with demand paths, it achieves accurate matching of service resources through knowledge graphs and improves resource utilization.

[0028] Furthermore, as a refinement and extension of the specific implementation of the above embodiment, in order to fully illustrate the specific implementation process of this embodiment, another method for intelligently processing enterprise digital transformation needs based on a large model is provided. The method includes the following steps: S1. Respond to the digital transformation needs of enterprises and analyze them using large models to determine the enterprise's characteristic parameters and demand realization paths. This demand realization path includes determining the demand type, identifying key links, and determining the demand resource tags. Specific demand realization paths include: "For equipment transformation needs, the software and hardware transformation points, output of the transformation plan and the corresponding quotation, cycle, and transformation process description"; "For process transformation needs, the description of the position personnel operation modification at the process change, the equipment replacement and operation process changes of the transformation design, the changes in the output of incoming materials and products, and the modification of the logistics coordination link"; and "the quotation list for finished product processing needs, detailed description, and intelligent analysis of the cost risk points required for processing." The specific steps of step S1 are as follows: S11. Receive digital transformation requirements submitted by enterprises in text format; For example, a machinery manufacturing company submitted a request: "We hope to improve the automation level of the production line, reduce manual intervention, and improve production efficiency." S12. Identify the industry attributes, scale, and historical data of the enterprise as enterprise characteristic parameters through the large model; For example, the large model identified that the enterprise belongs to the machinery manufacturing industry, is a medium-sized enterprise, and historical data shows that it has carried out some equipment upgrades; S13. Identify entities in digital transformation requirements through the big model and determine the classification of the required types; For example, the large model identifies the demand type as "equipment automation upgrade"; S14. Use the large model to identify the key links corresponding to the transformation points in the digital transformation requirements, and determine the resource tags required for digital transformation of the key links; For example, the large model identifies the key link as "production line assembly link", and the required resource tags include "automated assembly equipment" and "MES system integration"; S15. Integrate the demand types, key links, and demand resource tags of digital transformation requirements into a structured demand form; For example, the generated structured requirement form is as follows: Requirement type: Equipment automation upgrade Key link: production line assembly link Required resource tags: automated assembly equipment, MES system integration It should be noted that by converting unstructured text into structured forms, subsequent data processing and model analysis are facilitated, improving the efficiency of demand analysis. It not only identifies basic enterprise attributes but also extracts demand types, key links, and resource tags, enabling a precise grasp of demand and providing a foundation for subsequent resource matching and solutions. S2. Based on the enterprise characteristic parameters and the required implementation path, query the pre-built resource knowledge graph to match service resources; the enterprise characteristic parameters include industry attributes and scale; the specific steps of step S2 are as follows: S21. Based on the required resource tags in the structured requirement form, search the resource knowledge graph, select the related service providers, and filter them using enterprise characteristic parameters; For example, based on the required resource tag "automated assembly equipment", the resource knowledge graph is searched to screen out service providers that are suitable for the machinery manufacturing industry; S22. Obtaining historical service cases of the service provider obtained through screening and filtering; For example, by obtaining historical service cases of a service provider, it is found that the provider has provided installation and commissioning services for automated assembly equipment for similar machinery manufacturing companies; S23. Input the text of the digital transformation requirements and the service provider's historical service cases into the big model, extract the text feature vectors through the big model, calculate the cosine similarity, and retain the historical service cases whose cosine similarity exceeds the similarity threshold; For example, after calculation, the large model finds that the cosine similarity between the service provider's historical cases and the current demand is 0.85, which is higher than the set threshold of 0.8, and the case is retained; S24. Obtain the ratings of the service providers of the retained historical service cases, the service provider's quote for the service resource, and the response time. Then, combine the cosine similarity to perform a weighted ranking of each historical service case to obtain a comprehensive score. For example, the service provider has a rating of 4.5 stars, a quote of RMB 1 million, a response time of 1 week, and an overall score of 85 points; S25. Filter the service resources corresponding to the top N historical service cases as candidate resources based on the comprehensive scores; For example, the top three service resources with the highest comprehensive scores are selected as candidate resources; It should be noted that by combining tag retrieval, feature vector matching, and comprehensive scoring, we can achieve multi-dimensional intelligent sorting of service providers to ensure the rationality of matching results; based on large models, we analyze historical service cases to avoid duplication of work and improve the adaptability of solutions; Step S2 also includes the following steps: Pre-built Neo4j graph database; Collect service provider information and store it as service provider nodes in the Neo4j graph database; Collect solution information and store it as solution nodes in the Neo4j graph database; Establishing an association between service provider nodes and solution nodes to generate a resource knowledge graph; the service provider information includes the service provider's industry adaptability and scale range; the solution information includes the solution's application cases and implementation cycle; It should be noted that Neo4j is used to build a resource knowledge graph, which intuitively represents the relationship between service providers and solutions in a graph structure, supports complex related queries, and improves data retrieval efficiency. Service provider and solution information is structured and stored to form a resource knowledge base for enterprise digital transformation, which is convenient for long-term reuse and expansion. S3. Based on the matching results, determine the phased implementation steps, the service providers and service parameters for the required resources and associated service resources, as well as the risk points and optimization suggestions during the transformation process, and generate a digital transformation solution. Step S3 is as follows: S31. Based on the service parameters of the candidate service resources and the enterprise's characteristic parameters, determine the phased implementation steps for digital transformation needs, including the goals, tasks, and timelines for each phase; For example, the first phase goal is to "complete the selection and procurement of automated assembly equipment." The tasks include equipment selection, supplier negotiation, and procurement contract signing, and the time node is to be completed within 1 month. S32. Establish a relationship between the demand resources and candidate service resources, determine the service provider and service parameters, including service content, quotation and cycle; For example, a service provider provides "automated assembly equipment installation and commissioning" services, with a quoted price of RMB 1 million and a cycle of 3 months; S33. Analyze risk points in the digital transformation process based on a large-scale model and provide optimization suggestions for each risk point. For example, the large-scale model analysis found that the risk point was "compatibility issues between equipment and existing production lines," and recommended a small-scale pilot test; S34. Integrate the phased implementation steps, the service providers and service parameters of the demand resources, service resources, risk points, and optimization suggestions into a digital transformation solution and present it to the enterprise in a visual format. For example, the generated solution displays tasks at each stage, service provider information, risk points, and optimization suggestions in the form of charts, helping enterprises to intuitively understand the transformation path; It should be noted that setting phased goals based on enterprise characteristics and resource parameters can reduce the complexity of transformation; analyzing transformation risks through large models and providing optimization suggestions can help enterprises identify potential problems and improve the stability of transformation; presenting solutions in an intuitive form can reduce the cost of understanding for enterprises and promote decision-making efficiency; S4. Respond to enterprise feedback on the solution and optimize the large model's demand content parsing process and service resource matching process. The specific steps of step S4 are as follows: S41. Receive enterprise feedback on digital transformation solutions, including selected solutions, user satisfaction with the solutions, implementation issues, and improvement suggestions; For example, enterprises reported an 80% satisfaction rate with the solution, but during implementation, they discovered that device compatibility issues were more serious than expected; S42. Input the feedback information into the big model, analyze the feedback content through the big model, and extract key features; For example, the key features extracted by the large model are “device compatibility issues” and “extended implementation period”; S43. Adjust the parameters and weights of the large model in the process of demand content analysis and service resource matching based on the extracted key features; For example, the model parameters are adjusted to increase the weight of device compatibility issues and optimize the demand parsing and resource matching algorithms; S44. Use the adjusted parameters and weights to optimize the training of the large model; It should be noted that by dynamically adjusting the parameters of the large model through enterprise feedback, the continuous evolution of demand analysis and resource matching capabilities can be achieved, and the adaptability of the information service system can be improved; the model can be optimized through real business feedback to avoid model rigidity and ensure that the processing results are updated synchronously with the actual needs of the enterprise.

[0029] In one embodiment of the present invention, a possible embodiment is given below to illustrate its specific implementation scheme in a non-limiting manner.

[0030] The following steps are also included: S5. Connect to the enterprise's production system through an API to collect real-time data on the enterprise's digitalization level. Using a large model combined with industry benchmark parameters, the system then assigns a digitalization score to each production process. Root cause analysis is performed on weak production processes with low digitalization scores. A digital transformation requirements document is generated, and steps S1-S4 are then executed to recommend solutions. This digitalization level data includes device connectivity rate, sensor coverage, ERP / MES system coverage, data interface openness, data utilization, and the proportion of digitalized business processes. For example, by connecting to the enterprise production system through an API, data collection is completed in real time, including equipment networking rate, sensor coverage, and ERP / MES system coverage. Using a large model combined with industry benchmark parameters, each production link is scored, and the assembly link's digital score is found to be only 40 points (out of a maximum of 100), completing the digital scoring. Analysis reveals that the weak point of the assembly link is "outdated equipment and lack of automated equipment support," completing the root cause analysis. The requirement text is automatically generated: "Improve the automation level of the assembly link, reduce manual intervention, and improve production efficiency." S1. Respond to the digital transformation needs of enterprises and analyze them using a large model to determine the enterprise's characteristic parameters and the path to fulfilling these needs. This path includes determining the type of needs, identifying key links, and determining the required resource tags. S2. Query the pre-built resource knowledge graph to match service resources based on the enterprise's characteristic parameters and demand implementation path; the enterprise characteristic parameters include industry attributes and scale; S3. Based on the matching results, determine the phased implementation steps, the service providers and service parameters for the required resources and associated service resources, as well as the risk points and optimization suggestions during the transformation process, and generate a digital transformation solution. S4. Respond to enterprise feedback on solutions and optimize the large model's demand content parsing process and service resource matching process; It should be noted that by connecting to the production system through API and collecting digital level data in real time, the upgrade from passive response to demand to active acquisition of demand can be achieved, and the weak links of the enterprise can be identified in advance; digital scoring and root cause analysis can be carried out in combination with industry benchmark parameters to provide enterprises with accurate transformation entry points and reduce trial and error costs.

[0031] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0032] like Figure 2As shown, the following is an embodiment of the enterprise digital transformation demand intelligent processing system based on a big model provided by the embodiment of the present disclosure. This system and the enterprise digital transformation demand intelligent processing method based on a big model in the above-mentioned embodiments belong to the same inventive concept. For details not fully described in the embodiment of the enterprise digital transformation demand intelligent processing system based on a big model, please refer to the embodiment of the above-mentioned enterprise digital transformation demand intelligent processing method based on a big model.

[0033] The system includes: The demand realization path determination module is used to respond to the digital transformation needs of enterprises and use large models to analyze and determine the enterprise's characteristic parameters and demand realization path; the demand realization path includes determining the demand type, identifying key links, and determining the demand resource tags; The service resource matching module is used to query the pre-built resource knowledge graph and match service resources based on enterprise characteristic parameters and demand implementation paths; the enterprise characteristic parameters include industry attributes and scale; The solution generation module is used to determine the steps that need to be implemented in stages, the service providers and service parameters of the required resources and service resources, as well as the risk points and optimization suggestions during the transformation process based on the matching results, and generate digital transformation solutions; The large model optimization module is used to respond to enterprise feedback on solutions and optimize the large model's demand content parsing process and service resource matching process.

[0034] This embodiment realizes the interactive collaboration of the demand implementation path determination module, service resource matching module, solution generation module and large model optimization module to achieve end-to-end automation from demand input to solution output and reduce manual operation errors.

[0035] The method for intelligently processing enterprise digital transformation needs based on a large model provided in the embodiments of the present application can be applied to electronic devices. Those skilled in the art will understand that the electronic device structure involved in the embodiments of the present invention does not constitute a limitation on the electronic device, and the electronic device may include more or fewer components than shown, or combine certain components, or arrange components differently. In the embodiments of the present invention, electronic devices include but are not limited to laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the embodiments of the present application described and / or required herein.

[0036] The electronic device may include a processor, an external memory interface, an internal memory, a universal serial bus (USB) interface, a charging management module, a power management module, a battery, a wireless communication module, an audio module, a speaker, a microphone, a sensor module, a button, a camera, a display, and a SIM card interface, etc.

[0037] It is understood that the structures illustrated in the embodiments of the present application do not constitute specific limitations on the electronic device. In other embodiments of the present application, the electronic device may include more or fewer components than shown, or combine or separate certain components, or arrange the components differently. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0038] A processor may include one or more processing units, such as a central processing unit (CPU), an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural-network processing unit (NPU). Different processing units may be independent devices or integrated into one or more processors.

[0039] The processor can be the nerve center and command center of the electronic device. The controller can generate operation control signals based on the instruction opcode and timing signal to complete the control of instruction fetching and execution.

[0040] The processor may also include a memory for storing instructions and data. In some embodiments, the memory in the processor is a cache memory. This memory can store instructions or data that the processor has just used or is reusing. If the processor needs to use the instruction or data again, it can directly call it from the memory. This avoids repeated accesses, reduces processor latency, and thus improves system efficiency.

[0041] The above-mentioned electronic device realizes the response to the digital transformation needs of enterprises of the intelligent processing method of enterprise digital transformation needs based on big models of this application, and uses big models for analysis to determine the enterprise characteristic parameters and demand realization path; the demand realization path includes determining the demand type, identifying key links and determining the demand resource tags; according to the enterprise characteristic parameters and demand realization path, query the pre-built resource knowledge graph to match service resources; the enterprise characteristic parameters include industry attributes and scale; according to the matching results, determine the steps that need to be implemented in stages, the service providers and service parameters of the demand resources associated with the service resources, and the risk points and optimization suggestions in the transformation process to generate a digital transformation solution; in response to the enterprise's feedback on the solution, a technical solution is used to optimize the demand content parsing process and service resource matching process of the big model, so as to achieve the semantic understanding ability of the big model to accurately parse the demand text and avoid the subjectivity and errors of manual interpretation; combining the enterprise characteristic parameters and the demand path, the knowledge graph is used to achieve accurate matching of service resources, thereby improving the beneficial effect of resource utilization.

[0042] The storage medium provided in this application stores a program product that can implement an intelligent processing method for enterprise digital transformation needs based on a large model.

[0043] The intelligent processing method for enterprise digital transformation needs based on big models includes: responding to enterprise digital transformation needs, and using big models to analyze and determine enterprise characteristic parameters and demand realization paths; the demand realization paths include determining demand types, identifying key links, and determining demand resource tags; according to enterprise characteristic parameters and demand realization paths, querying pre-built resource knowledge graphs to match service resources; the enterprise characteristic parameters include industry attributes and scale; based on the matching results, determining the steps that need to be implemented in stages, the service providers and service parameters of the demand resources associated with the service resources, as well as the risk points and optimization suggestions in the transformation process, to generate digital transformation solutions; in response to enterprise feedback on solutions, optimizing the demand content parsing process and service resource matching process of the big model.

[0044] In some possible implementations, the big model-based intelligent processing method for enterprise digital transformation needs disclosed herein can be implemented in the form of a program product, which includes program code. When the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps described in the above "Exemplary Method" section of this specification according to various exemplary implementations of the present disclosure.

[0045] The storage medium of the present disclosure can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but not limited to, a system, device or component of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0046] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not limited to the embodiments shown herein but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for intelligently processing enterprise digital transformation needs based on a large model, characterized by: The steps include: S1. Respond to the digital transformation needs of enterprises and analyze them using a large model to determine the enterprise's characteristic parameters and the path to fulfilling these needs. This path includes determining the type of needs, identifying key links, and determining the required resource tags. S2. Query the pre-built resource knowledge graph to match service resources based on the enterprise's characteristic parameters and demand implementation path; the enterprise characteristic parameters include industry attributes and scale; S3. Based on the matching results, determine the phased implementation steps, the service providers and service parameters for the required resources and associated service resources, as well as the risk points and optimization suggestions during the transformation process, and generate a digital transformation solution. S4. Respond to enterprise feedback on solutions and optimize the large model demand content parsing process and service resource matching process.

2. The method for intelligently processing enterprise digital transformation needs based on a large model according to claim 1 is characterized in that: The specific steps of step S1 are as follows: S11. Receive digital transformation requirements submitted by enterprises in text format; S12. Identify the industry attributes, scale, and historical data of the enterprise as enterprise characteristic parameters through the large model; S13. Identify entities in digital transformation requirements through the big model and determine the classification of the required types; S14. Use the large model to identify the key links corresponding to the transformation points in the digital transformation requirements, and determine the resource tags required for digital transformation of the key links; S15. Integrate the demand types, key links, and demand resource tags of digital transformation requirements into a structured demand form.

3. The method for intelligently processing enterprise digital transformation needs based on a large model according to claim 2 is characterized in that: The specific steps of step S2 are as follows: S21. Based on the required resource tags in the structured requirement form, search the resource knowledge graph, select the related service providers, and filter them using enterprise characteristic parameters; S22. Obtaining historical service cases of the service provider obtained through screening and filtering; S23. Input the text of the digital transformation requirements and the service provider's historical service cases into the big model, extract the text feature vectors through the big model, calculate the cosine similarity, and retain the historical service cases whose cosine similarity exceeds the similarity threshold; S24. Obtain the ratings of the service providers of the retained historical service cases, the service provider's quote for the service resource, and the response time. Then, combine the cosine similarity to perform a weighted ranking of each historical service case to obtain a comprehensive score. S25. Filter the service resources corresponding to the top N historical service cases as candidate resources based on the comprehensive scores.

4. The method for intelligently processing enterprise digital transformation needs based on a large model according to claim 3 is characterized in that: Step S3 is as follows: S31. Based on the service parameters of the candidate service resources and the enterprise's characteristic parameters, determine the phased implementation steps for digital transformation needs, including the goals, tasks, and timelines for each phase; S32. Establish a relationship between the demand resources and candidate service resources, determine the service provider and service parameters, including service content, quotation and cycle; S33. Analyze risk points in the digital transformation process based on a large-scale model and provide optimization suggestions for each risk point. S34. Integrate the phased implementation steps, service providers and service parameters of demand resources and service resources, as well as risk points and optimization suggestions into a digital transformation solution, and present it to the enterprise in a visual form.

5. The method for intelligently processing enterprise digital transformation needs based on a large model according to claim 4 is characterized in that: The specific steps of step S4 are as follows: S41. Receive enterprise feedback on digital transformation solutions, including selected solutions, user satisfaction with the solutions, implementation issues, and improvement suggestions; S42. Input the feedback information into the big model, analyze the feedback content through the big model, and extract key features; S43. Adjust the parameters and weights of the large model in the process of demand content analysis and service resource matching based on the extracted key features; S44. Use the adjusted parameters and weights to optimize the training of the large model.

6. The method for intelligently processing enterprise digital transformation needs based on a large model according to claim 1 is characterized in that: The following steps are also included: S5. Connect to the enterprise production system through API, collect enterprise digitalization level data in real time, use large models combined with industry benchmark parameters to conduct digital scoring for each production link, conduct root cause analysis for weak production links with low digital scores, generate digital transformation demand text, and then execute steps S1-S4 to recommend solutions.

7. The method for intelligently processing enterprise digital transformation needs based on a large model according to claim 3 is characterized in that: Step S2 also includes the following steps: Pre-built Neo4j graph database; Collect service provider information and store it as service provider nodes in the Neo4j graph database; Collect solution information and store it as solution nodes in the Neo4j graph database; Establish an association between service provider nodes and solution nodes to generate a resource knowledge graph.

8. An intelligent processing system for enterprise digital transformation needs based on a large model, characterized by: include: The demand realization path determination module is used to respond to the digital transformation needs of enterprises and use large models for analysis to determine the enterprise's characteristic parameters and demand realization paths; The demand realization path includes determining the demand type, identifying key links, and determining the demand resource tags; The service resource matching module is used to query the pre-built resource knowledge graph and match service resources based on enterprise characteristic parameters and demand implementation paths; the enterprise characteristic parameters include industry attributes and scale; The solution generation module is used to determine the steps that need to be implemented in stages, the service providers and service parameters of the required resources and service resources, as well as the risk points and optimization suggestions during the transformation process based on the matching results, and generate digital transformation solutions; The large model optimization module is used to respond to enterprise feedback on solutions and optimize the large model's demand content parsing process and service resource matching process.

9. An electronic device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method implements the steps of the method for intelligently processing enterprise digital transformation needs based on a large model as claimed in any one of claims 1 to 7.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for intelligently processing enterprise digital transformation needs based on a large model as described in any one of claims 1 to 7 are implemented.

Images