A digital transformation service provider recommendation system and method
Patent Information
- Application Number
- CN202611259322.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-08-19
- Publication Date
- 2026-10-23
AI Technical Summary
综上所述，本发明实施方式提供了一种数字化转型服务商推荐系统及方法，该系统包括：数据处理模块，用于获取企业的多源异构数据并进行数据处理，得到量化需求向量和属性标识向量；企业需求整合模块，用于基于所述量化需求向量进行特征重要性重排，并利用所述属性标识向量进行上下文增强，得到企业的需求特征集；服务商能力特征向量构建模块，用于根据服务商在各技术维度的能力评分，构建服务商的能力特征向量；候选服务商筛选模块，用于基于项目约束条件数据，进行候选服务商筛选，得到候选服务商集合；匹配指数生成模块，用于针对所述候选服务商集合中的各服务商，基于所述企业的需求特征集进行匹配计算，得到匹配指数；推荐结果获取模块，用于基于所述匹配指数得到推荐结果。本发明实施方式提供的技术方案，通过采用逻辑明确的递进式数据处理流程，使得推荐系统的匹配逻辑能够自适应地聚焦于每个企业最独特的需求结构，并且所采用的均为通用数据处理技术，并不依赖于特定的行业知识或商业规则，从客观的技术角度实现了将企业需求和服务商的服务精确匹配，所得到的推荐结果具有较高的客观性、准确性和可靠性。
Smart Images
Figure CN122964556A_ABST
Abstract
Description
Technical Field
[0001] The embodiments of the present invention relate to the field of data processing technology, and in particular to a digital transformation service provider recommendation system and method. Background Technology
[0002] Digital transformation service providers are companies that help enterprises achieve digital transformation, and can provide implementation and integration services for technologies including but not limited to cloud computing, big data, artificial intelligence, and the Internet of Things.
[0003] Currently, there are various digital transformation service providers in the market, but their service advantages and resources differ. Enterprises needing digital transformation also have diverse requirements. How to accurately match enterprise needs with service providers' services, and ensure that this matching is quantifiable and repeatable, has become a pressing issue. Summary of the Invention
[0004] Based on the above-mentioned situation of the prior art, the purpose of the embodiments of the present invention is to provide a digital transformation service provider recommendation system and method, which can achieve accurate matching between enterprise needs and service providers' services, and has quantifiability and repeatability.
[0005] To achieve the above objectives, according to one aspect of the present invention, a digital transformation service provider recommendation system is provided, comprising: The data processing module is used to acquire multi-source heterogeneous data from enterprises and process the data to obtain quantitative demand vectors and attribute identification vectors. The enterprise demand integration module is used to rearrange the importance of features based on the quantified demand vector and use the attribute identifier vector to perform context enhancement to obtain the enterprise's demand feature set. The service provider capability feature vector construction module is used to construct the service provider's capability feature vector based on the service provider's capability scores in various technical dimensions; The candidate service provider screening module is used to screen candidate service providers based on project constraint data to obtain a set of candidate service providers; The matching index generation module is used to perform matching calculations for each service provider in the candidate service provider set based on the enterprise's demand feature set, and obtain a matching index. The recommendation result acquisition module is used to obtain recommendation results based on the matching index.
[0006] Furthermore, the multi-source heterogeneous data includes quantitative indicator data, non-numerical attribute data, and project constraint data; the project constraint data includes periodic constraint data and budget constraint data.
[0007] Furthermore, the quantified demand vector is obtained through the following steps: Obtain the current status value and expected target status value of the enterprise's quantitative indicator data; Calculate the sequence of differences between the quantitative index data from the current state value to the target state value; The difference sequence is normalized to obtain the quantization requirement vector; The attribute identifier vector is obtained through the following steps: The discrete attribute information in the non-numerical attribute data is converted into one-hot encoding or embedding vectors to form attribute identification vectors.
[0008] Furthermore, based on the quantified demand vector, feature importance is reordered, and the attribute identifier vector is used for context enhancement to obtain the enterprise's demand feature set, including: Based on the magnitude of each element value in the quantification demand vector, the feature dimensions of the quantification demand vector are rearranged in descending order of element values to generate a priority rearranged vector. Statistical analysis is performed on the elements of the priority rearranged vector to calculate the median and interquartile range of all elements. According to the preset rules, a corresponding demand level label is generated for each element to form a demand feature vector. Based on the attribute identifier vector, a similar context search is performed in the preset service provider knowledge base to obtain the project group with the highest similarity between the enterprise attribute tag and the current enterprise's attribute identifier vector in all historical projects. The project success attribute tag of the project group is extracted as the context enhancement tag. By integrating the demand feature vector and context-enhanced labels, the enterprise's demand feature set is obtained.
[0009] Furthermore, based on the service provider's capability scores across various technical dimensions, a capability feature vector for the service provider is constructed, including: Obtain service providers' capability ratings across various technical dimensions; The capability scores for each technical dimension are arranged in the same order as the priority rearrangement vector to generate the service provider's capability feature vector.
[0010] Furthermore, based on the project constraint data, candidate service providers are screened to obtain a set of candidate service providers, including: Based on the service provider's historical project cycle data, an assessment of the service provider's transformation cycle capabilities is conducted. Multiple constraints are jointly screened based on project constraint data.
[0011] Furthermore, the joint screening based on multiple constraints according to project constraint data includes: Convert the project constraint data into threshold parameters; The threshold parameter is used as a filtering condition to perform periodic and budget-based screening of all service providers. Service providers that pass both periodic screening and budget screening will form a candidate service provider set.
[0012] Furthermore, a matching index is obtained by performing a matching calculation based on the demand feature set of the enterprise, including: Calculate the similarity between the enterprise's priority rearrangement vector and the service provider's capability feature vector; The similarity is corrected based on the context-enhanced tags to obtain the matching index.
[0013] Furthermore, the similarity is corrected based on the context-enhanced tags to obtain a matching index, including: Obtain the context enhancement tags and their mapping relationship with each technical dimension of the priority rearrangement vector; For each service provider in the candidate service provider set, obtain the project experience in the service provider's historical project records that matches each tag in the context enhancement tags; The percentage of successfully matched tags out of the total number of tags is calculated as the service provider's experience matching rate. The experience matching rate is mapped to a correction coefficient using a preset conversion function; The matching index is obtained by multiplying the similarity by the correction coefficient.
[0014] According to another aspect of the present invention, a method for recommending digital transformation service providers based on the digital transformation service provider recommendation system as described in the first aspect of the present invention is provided, comprising: Acquire multi-source heterogeneous data from enterprises and process the data to obtain quantitative demand vectors and attribute identification vectors; Based on the quantified demand vector, the importance of features is rearranged, and the context is enhanced using the attribute identifier vector to obtain the enterprise's demand feature set. Based on the service provider's capability scores across various technical dimensions, construct the service provider's capability feature vector; Based on the project constraint data, candidate service providers are screened to obtain a set of candidate service providers; For each service provider in the candidate service provider set, a matching index is obtained by matching based on the enterprise's demand feature set; Recommendation results are obtained based on the matching index. In summary, the embodiments of the present invention provide a digital transformation service provider recommendation system and method. The system includes: a data processing module for acquiring and processing multi-source heterogeneous data from enterprises to obtain a quantified demand vector and an attribute identifier vector; an enterprise demand integration module for reordering feature importance based on the quantified demand vector and performing context enhancement using the attribute identifier vector to obtain an enterprise demand feature set; a service provider capability feature vector construction module for constructing a service provider capability feature vector based on the service provider's capability scores in various technical dimensions; a candidate service provider screening module for screening candidate service providers based on project constraint data to obtain a candidate service provider set; a matching index generation module for performing matching calculations on each service provider in the candidate service provider set based on the enterprise's demand feature set to obtain a matching index; and a recommendation result acquisition module for obtaining recommendation results based on the matching index. The technical solution provided by the embodiments of the present invention, by adopting a logically clear progressive data processing flow, enables the matching logic of the recommendation system to adaptively focus on the most unique demand structure of each enterprise. Moreover, the technologies used are all general data processing technologies, which do not rely on specific industry knowledge or business rules. From an objective technical perspective, it achieves accurate matching of enterprise needs and service providers' services, and the resulting recommendation results have high objectivity, accuracy and reliability. Attached Figure Description
[0015] Figure 1 This is a structural block diagram of the digital transformation service provider recommendation system provided in the embodiments of the present invention; Figure 2 This is a flowchart of the digital transformation service provider recommendation method provided in the embodiments of the present invention. Detailed Implementation
[0016] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to specific embodiments and the accompanying drawings. It should be understood that these descriptions are merely exemplary and not intended to limit the scope of the invention. Furthermore, descriptions of well-known structures and techniques are omitted in the following description to avoid unnecessarily obscuring the concept of the invention.
[0017] It should be noted that, unless otherwise defined, the technical or scientific terms used in one or more embodiments of the present invention should have the ordinary meaning understood by one of ordinary skill in the art to which this invention pertains. The terms "first," "second," and similar terms used in one or more embodiments of the present invention do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the element or object listed following the word and its equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect.
[0018] The embodiments of the present invention provide a digital transformation service provider recommendation system. Figure 1 The diagram shows the structural block of the digital transformation service provider recommendation system, such as... Figure 1 As shown, the digital transformation service provider recommendation system of this invention includes a data processing module, an enterprise demand integration module, a service provider capability feature vector construction module, a candidate service provider screening module, a matching index generation module, and a recommendation result acquisition module.
[0019] The data processing module is used to acquire multi-source heterogeneous data from enterprises and process the data to obtain quantitative demand vectors and attribute identification vectors. The enterprise demand integration module is used to reorder the importance of features based on the quantified demand vector and use the attribute identifier vector for context enhancement to obtain the enterprise's demand feature set. The service provider capability feature vector construction module is used to construct the service provider's capability feature vector based on the service provider's capability scores in various technical dimensions; The candidate service provider screening module is used to screen candidate service providers based on project constraint data to obtain a set of candidate service providers; The matching index generation module is used to perform matching calculations for each service provider in the candidate service provider set based on the enterprise's demand feature set, and obtain the matching index. The recommendation result acquisition module is used to obtain recommendation results based on the matching index.
[0020] The functions of each module in the digital transformation service provider recommendation system provided in this invention can be implemented by running a computer program on a controller. The controller includes a processor and a memory, the memory storing the computer program, and the processor executing the computer program to implement the various steps of the digital transformation service provider recommendation method provided in the following embodiments of this invention.
[0021] In addition, the present invention provides a method for recommending digital transformation service providers. This method is based on the digital transformation service provider recommendation system provided in the above embodiments of the present invention. The specific implementation methods and working principles of each module in the digital transformation service provider recommendation system provided in the above embodiments of the present invention are consistent with the steps of the digital transformation service provider recommendation method. Figure 2 The present invention illustrates a method for recommending digital transformation service providers, such as... Figure 2 As shown, the method includes the following steps: S202. Acquire multi-source heterogeneous data from the enterprise and process the data to obtain a quantitative demand vector and an attribute identification vector. This multi-source heterogeneous data includes quantitative indicator data, non-numerical attribute data, and project constraint data.
[0022] S2021a. Obtain the current status and expected target status values of the enterprise's quantitative indicator data. Obtain the enterprise's quantitative indicator data in terms of data management, system architecture, and infrastructure. Specifically, this includes the current status values of data logic integration, data platform coverage, business system cloudification rate, and computing resource utilization. At the same time, obtain the enterprise's expected target status values for these indicators.
[0023] S2021b. Calculate the difference sequence of the above quantitative indicator data from the current state value to the target state value.
[0024] S2021c. Normalize the difference sequence to obtain a quantified demand vector. Normalize the difference sequence to map it to a uniform numerical range to obtain the quantified demand vector. The quantified demand vector reflects the intensity of improvement needed by the enterprise in various technological dimensions.
[0025] S2022. Obtain the enterprise's non-numerical attribute data, including the enterprise's industry category, enterprise size level, and current digital maturity stage. This non-numerical attribute data is discrete attribute information. Based on a pre-defined encoding mapping table, convert this discrete attribute information into one-hot encoding or embedding vectors to form attribute identifier vectors.
[0026] S2023. Obtain project constraint data at the project execution level. This data includes periodic constraints and budget constraints. Periodic constraints may include, for example, the expected transformation completion period and the longest acceptable completion period; budget constraints may include, for example, the acceptable project budget range. Convert this project constraint data into threshold parameters, which will then be used as filtering parameters in subsequent steps.
[0027] S204. Based on the quantified demand vector, the importance of features is rearranged, and the context is enhanced using the attribute identifier vector to obtain the enterprise's demand feature set.
[0028] S2041. Based on the magnitude of each element value in the quantified demand vector, the feature dimensions of the quantified demand vector are rearranged in descending order of element value to generate a priority rearrangement vector. The magnitude of each element value in the quantified demand vector represents the urgency of the enterprise's improvement needs in the corresponding technology dimension. By generating the priority rearrangement vector, the technology dimension with the most urgent improvement needs of the enterprise is placed at the beginning of the vector. Statistical analysis is performed on the elements of the rearranged quantified demand vector, i.e., the priority rearrangement vector, to calculate the median and interquartile range of all elements. According to preset rules, a corresponding demand level label is generated for each element of the quantified demand vector, thus forming a demand feature vector. This demand feature vector is a labeled feature vector of numerical value + level. According to some optional implementation methods, elements with values greater than or equal to the upper quartile are marked as high demand, those between the median and the upper quartile are marked as medium demand, and those below the median are marked as low demand.
[0029] S2042. Based on the attribute identifier vector, perform a similar context search in the preset service provider knowledge base to obtain the project group with the highest similarity between the enterprise attribute tags and the current enterprise's attribute identifier vector among all historical projects. The preset service provider knowledge base stores historical projects, each with a corresponding enterprise attribute tag and a project success attribute tag. From the retrieved similar project groups, extract the project success attribute tags as context enhancement tags. Semantically map each tag in this context enhancement tag to each technical dimension in the requirement feature vector, and label the results of the semantic mapping.
[0030] S2043. Integrate the demand feature vector and context enhancement tags to obtain the enterprise's demand feature set. The main feature vector in this demand feature set is the priority reordering vector, and the context enhancement tags and their mapping relationship with the main feature vector serve as metadata in the demand feature set.
[0031] S206. Based on the service provider's capability scores across various technical dimensions, construct the service provider's capability feature vector. In this step, historical project data from the service provider's knowledge base is aggregated into a standardized capability feature vector aligned with the technical dimensions of the demand feature vector, providing a comparable numerical basis for subsequent matching calculations.
[0032] S2061. Obtain the service provider's capability scores across various technical dimensions. Obtain the service provider's capability scores across various technical dimensions by accessing a pre-defined service provider knowledge base. This knowledge base stores historical project records for each service provider. Each project record includes: the service provider's identifier, the technical dimension involved in the project (this technical dimension corresponds to the technical dimensions in the preceding steps, i.e., the current status values of data logic integration, data platform coverage, business system cloudification rate, and computing resource utilization), the project's achievement rate in that technical dimension (the ratio of the actual improvement value to the target improvement value after project completion), and an indicator indicating whether the project was successful. For each service provider, perform the following aggregation operation: For each technical dimension, extract the achievement rate data for that technical dimension from all historical projects of that service provider; calculate the weighted average of all achievement rates under that technical dimension (the weight is the project's success indicator, with a weight of 1.0 for successful projects and 0.5 for failed projects to reduce the impact of failed projects on capability assessment), obtaining the service provider's individual capability score for that technical dimension.
[0033] S2062. Based on the capability scores for each technical dimension, generate the service provider's capability feature vector. Arrange the individual capability scores for each technical dimension calculated in the above steps according to the same technical dimension order as the priority rearrangement vector in step S2041 to generate the service provider's capability feature vector. This capability feature vector has the same technical dimension order and meaning as the demand feature vector, allowing for element-by-element numerical comparisons in subsequent steps. If a service provider lacks historical data for a particular technical dimension, the capability score for that technical dimension can be set to a preset default benchmark value (e.g., the industry average, which is dynamically calculated based on statistical data from all service providers in that technical dimension).
[0034] S208. Based on the project constraint data, candidate service providers are screened to obtain a set of candidate service providers.
[0035] S2081. Based on the service provider's historical project cycle data, assess the service provider's transformation cycle capability. Extract the historical project cycle data of each service provider from the service provider's knowledge base, calculate the historical average completion cycle of the service provider for similar projects (referring to projects with similar technical dimensions), and use this as the service provider's estimated completion cycle.
[0036] S2082. Perform joint screening based on project constraint data. Using the threshold parameters obtained in step S2023 as filtering conditions, perform cycle screening and budget screening on all service providers. Service providers that pass both cycle screening and budget screening constitute a candidate service provider set. Cycle screening includes eliminating service providers whose estimated completion period is longer than the longest acceptable completion period; budget screening includes extracting the historical project quotation range for each service provider from the service provider knowledge base and eliminating service providers whose quotation range does not intersect with the acceptable project budget range. If the candidate service provider set is empty, the longest acceptable completion period and project budget range can be gradually relaxed according to a preset step size until the candidate set is not empty, and the relaxation amount is recorded as additional explanation of the recommendation results.
[0037] S210. For each service provider in the candidate service provider set, perform matching calculations based on the enterprise's demand feature set to obtain a matching index.
[0038] S2101. Calculate the similarity between the enterprise's demand feature vector and the service provider's capability feature vector. In this embodiment of the invention, weighted cosine similarity is used for calculation. For technology dimensions marked as high demand in the demand feature vector, a high weight coefficient is assigned, with a value range of, for example, [1.2, 1.5]; for technology dimensions marked as medium demand in the demand feature vector, a baseline weight coefficient is assigned, with a value range of, for example, [0.8, 1.0]; for technology dimensions marked as low demand in the demand feature vector, a low weight coefficient is assigned, with a value range of, for example, [0.3, 0.6]. This weight coefficient is dynamically generated based on the demand level label before calculation. The value of the weight coefficient should ensure that the influence of high-demand technology dimensions can dominate the matching structure, while not completely overshadowing the information of other technology dimensions.
[0039] S2102. Correct the similarity based on context-enhanced tags to obtain the matching index. Obtain the context-enhanced tags and their mapping relationship with each technical dimension of the demand feature vector. For each service provider in the candidate service provider set, obtain the project experience in the service provider's historical project records that matches each tag in the context-enhanced tags; calculate the proportion of successfully matched tags to the total number of tags, as the service provider's experience matching rate. Map the experience matching rate to a correction coefficient through a preset conversion function, ranging from [0.95, 1.05]. The preset conversion function can be, for example, a linear mapping function, a sigmoid function, etc. The higher the experience matching rate, the closer the correction coefficient is to 1.05, playing a positive correction role; when the experience matching rate is 0, the correction coefficient is 0.95, playing a negative correction role. Multiply the similarity by the correction coefficient to obtain the matching index.
[0040] S212. Obtain recommendation results based on the matching index. Candidate service providers can be sorted from high to low according to their matching index, and the service provider with the highest ranking can be selected as the final service provider. Alternatively, different dimensions of needs can be selected from the ranking results. This invention does not impose specific limitations here.
[0041] In summary, the embodiments of the present invention relate to a digital transformation service provider recommendation system and method. The system includes: a data processing module for acquiring and processing multi-source heterogeneous data from enterprises to obtain a quantified demand vector and an attribute identifier vector; an enterprise demand integration module for reordering feature importance based on the quantified demand vector and performing context enhancement using the attribute identifier vector to obtain an enterprise demand feature set; a service provider capability feature vector construction module for constructing a service provider capability feature vector based on the service provider's capability scores in various technical dimensions; a candidate service provider screening module for screening candidate service providers based on project constraint data to obtain a candidate service provider set; a matching index generation module for performing matching calculations on each service provider in the candidate service provider set based on the enterprise's demand feature set to obtain a matching index; and a recommendation result acquisition module for obtaining recommendation results based on the matching index. The technical solution provided by the embodiments of the present invention, by adopting a logically clear progressive data processing flow, enables the matching logic of the recommendation system to adaptively focus on the most unique demand structure of each enterprise. Moreover, the technologies used are all general data processing technologies, which do not rely on specific industry knowledge or business rules. From an objective technical perspective, it achieves accurate matching of enterprise needs and service providers' services, and the resulting recommendation results have high objectivity, accuracy and reliability.
[0042] It should be understood that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of the invention (including the claims) is limited to these examples; within the framework of the invention, the technical features of the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of different aspects of one or more embodiments of the invention as described above, which are not provided in the details for the sake of brevity. The specific embodiments of the invention described above are merely illustrative or explanatory of the principles of the invention and do not constitute a limitation of the invention. Therefore, any modifications, equivalent substitutions, improvements, etc., made without departing from the spirit and scope of the invention should be included within the protection scope of the invention. Furthermore, the appended claims are intended to cover all variations and modifications falling within the scope and boundaries of the appended claims, or equivalent forms of such scope and boundaries.
Claims
1. A digital transformation service provider recommendation system, characterized in that, include: The data processing module is used to acquire multi-source heterogeneous data from enterprises and process the data to obtain quantitative demand vectors and attribute identification vectors. The enterprise demand integration module is used to rearrange the importance of features based on the quantified demand vector and use the attribute identifier vector to perform context enhancement to obtain the enterprise's demand feature set. The service provider capability feature vector construction module is used to construct the service provider's capability feature vector based on the service provider's capability scores in various technical dimensions; The candidate service provider screening module is used to screen candidate service providers based on project constraint data to obtain a set of candidate service providers; The matching index generation module is used to perform matching calculations for each service provider in the candidate service provider set based on the enterprise's demand feature set, and obtain a matching index. The recommendation result acquisition module is used to obtain recommendation results based on the matching index.
2. The system according to claim 1, characterized in that, The multi-source heterogeneous data includes quantitative indicator data, non-numerical attribute data, and project constraint data; the project constraint data includes periodic constraint data and budget constraint data.
3. The system according to claim 2, characterized in that, The quantified demand vector is obtained through the following steps: Obtain the current status value and expected target status value of the enterprise's quantitative indicator data; Calculate the sequence of differences between the quantitative index data from the current state value to the target state value; The difference sequence is normalized to obtain the quantization requirement vector; The attribute identifier vector is obtained through the following steps: The discrete attribute information in the non-numerical attribute data is converted into one-hot encoding or embedding vectors to form attribute identification vectors.
4. The system according to claim 3, characterized in that, Based on the quantified demand vector, feature importance is reordered, and context enhancement is performed using the attribute identifier vector to obtain the enterprise's demand feature set, including: Based on the magnitude of each element value in the quantification demand vector, the feature dimensions of the quantification demand vector are rearranged in descending order of element values to generate a priority rearranged vector. Statistical analysis is performed on the elements of the priority rearranged vector to calculate the median and interquartile range of all elements. According to the preset rules, a corresponding demand level label is generated for each element to form a demand feature vector. Based on the attribute identifier vector, a similar context search is performed in the preset service provider knowledge base to obtain the project group with the highest similarity between the enterprise attribute tag and the current enterprise's attribute identifier vector in all historical projects. The project success attribute tag of the project group is extracted as the context enhancement tag. By integrating the demand feature vector and context-enhanced labels, the enterprise's demand feature set is obtained.
5. The system according to claim 4, characterized in that, Based on the service provider's capability scores across various technical dimensions, a capability feature vector is constructed for the service provider, including: Obtain service providers' capability ratings across various technical dimensions; The capability scores for each technical dimension are arranged in the same order as the priority rearrangement vector to generate the service provider's capability feature vector.
6. The system according to claim 5, characterized in that, Based on the project constraint data, candidate service providers are screened to obtain a set of candidate service providers, including: Based on the service provider's historical project cycle data, an assessment of the service provider's transformation cycle capabilities is conducted. Multiple constraints are jointly screened based on project constraint data.
7. The system according to claim 6, characterized in that, The multi-constraint joint screening based on project constraint data includes: Convert the project constraint data into threshold parameters; The threshold parameter is used as a filtering condition to perform periodic and budget-based screening of all service providers. Service providers that pass both periodic screening and budget screening will form a candidate service provider set.
8. The system according to claim 7, characterized in that, A matching index is obtained by performing a matching calculation based on the demand feature set of the aforementioned enterprises, including: Calculate the similarity between the enterprise's priority rearrangement vector and the service provider's capability feature vector; The similarity is corrected based on the context-enhanced tags to obtain the matching index.
9. The system according to claim 8, characterized in that, The similarity is corrected based on the context-enhanced tags to obtain a matching index, including: Obtain the context enhancement tags and their mapping relationship with each technical dimension of the priority rearrangement vector; For each service provider in the candidate service provider set, obtain the project experience in the service provider's historical project records that matches each tag in the context enhancement tags; The percentage of successfully matched tags out of the total number of tags is calculated as the service provider's experience matching rate. The experience matching rate is mapped to a correction coefficient using a preset conversion function; The matching index is obtained by multiplying the similarity by the correction coefficient.
10. A method for recommending digital transformation service providers based on the digital transformation service provider recommendation system as described in any one of claims 1-9, characterized in that, include: Acquire multi-source heterogeneous data from enterprises and process the data to obtain quantitative demand vectors and attribute identification vectors; Based on the quantified demand vector, the importance of features is rearranged, and the context is enhanced using the attribute identifier vector to obtain the enterprise's demand feature set. Based on the service provider's capability scores across various technical dimensions, construct the service provider's capability feature vector; Based on the project constraint data, candidate service providers are screened to obtain a set of candidate service providers; For each service provider in the candidate service provider set, a matching index is obtained by matching based on the enterprise's demand feature set; Recommendation results are obtained based on the matching index.