Data processing method, device, electronic device and computer readable medium

Abstract

The present application discloses a data processing method, device, electronic device and computer-readable medium, and relates to the technical field of big data processing. The method includes: receiving a data processing request, obtaining corresponding enterprise data, enterprise identification and evaluation dimension identification; based on the evaluation dimension identification, extracting corresponding evaluation features from enterprise data, and then generating an enterprise portrait corresponding to the enterprise identification; matching the enterprise portrait with the evaluation index information of the target project to determine the matching degree between the enterprise corresponding to the enterprise portrait and the target project; in response to the matching degree being less than a preset threshold, calling an adjustment program to adjust the evaluation index information until the matching degree is greater than the preset threshold, determining the target enterprise among each enterprise and outputting it; in response to the matching degree being greater than the preset threshold, determining the target enterprise among each enterprise according to the matching degree and outputting it. Balance competition and bidding, ensure good transaction conditions, ensure the safe construction of construction projects and improve the level of supervision.

Description

Technical Field

[0001] The present application relates to the field of big data processing technology, and in particular to a data processing method, device, electronic device and computer-readable medium. Background Art

[0002] Obtaining engineering projects through bidding is the fairness of the market economy. The fundamental reason why the market can play an important and even decisive role in resource allocation is that the competition mechanism can fully mobilize the enthusiasm of all parties. However, there are obvious problems with competition and bidding at present.

[0003] With the deepening of bidding and procurement work, bidding has become increasingly complex and has become a professional discipline integrating law, economics, management and technology. Bidding is only a tool for construction project procurement, and using this tool does not necessarily mean good procurement results.

[0004] In the process of implementing this application, the inventors found that there are at least the following problems in the prior art:

[0005] Obtaining engineering projects through bidding is only a tool for construction engineering procurement, and the final transaction conditions and results are poor. Summary of the invention

[0006] In view of this, the embodiments of the present application provide a data processing method, device, electronic device and computer-readable medium, which can solve the problem that the existing project acquisition through bidding is only a tool for construction project procurement, and the final transaction conditions and results are poor.

[0007] To achieve the above objective, according to one aspect of an embodiment of the present application, a data processing method is provided, including:

[0008] Receive data processing requests and obtain corresponding enterprise data, enterprise identification and evaluation dimension identification;

[0009] Based on the evaluation dimension identification, the corresponding evaluation features are extracted from the enterprise data, and then the enterprise portrait corresponding to the enterprise identification is generated according to the evaluation features;

[0010] Match the enterprise profile with the evaluation index information of the target project to determine the matching degree between the enterprise corresponding to the enterprise profile and the target project;

[0011] In response to the matching degree being less than a preset threshold, an adjustment program is called to adjust the evaluation index information based on a preset gradient adjustment strategy until the matching degree between the enterprise corresponding to the enterprise portrait and the target project is greater than a preset threshold, and a target enterprise among the enterprises is determined and output according to the matching degree greater than the preset threshold;

[0012] In response to the matching degree being greater than a preset threshold, a target enterprise among the enterprises is determined according to the matching degree and outputted.

[0013] Optionally, a corporate profile corresponding to the corporate identity is generated based on the evaluation features, including:

[0014] Determine the number of times the evaluation feature appears in the enterprise data;

[0015] Determine the feature weight corresponding to the evaluation feature according to the number of times;

[0016] Generate enterprise portraits based on evaluation features and feature weights.

[0017] Optionally, the enterprise profile is matched with the evaluation index information of the target project, including:

[0018] Perform word embedding processing on each enterprise portrait to generate a vector for each enterprise portrait;

[0019] Perform word embedding processing on the evaluation index information of the target project to generate an evaluation index information vector;

[0020] Calculate the similarity between each enterprise portrait vector and the evaluation index information vector.

[0021] Optionally, generating a portrait vector of each enterprise includes:

[0022] Perform word embedding processing on the evaluation features corresponding to each enterprise portrait to generate each evaluation feature vector;

[0023] The evaluation feature vectors corresponding to each enterprise portrait are averaged to obtain the corresponding enterprise portrait vector.

[0024] Optionally, determining the matching degree between the enterprise corresponding to the enterprise profile and the target project includes:

[0025] Each similarity is determined as the matching degree between the enterprise corresponding to the corresponding enterprise portrait and the target project.

[0026] Optionally, before calling the adjustment program to adjust the evaluation index information based on a preset gradient adjustment strategy until the matching degree between the enterprise corresponding to the enterprise portrait and the target project is greater than a preset threshold, the method further includes:

[0027] Determine the similarity between each evaluation feature vector corresponding to the enterprise portrait corresponding to the matching degree less than the preset threshold and the evaluation index information vector, and then determine the evaluation feature vector with the similarity less than the preset similarity threshold as the target evaluation feature vector;

[0028] The information in the evaluation index information corresponding to the target evaluation feature vector is determined as the evaluation index information to be adjusted.

[0029] Optionally, calling an adjustment program to adjust the evaluation index information based on a preset gradient adjustment strategy until the matching degree between the enterprise corresponding to the enterprise portrait and the target project is greater than a preset threshold value includes:

[0030] The adjustment program is called to adjust the evaluation index information to be adjusted based on the preset gradient adjustment strategy until the matching degree between the enterprise corresponding to the enterprise portrait and the target project is greater than the preset threshold.

[0031] In addition, the present application also provides a data processing device, including:

[0032] A receiving unit is configured to receive a data processing request and obtain corresponding enterprise data, enterprise identification and evaluation dimension identification;

[0033] The enterprise portrait generation unit is configured to extract corresponding evaluation features from the enterprise data based on the evaluation dimension identifier, and then generate an enterprise portrait corresponding to the enterprise identifier according to the evaluation features;

[0034] A matching degree determination unit is configured to match the enterprise profile with the evaluation index information of the target project to determine the matching degree between the enterprise corresponding to the enterprise profile and the target project;

[0035] An adjustment unit is configured to, in response to the matching degree being less than a preset threshold, call an adjustment program to adjust the evaluation index information based on a preset gradient adjustment strategy until the matching degree between the enterprise corresponding to the enterprise profile and the target project is greater than a preset threshold, and determine and output a target enterprise among the enterprises according to the matching degree greater than the preset threshold;

[0036] The output unit is configured to determine and output a target enterprise among the enterprises according to the matching degree in response to the matching degree being greater than a preset threshold.

[0037] Optionally, the enterprise portrait generation unit is further configured to:

[0038] Determine the number of times the evaluation feature appears in the enterprise data;

[0039] Determine the feature weight corresponding to the evaluation feature according to the number of times;

[0040] Generate enterprise portraits based on evaluation features and feature weights.

[0041] Optionally, the matching degree determination unit is further configured to:

[0042] Perform word embedding processing on each enterprise portrait to generate a vector for each enterprise portrait;

[0043] Perform word embedding processing on the evaluation index information of the target project to generate an evaluation index information vector;

[0044] Calculate the similarity between each enterprise portrait vector and the evaluation index information vector.

[0045] Optionally, the matching degree determination unit is further configured to:

[0046] Perform word embedding processing on the evaluation features corresponding to each enterprise portrait to generate each evaluation feature vector;

[0047] The evaluation feature vectors corresponding to each enterprise portrait are averaged to obtain the corresponding enterprise portrait vector.

[0048] Optionally, the matching degree determination unit is further configured to:

[0049] Each similarity is determined as the matching degree between the enterprise corresponding to the corresponding enterprise portrait and the target project.

[0050] Optionally, the adjustment unit is further configured to:

[0051] Determine the similarity between each evaluation feature vector corresponding to the enterprise portrait corresponding to the matching degree less than the preset threshold and the evaluation index information vector, and then determine the evaluation feature vector with the similarity less than the preset similarity threshold as the target evaluation feature vector;

[0052] The information in the evaluation index information corresponding to the target evaluation feature vector is determined as the evaluation index information to be adjusted.

[0053] Optionally, the adjustment unit is further configured to:

[0054] The adjustment program is called to adjust the evaluation index information to be adjusted based on the preset gradient adjustment strategy until the matching degree between the enterprise corresponding to the enterprise portrait and the target project is greater than the preset threshold.

[0055] In addition, the present application also provides a data processing electronic device, including: one or more processors; a storage device for storing one or more programs, when the one or more programs are executed by one or more processors, the one or more processors implement the data processing method as described above.

[0056] In addition, the present application also provides a computer-readable medium on which a computer program is stored, and when the program is executed by a processor, the data processing method as described above is implemented.

[0057] To achieve the above objective, according to another aspect of the embodiments of the present application, a computer program product is provided.

[0058] A computer program product according to an embodiment of the present application includes a computer program, and when the program is executed by a processor, the data processing method provided by the embodiment of the present application is implemented.

[0059] One embodiment of the above invention has the following advantages or beneficial effects: the application obtains corresponding enterprise data, enterprise identification and evaluation dimension identification by receiving a data processing request; based on the evaluation dimension identification, extracts corresponding evaluation features from the enterprise data, and then generates an enterprise portrait corresponding to the enterprise identification according to the evaluation features; matches the enterprise portrait with the evaluation index information of the target project to determine the matching degree between the enterprise corresponding to the enterprise portrait and the target project; in response to the matching degree being less than a preset threshold, calls an adjustment program to adjust the evaluation index information based on a preset gradient adjustment strategy until the matching degree between the enterprise corresponding to the enterprise portrait and the target project is greater than a preset threshold, determines the target enterprise among the enterprises according to the matching degree greater than the preset threshold and outputs it; in response to the matching degree being greater than the preset threshold, determines the target enterprise among the enterprises according to the matching degree and outputs it. The enterprise portrait is applied to the bidding scenario, by constructing the enterprise portrait and matching it with the evaluation index information of the target project in the bidding, when all the enterprise portraits do not match, by adjusting the requirements for the qualification conditions of the supplier enterprise in the evaluation index information, technical parameters, scoring methods and evaluation factors, contract terms, etc., so as to find an appropriate balance between meeting its own needs and promoting reasonable competition. This will balance competition and bidding, ensure good transaction conditions and results, ensure the safe construction of construction projects and improve the level of supervision.

[0060] The further effects of the above-mentioned non-conventional optional manner will be described below in conjunction with the specific implementation manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] The accompanying drawings are used to better understand the present application and do not constitute an improper limitation on the present application.

[0062] Figure 1 is a schematic diagram of the main flow of the data processing method according to the first embodiment of the present application;

[0063] Figure 2 is a schematic diagram of the main flow of the data processing method according to the second embodiment of the present application;

[0064] Figure 3 is a schematic diagram of an application scenario of a data processing method according to a third embodiment of the present application;

[0065] Figure 4 is a schematic diagram of main units of a data processing device according to an embodiment of the present application;

[0066] Figure 5 is an exemplary system architecture diagram to which the embodiments of the present application can be applied;

[0067] Figure 6 It is a structural diagram of a computer system of a terminal device or server suitable for implementing an embodiment of the present application. DETAILED DESCRIPTION

[0068] The following is a description of exemplary embodiments of the present application in conjunction with the accompanying drawings, including various details of the embodiments of the present application to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present application. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description. The acquisition, storage, use, and processing of data in the technical solution of the present application are in compliance with the relevant provisions of national laws and regulations.

[0069] Figure 1 is a schematic diagram of the main flow of the data processing method according to the first embodiment of the present application, such as Figure 1 As shown, the data processing method includes:

[0070] Step S101, receiving a data processing request, and obtaining corresponding enterprise data, enterprise identification and evaluation dimension identification.

[0071] In this embodiment, the execution subject of the data processing method (for example, it can be a server) extracts the corresponding evaluation features from the enterprise data based on the evaluation dimension identifier, and then generates the enterprise picture corresponding to the enterprise identifier according to the evaluation features. The data processing request can be received through a wired connection or a wireless connection. Specifically, the data processing request can be a request to determine the target enterprise that matches the bidding project from the enterprises corresponding to the numerous enterprise data. Specifically, after receiving the data processing request, the execution subject can obtain data such as enterprise reporting and enterprise credit by embedding JS code in the page, and obtain the clickstream log data generated on each server, and further obtain business data in the database (such as basic enterprise information, enterprise credit information, enterprise financial information, etc.) and external data that is beneficial to data analysis. External data includes customer feedback data, market research data, industry scale data, etc. The specific content of the external data is not limited in this embodiment of the application.

[0072] Specifically, bidding is a form of comprehensive economic responsibility system to promote competition in the field of capital construction. Several construction units participate in the project bidding, and the bidding enterprise (i.e. the enterprise responsible for construction) is selected on a merit basis. The project task is awarded to the one with the shortest construction period, the lowest cost, the highest quality and the best reputation. The construction unit signs a contract with the contracting unit, and the project is organized in a turnkey manner.

[0073] After receiving the data processing request, the execution entity can also obtain the enterprise identification and evaluation dimension identification carried in the request. Among them, the enterprise identification can be the name of each enterprise participating in the bidding (such as enterprise A, enterprise B, etc.) or code (such as 01, 02, etc.). The evaluation dimension identification represents the dimension in which the bidding enterprise evaluates each bidding enterprise, that is, from which aspects the bidding enterprise is evaluated to determine the final target bidding enterprise.

[0074] Step S102, based on the evaluation dimension identifier, extract the corresponding evaluation features from the enterprise data, and then generate an enterprise portrait corresponding to the enterprise identifier according to the evaluation features.

[0075] After obtaining the evaluation dimension identifier, the execution entity can extract the evaluation features corresponding to the evaluation dimension identifier from the enterprise data. For example, the evaluation dimension identifier can be CWBB, XY, RL, etc., representing financial statements, credit, and manpower, respectively. The embodiment of the present application does not specifically limit the content contained in the evaluation dimension identifier. The execution entity can call the feature extraction model to extract evaluation features such as financial statements, credit, and manpower from the enterprise data based on the evaluation dimension identifier, and generate enterprise portraits corresponding to each enterprise identifier according to the extracted evaluation features and the weights of the evaluation features. The enterprise portrait is a corporate portrait for the bidding project. Generating a corporate portrait can more accurately judge the matching degree of each bidding enterprise, so as to ensure that good transaction conditions and transaction results are finally obtained. The transaction result may refer to the target bidding enterprise that is finally obtained being able to complete the construction of the bidding project with guaranteed quality.

[0076] Step S103, matching the enterprise portrait with the evaluation index information of the target project to determine the matching degree between the enterprise corresponding to the enterprise portrait and the target project.

[0077] After obtaining the corporate portraits of the bidding companies corresponding to each corporate identity, the executive entity can match each corporate portrait with the evaluation index information of the target project (i.e., the bidding project). The evaluation index information of the target project includes the requirements for the qualification conditions of the bidding company, technical parameters, scoring methods and evaluation factors, contract terms and other information. The embodiment of the present application does not specifically limit the specific content of the evaluation index information of the target project, and can be adjusted in real time according to actual conditions.

[0078] The execution entity can first convert the evaluation index information of each enterprise portrait and the target project into vectors by word embedding method, and then calculate the similarity between the vector corresponding to each enterprise portrait and the vector corresponding to the evaluation index information, that is, the matching degree.

[0079] Specifically, the enterprise portraits are matched with the evaluation index information of the target project, including: performing word embedding processing on each enterprise portrait to generate each enterprise portrait vector; performing word embedding processing on the evaluation index information of the target project to generate an evaluation index information vector; and calculating the similarity between each enterprise portrait vector and the evaluation index information vector.

[0080] Specifically, calculating the similarity between each enterprise portrait vector and the evaluation index information vector may be calculating the cosine similarity, Mahalanobis distance, Langmuir distance, etc. of each enterprise portrait vector and the evaluation index information vector. The embodiment of the present application does not specifically limit the method for calculating the similarity.

[0081] After matching the evaluation index information of each enterprise portrait with the target project, the executing entity can obtain the matching degree between each enterprise portrait and the target project.

[0082] Specifically, the generation of each enterprise portrait vector includes:

[0083] The evaluation features corresponding to each enterprise portrait are word-embedded to generate evaluation feature vectors; each enterprise portrait is obtained based on the evaluation features extracted from the enterprise data of each enterprise. The execution subject can convert the evaluation features corresponding to each enterprise into evaluation feature vectors, and then obtain the enterprise portrait vector of the corresponding enterprise based on each evaluation feature vector. Specifically, the execution subject can average the evaluation feature vectors corresponding to each enterprise portrait (for example, {9,17}) to obtain the corresponding enterprise portrait vector (for example, {9,17}). Of course, the execution subject can also determine the median (for example, {9,19}) or mode (for example, {10,18}) of the evaluation feature vector corresponding to each enterprise portrait as the enterprise portrait vector of the corresponding enterprise.

[0084] Specifically, determining the degree of match between the enterprise corresponding to the enterprise portrait and the target project includes: determining each similarity (for example, 0.80, 0.90, 0.99) as the degree of match between the enterprise corresponding to the corresponding enterprise portrait and the target project.

[0085] Step S104, in response to the matching degree being less than a preset threshold, calls an adjustment program to adjust the evaluation index information based on a preset gradient adjustment strategy until the matching degree between the enterprise corresponding to the enterprise portrait and the target project is greater than a preset threshold, and determines the target enterprise among the enterprises based on the matching degree greater than the preset threshold and outputs it.

[0086] For example, the executing entity may adjust the qualification requirements, technical parameters, scoring methods and evaluation factors, contract terms, etc. for the supplier enterprise (that is, the bidding enterprise, that is, the enterprise corresponding to the enterprise identifier corresponding to the data processing request) in the bidding documents in order to find an appropriate balance between meeting its own needs and promoting reasonable competition.

[0087] When the execution subject determines that the matching degree of all bidding enterprises and the target project has not reached the requirement (that is, none of them have reached the preset threshold), the execution subject can call the adjustment program to adjust the evaluation index information of the target project based on the preset gradient adjustment strategy, and continue to execute the matching process of each enterprise portrait and the evaluation index information of the continuously adjusted target project, until there is an enterprise portrait that matches the evaluation index information of the adjusted target enterprise. For example, the information corresponding to gradient 1 (such as qualification condition 1) is adjusted for a certain evaluation index information (such as the qualification conditions of the supplier). If there is no matching enterprise portrait, the information corresponding to gradient 2 (such as qualification condition 2) of the evaluation index information is continued to be adjusted until a matching enterprise portrait appears. Thus, the target enterprise (that is, the enterprise corresponding to the enterprise portrait and the enterprise whose matching degree with the target project is greater than the preset threshold) that best meets the evaluation index information of the target project can be screened out from each candidate bidding enterprise to ensure the realization of better transaction conditions and transaction results. It can be understood that there can be one or more target enterprises, and the embodiment of the present application does not specifically limit the number of target enterprises.

[0088] Specifically, before calling the adjustment program to adjust the evaluation index information based on a preset gradient adjustment strategy until the matching degree between the enterprise corresponding to the enterprise portrait and the target project is greater than a preset threshold, the method also includes: determining the similarity between each evaluation feature vector corresponding to the enterprise portrait corresponding to the matching degree less than the preset threshold and the evaluation index information vector, and then determining the evaluation feature vector with a similarity less than the preset similarity threshold as the target evaluation feature vector; and determining the information in the evaluation index information corresponding to the target evaluation feature vector as the evaluation index information to be adjusted.

[0089] In the embodiment of the present application, before the execution subject adjusts the evaluation index information of the target project, it can first determine the information to be adjusted in the evaluation index information. Specifically, it can be determined that the enterprise portrait with the largest matching degree in the enterprise portrait with a matching degree less than a preset threshold, and then the evaluation feature vectors corresponding to the enterprise portrait with the largest matching degree are calculated with the evaluation index information vector for similarity calculation, and the evaluation feature vector with the calculated similarity less than the preset threshold is determined as the target feature vector, such as the feature vector corresponding to the financial statements corresponding to the enterprise, so that the information corresponding to the target evaluation feature vector in the evaluation index information (such as the qualification information of the supplier enterprise corresponding to the financial statements of the enterprise in the evaluation index information) is determined as the evaluation index information to be adjusted. It can be understood that the evaluation index information to be adjusted can be one or more, and the embodiment of the present application does not specifically limit the number of evaluation index information to be adjusted, and does not specifically limit the timing of adjusting the evaluation index information to be adjusted. It can be adjusted at the same time or separately at different preset times.

[0090] Specifically, calling an adjustment program to adjust the evaluation index information based on a preset gradient adjustment strategy until the matching degree between the enterprise corresponding to the enterprise portrait and the target project is greater than a preset threshold, including: calling an adjustment program to adjust the evaluation index information to be adjusted based on a preset gradient adjustment strategy until the matching degree between the enterprise corresponding to the enterprise portrait and the target project is greater than a preset threshold.

[0091] Step S105 , in response to the matching degree being greater than a preset threshold, a target enterprise among the enterprises is determined according to the matching degree and outputted.

[0092] When the executing entity determines that there is a match between the enterprise portrait of each enterprise and the evaluation index information of the target project, that is, when the degree of match between the enterprise portrait of each enterprise and the evaluation index information of the target project is greater than a preset threshold, the enterprise corresponding to the matching degree greater than the preset threshold can be determined as the target enterprise and output.

[0093] This embodiment receives a data processing request to obtain corresponding enterprise data, enterprise identification and evaluation dimension identification; based on the evaluation dimension identification, extracts corresponding evaluation features from enterprise data, and then generates an enterprise portrait corresponding to the enterprise identification according to the evaluation features; matches the enterprise portrait with the evaluation index information of the target project to determine the matching degree between the enterprise corresponding to the enterprise portrait and the target project; in response to the matching degree being less than a preset threshold, calls an adjustment program to adjust the evaluation index information based on a preset gradient adjustment strategy until the matching degree between the enterprise corresponding to the enterprise portrait and the target project is greater than a preset threshold, determines the target enterprise among each enterprise according to the matching degree greater than the preset threshold and outputs it; in response to the matching degree being greater than the preset threshold, determines the target enterprise among each enterprise according to the matching degree and outputs it. The enterprise portrait is applied to the bidding scenario, by constructing an enterprise portrait and matching it with the evaluation index information of the target project in the bidding, when all enterprise portraits do not match, the qualification requirements, technical parameters, scoring methods and evaluation factors, contract terms, etc. of the supplier enterprise in the evaluation index information are adjusted to find an appropriate balance between meeting its own needs and promoting reasonable competition. This will balance competition and bidding, ensure good transaction conditions and results, ensure the safe construction of construction projects and improve the level of supervision.

[0094] Figure 2 is a schematic diagram of the main flow of the data processing method according to the second embodiment of the present application. Figure 2 As shown, the data processing method includes:

[0095] Step S201, receiving a data processing request, and obtaining corresponding enterprise data, enterprise identification and evaluation dimension identification.

[0096] The execution subject can specifically receive the data processing request through airdrop. After receiving the data processing request, the data acquisition address carried in the request can be obtained, and then jump to the data acquisition address to obtain the corresponding enterprise data. Enterprise data may include the credit information of the enterprise, the financial information of the enterprise, the legal person information of the enterprise, etc. The execution subject can also obtain the enterprise identifier (such as the enterprise name or enterprise code, etc.) and the evaluation dimension identifier (such as the financial dimension identifier CW of the enterprise, the credit dimension identifier XY of the enterprise, etc.).

[0097] Step S202: extract corresponding evaluation features from enterprise data based on the evaluation dimension identifier.

[0098] Step S203, determining the number of times the evaluation feature appears in the enterprise data.

[0099] Enterprise data may not exist directly in the form of evaluation features. The execution entity may convert the evaluation features into the data display form in the enterprise data, and then count the number of times the data corresponding to the evaluation features appear in the enterprise data. For example, if the evaluation features are {1,2,3} and the corresponding data is "enterprise credit", the execution entity can count the number of times "enterprise credit" appears in the corresponding enterprise data.

[0100] Step S204: determining the feature weight corresponding to the evaluation feature according to the number of times.

[0101] Step S205, generating a corporate portrait based on the evaluation features and feature weights.

[0102] Corporate portrait, that is, the labeling of corporate information, collects data from various dimensions such as corporate social attributes, financial statements, credit, and human resources, and then characterizes the corporate characteristic data. These characteristics are analyzed and statistically mined to mine potential valuable information, thereby abstracting the overall information picture of a company.

[0103] Corporate portrait is not a simple combination of corporate labels. It needs to be combined with business and projects. The corporate portrait label systems of different businesses and projects are not consistent.

[0104] The enterprise portrait also includes the feature weights of the evaluation features that constitute the enterprise portrait. The feature weights affect the classification of enterprise attributes to ensure accurate classification of enterprise attributes, thereby ensuring that the enterprise portrait based on the evaluation features and feature attributes can play a more accurate role in recommendation and marketing.

[0105] Specifically, for each enterprise data, the execution subject can determine the number of times each evaluation feature in the enterprise data appears in the enterprise data, sort the numbers in descending order, and assign decreasing feature weights to the evaluation features corresponding to each number after sorting. That is, the size of the feature weight is proportional to the number of times the evaluation feature appears in the corresponding enterprise data. Furthermore, for each enterprise corresponding to the enterprise identifier, the execution subject can use the evaluation feature corresponding to the enterprise as a node and the feature weight corresponding to the evaluation feature as a connecting line, and connect each node with the corresponding connecting line to obtain an enterprise portrait.

[0106] Step S206, matching the enterprise portrait with the evaluation index information of the target project to determine the matching degree between the enterprise corresponding to the enterprise portrait and the target project.

[0107] Step S207, in response to the matching degree being less than a preset threshold, calling an adjustment program to adjust the evaluation index information based on a preset gradient adjustment strategy until the matching degree between the enterprise corresponding to the enterprise portrait and the target project is greater than a preset threshold, and determining the target enterprise among the enterprises based on the matching degree greater than the preset threshold and outputting it.

[0108] Step S208, in response to the matching degree being greater than a preset threshold, a target enterprise among the enterprises is determined according to the matching degree and outputted.

[0109] In the embodiments of the present application, by applying the enterprise portrait to the bidding scenario, an enterprise portrait is constructed, and the potential risks of each bidding enterprise in the future are predicted in a timely manner, thereby ensuring the safe construction of the bidding project and improving the level of supervision.

[0110] Figure 3 Schematic diagram of the application scenario of the data processing method according to the third embodiment of the present application. The data processing method of the embodiment of the present application is applied to the data processing scenario in the bidding process. After receiving the data processing request, the execution subject, for example, Figure 3 As shown, the core of the data processing of the embodiment of the present application is: data collection, data storage and analysis, data sharing, and data application. Among them, data collection can obtain the buried point log data file from the business system, obtain the buried point log data file from the Web system, obtain the buried point log data file from the mobile phone App, crawl external data from the external system through a crawler, or obtain manual files from manually sorted data. After the data is collected, it is transmitted to the data storage layer for data storage and analysis via the data acquisition transmission channel. The data storage and analysis can specifically include temporary storage processing, micro-batch / stream processing, and stream processing. Among them, micro-batch processing regularly checks whether there is new data arriving, and then opens a new batch for processing. In the micro-batch processing mode, when a piece of data arrives, it will not be processed immediately. It is necessary to process the previous batch first, and then record the offset of this batch before processing. Stream processing will calculate the data generated at any time.

[0111] Specifically, temporary storage processing is to perform offline data storage through data warehouse technology (Extract-Transform-Load, ETL); micro-batch / stream processing is to perform near-line data storage; and stream processing is to perform real-time data storage.

[0112] Offline data storage is a backup of online data to prevent possible data disasters. Offline data is not often used and is usually far away from system applications. Data on offline storage media is read and written sequentially. When data needs to be read, the tape needs to be rolled to the end and then located. When the written data needs to be modified, all the data needs to be rewritten. Therefore, offline storage has slow access speed and low efficiency. The typical product of offline storage is a tape library, which is relatively cheap.

[0113] Near-line data storage is to store data that is not frequently used or has a low access volume on storage devices with low performance. However, these devices are required to have fast addressing and high transmission rates. Therefore, near-line data storage does not require high performance, but requires relatively good access performance. At the same time, in most cases, since infrequently used data accounts for a relatively large proportion of the total data volume, this also requires that near-line data storage devices have a relatively large capacity. That is, data of different values ​​are stored on storage media with different performance.

[0114] Real-time data storage means that the storage device and the stored data are always kept "online" and can be read by users at will, meeting the data access speed requirements of the computing platform. It is just like the disk storage mode commonly used in PCs. Generally, online storage devices are storage devices such as disks and disk arrays. They are relatively expensive, but have good performance.

[0115] After data storage and analysis, the executing entity can share and apply the analyzed data.

[0116] In the embodiment of the present application, Hive is a data warehouse tool based on Hadoop, which is used for data extraction, conversion, and loading. It is a mechanism that can store, query, and analyze large-scale data stored in Hadoop. The Hive data warehouse tool can map structured data files to a database table, and provides SQL query functions, which can convert SQL statements into MapReduce tasks for execution. The advantage of Hive is that it has a low learning cost, and can implement fast MapReduce statistics through similar SQL statements, making MapReduce simpler without having to develop special MapReduce applications. Hive is very suitable for statistical analysis of data warehouses. Spark is a fast and general computing engine designed specifically for large-scale data processing.

[0117] Among them, data sharing can be used to synchronize various data sources such as business databases and website logs to distributed file systems such as HDFS. For data analysis and calculation on HDFS, the data warehouse tool Hive can be used. Hive has rich data types and built-in functions; ORC file storage format with a very high compression ratio. Very convenient SQL support makes Hive extremely efficient in statistical analysis based on structured data. The execution subject can combine Spark and Hive, and use the computing engine Spark and SparkSQL to do analysis and calculation. Since most businesses cannot directly obtain data from HDFS, a place for data sharing is required. Business systems such as report display and interface calls can be directly accessed from the data sharing layer. Spark SQL is a component applied to Spark. Spark SQL is a distributed parsing engine that can execute Spark tasks through SQL. It can parse the SQL language written by the user into distributed tasks corresponding to RDD. Since Spark is based on memory to process and calculate data sets, its execution speed is very fast. Specifically, Spark Streaming, a distributed, high-throughput, low-latency, and highly reliable real-time computing framework, can be used for data analysis and calculation. The execution entity can schedule and monitor the allocation and operation of all tasks (including data collection tasks, data storage and analysis tasks, data sharing tasks, and data application tasks) based on the task scheduling and monitoring system.

[0118] Among them, data applications can include report display, data analysis, real-time analysis, data mining, machine learning, deep learning and data online services of bidding companies.

[0119] With the rapid development of information technology, data has begun to grow explosively. Storage units have also increased from GB to TB, and even to PB and EB levels. The official websites of construction companies, various government websites, and various websites related to construction have become sources of data for construction companies, which provides data support for corporate portraits and corporate labels. The wide range of data sources determines the diversity of big data forms. Database data is obviously structured data, and some data is not obviously structured, such as files, pictures, audio, video, etc. Big data is generated very quickly and is mainly transmitted through the Internet. In life, every construction company cannot do without the Internet, which means that the operation and operation of construction companies are providing a lot of information to big data every day. And these data need to be processed in a timely manner, otherwise the cost is too high. Based on this situation, big data has very strict requirements on processing speed. A large amount of resources in the server are used to process and calculate data, and many platforms need to achieve real-time analysis. Data is generated all the time, and it is necessary to ensure that the data processing speed is extremely fast to gain an advantage. For the data generated by construction companies, the greatest value of big data lies in mining valuable data for governments, enterprises, and individuals from a large amount of unrelated data of various types, and conducting in-depth analysis through machine learning methods, artificial intelligence methods, or data mining methods to discover the latest operating conditions, and apply them to various links such as bidding, government supervision, and corporate managers, so as to achieve better construction of construction projects, better improve corporate management, and promote healthier and safer development of the construction industry.

[0120] Big data technology can redistribute the value of the industrial chain from modeling all disciplines, calculating engineering quantities, analyzing conflicts among various professional technologies, and providing information symmetry throughout the entire industrial chain, which is more conducive to the construction process of the construction industry and the safe construction of construction projects. The production method of the construction industry, even the construction of an ordinary 9-story residential building, is also faced with the management of massive data. The construction industry must achieve the level of precision in construction, and must arrange every wall and every brick in advance, produce a good layout diagram, and count the number of bricks of various specifications in advance. According to the data, notify the supplier to supply, arrange the transportation team according to the detailed data, and carry out vertical transportation and floor placement according to the marked diagram of the usage of each wall. This also fundamentally reflects the application value of big data technology in the construction industry.

[0121] Big data has been integrated into all aspects of the world, from business technology to medical care, government, education, economy, humanities and other fields of society. By integrating and associating structured data, unstructured data, Internet-collected data, and third-party cooperation data, based on multi-dimensional massive databases, language relationship recognition capabilities and knowledge base representation structures, enterprise data portraits can be constructed in a short period of time to timely predict potential risks in the future. For example: the application of big data in construction companies, through the data analysis of historical engineering projects, the construction level data of different construction types and different labor teams can be obtained, so as to ensure the safe construction of construction projects and improve the government's supervision level.

[0122] In an embodiment of the present application, when the execution subject receives a data processing request, first, it can obtain information such as enterprise reporting and enterprise credit by embedding JS code in the page, and send it to the background record log of the web service; then, the click stream logs generated on each server are aggregated to the HDFS file system in real time or batch. The data source of the HDFS file system can also include click stream data, as well as business data in the database (such as basic enterprise information, enterprise credit information, enterprise financial information, etc.) and external data that is useful for analysis. The collected traffic data is pre-processed by big data technology, such as cleaning, formatting, filtering out dirty data, etc., and the pre-processed data is imported into the corresponding library and table in the big data warehouse. The embodiment of the present application can develop ETL analysis statements according to demand, obtain various statistical results and construction enterprise labels, and visualize the analyzed data. The embodiment of the present application combines big data technology to analyze a large amount of enterprise information and obtain evaluation results, which can enhance the ability of supervision.

[0123] Figure 4 Schematic diagram of the main units of the data processing device according to an embodiment of the present application. Figure 4 As shown, the data processing device 400 includes a receiving unit 401, a corporate portrait generating unit 402, a matching degree determining unit 403, an adjusting unit 404 and an output unit 405.

[0124] The receiving unit 401 is configured to receive a data processing request and obtain corresponding enterprise data, enterprise identification and evaluation dimension identification;

[0125] The enterprise portrait generating unit 402 is configured to extract corresponding evaluation features from the enterprise data based on the evaluation dimension identifier, and then generate an enterprise portrait corresponding to the enterprise identifier according to the evaluation features;

[0126] A matching degree determination unit 403 is configured to match the enterprise profile with the evaluation index information of the target project to determine the matching degree between the enterprise corresponding to the enterprise profile and the target project;

[0127] The adjustment unit 404 is configured to, in response to the matching degree being less than a preset threshold, call an adjustment program to adjust the evaluation index information based on a preset gradient adjustment strategy until the matching degree between the enterprise corresponding to the enterprise profile and the target project is greater than a preset threshold, and determine and output a target enterprise among the enterprises according to the matching degree greater than the preset threshold;

[0128] The output unit 405 is configured to determine and output a target enterprise among the enterprises according to the matching degree in response to the matching degree being greater than a preset threshold.

[0129] In some embodiments, the enterprise portrait generation unit 402 is further configured to: determine the number of times the evaluation feature appears in the enterprise data; determine the feature weight corresponding to the evaluation feature according to the number; and generate the enterprise portrait based on the evaluation feature and the feature weight.

[0130] In some embodiments, the matching degree determination unit 403 is further configured to: perform word embedding processing on each enterprise portrait to generate each enterprise portrait vector; perform word embedding processing on the evaluation index information of the target project to generate an evaluation index information vector; calculate the similarity between each enterprise portrait vector and the evaluation index information vector.

[0131] In some embodiments, the matching degree determination unit 403 is further configured to: perform word embedding processing on the evaluation features corresponding to each corporate portrait to generate each evaluation feature vector; and average the evaluation feature vectors corresponding to each corporate portrait to obtain the corresponding corporate portrait vector.

[0132] In some embodiments, the matching degree determination unit 403 is further configured to: determine each similarity as the matching degree between the enterprise corresponding to the corresponding enterprise portrait and the target project.

[0133] In some embodiments, the adjustment unit 404 is further configured to: determine the similarity between each evaluation feature vector corresponding to the corporate portrait corresponding to a matching degree less than a preset threshold and the evaluation index information vector, and then determine the evaluation feature vector whose similarity is less than the preset similarity threshold as the target evaluation feature vector; determine the information in the evaluation index information corresponding to the target evaluation feature vector as the evaluation index information to be adjusted.

[0134] In some embodiments, the adjustment unit 404 is further configured to: call an adjustment program to adjust the evaluation index information to be adjusted based on a preset gradient adjustment strategy until the matching degree between the enterprise corresponding to the enterprise portrait and the target project is greater than a preset threshold.

[0135] In some embodiments, the receiving unit 401 is further configured to: call the page embedding script program of the target page to obtain the click stream data corresponding to the target page and obtain the business data in the database; and combine the click stream data and the business data into enterprise data.

[0136] It should be noted that the data processing method and the data processing device in the present application have a corresponding relationship in terms of specific implementation content, so the repeated content will not be described again.

[0137] Figure 5 An exemplary system architecture 500 to which the data processing method or data processing device according to the embodiment of the present application can be applied is shown.

[0138] like Figure 5 As shown, system architecture 500 may include terminal devices 501, 502, 503, a network 504 and a server 505. Network 504 is used to provide a medium for communication links between terminal devices 501, 502, 503 and server 505. Network 504 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0139] Users can use terminal devices 501, 502, 503 to interact with server 505 through network 504 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 501, 502, 503, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only as examples).

[0140] The terminal devices 501 , 502 , and 503 may be various electronic devices having a data processing screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

[0141] The server 505 may be a server that provides various services, such as a background management server (only as an example) that provides support for data processing requests submitted by users using terminal devices 501, 502, and 503. The background management server may receive a data processing request, obtain corresponding enterprise data, enterprise identification, and evaluation dimension identification; based on the evaluation dimension identification, extract corresponding evaluation features from the enterprise data, and then generate an enterprise portrait corresponding to the enterprise identification according to the evaluation features; match the enterprise portrait with the evaluation index information of the target project to determine the matching degree between the enterprise corresponding to the enterprise portrait and the target project; in response to the matching degree being less than a preset threshold, call an adjustment program to adjust the evaluation index information based on a preset gradient adjustment strategy until the matching degree between the enterprise corresponding to the enterprise portrait and the target project is greater than a preset threshold, determine the target enterprise among the enterprises according to the matching degree greater than the preset threshold and output it; in response to the matching degree being greater than the preset threshold, determine the target enterprise among the enterprises according to the matching degree and output it. Apply enterprise portraits to bidding scenarios. By building enterprise portraits and matching them with the evaluation index information of target projects in bidding, when all enterprise portraits do not match, adjust the qualification requirements, technical parameters, scoring methods, evaluation factors, contract terms, etc. of supplier enterprises in the evaluation index information to find the appropriate balance between meeting their own needs and promoting reasonable competition. In this way, competition and bidding can be balanced, good transaction conditions and results can be guaranteed, the safe construction of construction projects can be guaranteed, and the level of supervision can be improved.

[0142] It should be noted that the data processing method provided in the embodiment of the present application is generally executed by the server 505 , and accordingly, the data processing device is generally set in the server 505 .

[0143] It should be understood that Figure 5 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0144] Reference below Figure 6 , which shows a schematic diagram of the structure of a computer system 600 of a terminal device suitable for implementing an embodiment of the present application. Figure 6 The terminal device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0145] like Figure 6As shown, the computer system 600 includes a central processing unit (CPU) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage part 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the computer system 600 are also stored. The CPU 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0146] The following components are connected to the I / O interface 605: an input section 606 including a keyboard, a mouse, etc.; an output section 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, a modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I / O interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed, so that a computer program read therefrom is installed into the storage section 608 as needed.

[0147] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 609, and / or installed from the removable medium 611. When the computer program is executed by the central processing unit (CPU) 601, the above-mentioned functions defined in the system of the present application are executed.

[0148] It should be noted that the computer-readable medium shown in the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. Computer-readable storage media may include, for example, but are not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer 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 of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0149] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the above-mentioned module, program segment or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0150] The units involved in the embodiments described in the present application may be implemented by software or hardware. The units described may also be set in a processor, for example, it may be described as: a processor includes a receiving unit, a corporate portrait generation unit, a matching degree determination unit, an adjustment unit, and an output unit. The names of these units do not, in some cases, constitute limitations on the units themselves.

[0151] As another aspect, the present application also provides a computer-readable medium, which may be included in the device described in the above embodiment; or it may exist independently and not be assembled into the device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by a device, the device receives a data processing request, obtains corresponding enterprise data, enterprise identification and evaluation dimension identification; based on the evaluation dimension identification, extracts corresponding evaluation features from the enterprise data, and then generates an enterprise portrait corresponding to the enterprise identification according to the evaluation features; matches the enterprise portrait with the evaluation index information of the target project to determine the matching degree between the enterprise corresponding to the enterprise portrait and the target project; in response to the matching degree being less than a preset threshold, calls an adjustment program to adjust the evaluation index information based on a preset gradient adjustment strategy until the matching degree between the enterprise corresponding to the enterprise portrait and the target project is greater than a preset threshold, determines the target enterprise among the enterprises according to the matching degree greater than the preset threshold and outputs it; in response to the matching degree being greater than the preset threshold, determines the target enterprise among the enterprises according to the matching degree and outputs it.

[0152] The computer program product of the present application includes a computer program, and the computer program implements the data processing method in the embodiment of the present application when executed by a processor.

[0153] According to the technical solution of the embodiment of the present application, the enterprise portrait is applied to the bidding scenario. By constructing the enterprise portrait and matching it with the evaluation index information of the target project in the bidding, when all the enterprise portraits do not match, the qualification requirements, technical parameters, scoring methods and evaluation factors, contract terms, etc. of the supplier enterprise in the evaluation index information are adjusted to find the appropriate balance between meeting its own needs and promoting reasonable competition. In this way, the competition and bidding are balanced, good transaction conditions and results are guaranteed, the safe construction of the construction project is guaranteed, and the supervision level is improved.

[0154] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. A data processing method, characterized in that: include: Receive a data processing request to obtain corresponding enterprise data, enterprise identification and evaluation dimension identification, wherein the data processing request is a request to determine a target enterprise matching a target project from enterprises corresponding to a large number of enterprise data; Based on the evaluation dimension identifier, extract corresponding evaluation features from the enterprise data, and then generate an enterprise portrait corresponding to the enterprise identifier according to the evaluation features; Matching each of the enterprise portraits with the evaluation index information of the target project respectively to determine the matching degree between the enterprise corresponding to each of the enterprise portraits and the target project; In response to the fact that the matching degree between all enterprises and the target project is less than a preset threshold, determine the enterprise portrait with the greatest matching degree among the enterprise portraits with matching degrees less than the preset threshold; perform similarity calculation between each evaluation feature vector corresponding to the enterprise portrait with the greatest matching degree and the evaluation index information vector corresponding to the evaluation index information, determine the evaluation feature vector with the calculated similarity less than the preset threshold as the target evaluation feature vector, and determine the information corresponding to the target evaluation feature vector in the evaluation index information as the evaluation index information to be adjusted; then call an adjustment program to adjust the evaluation index information to be adjusted based on a preset gradient adjustment strategy until the matching degree between the enterprise corresponding to the enterprise portrait and the target project is greater than the preset threshold, and determine the target enterprise among the enterprises according to the matching degree greater than the preset threshold and output it; In response to the matching degree being greater than a preset threshold, a target enterprise among the enterprises is determined according to the matching degree and outputted.

2. The method according to claim 1, characterized in that Generating the enterprise portrait corresponding to the enterprise logo according to the evaluation features includes: Determining the number of times the evaluation feature appears in the enterprise data; Determine a feature weight corresponding to the evaluation feature according to the number of times; Generate a corporate portrait based on the evaluation features and the feature weights.

3. The method according to claim 1, characterized in that: The matching of each of the enterprise portraits with the evaluation index information of the target project to determine the matching degree between the enterprise corresponding to each of the enterprise portraits and the target project includes: Performing word embedding processing on each of the enterprise portraits to generate a vector of each enterprise portrait; Perform word embedding processing on the evaluation index information of the target project to generate an evaluation index information vector; Calculating the similarity between the enterprise portrait vector and the evaluation index information vector; Each similarity is determined as a matching degree between the enterprise corresponding to the corresponding enterprise portrait and the target project.

4. The method according to claim 3, characterized in that: The generating of each enterprise portrait vector comprises: Performing word embedding processing on the evaluation features corresponding to each of the enterprise portraits to generate each evaluation feature vector; The evaluation feature vectors corresponding to each enterprise portrait are averaged to obtain the corresponding enterprise portrait vector.

5. A data processing device, characterized in that: include: A receiving unit is configured to receive a data processing request, and obtain corresponding enterprise data, enterprise identification, and evaluation dimension identification, wherein the data processing request is a request to determine a target enterprise matching a target project from enterprises corresponding to a plurality of enterprise data; An enterprise portrait generating unit is configured to extract corresponding evaluation features from the enterprise data based on the evaluation dimension identifier, and then generate an enterprise portrait corresponding to the enterprise identifier according to the evaluation features; A matching degree determination unit is configured to match each of the enterprise portraits with the evaluation index information of the target project respectively, so as to determine the matching degree between the enterprise corresponding to each of the enterprise portraits and the target project; The adjustment unit is configured to, in response to the matching degree between all enterprises and the target project being less than a preset threshold, determine the enterprise portrait with the greatest matching degree among the enterprise portraits with matching degrees less than the preset threshold; perform similarity calculation between each evaluation feature vector corresponding to the enterprise portrait with the greatest matching degree and the evaluation index information vector corresponding to the evaluation index information, determine the evaluation feature vector with the calculated similarity less than the preset threshold as the target evaluation feature vector, and determine the information corresponding to the target evaluation feature vector in the evaluation index information as the evaluation index information to be adjusted; then call the adjustment program to adjust the evaluation index information to be adjusted based on a preset gradient adjustment strategy until the matching degree between the enterprise corresponding to the enterprise portrait and the target project is greater than the preset threshold, and determine the target enterprise among the enterprises according to the matching degree greater than the preset threshold and output it; The output unit is configured to determine and output a target enterprise among the enterprises according to the matching degree in response to the matching degree being greater than a preset threshold.

6. The device according to claim 5, characterized in that The enterprise portrait generation unit is further configured to: Determining the number of times the evaluation feature appears in the enterprise data; Determine a feature weight corresponding to the evaluation feature according to the number of times; Generate a corporate portrait based on the evaluation features and the feature weights.

7. The device according to claim 5, characterized in that The matching degree determination unit is further configured to: Performing word embedding processing on each of the enterprise portraits to generate a vector of each enterprise portrait; Perform word embedding processing on the evaluation index information of the target project to generate an evaluation index information vector; Calculating the similarity between the enterprise portrait vector and the evaluation index information vector; Each similarity is determined as a matching degree between the enterprise corresponding to the corresponding enterprise portrait and the target project.

8. The device according to claim 7, characterized in that The matching degree determination unit is further configured to: Performing word embedding processing on the evaluation features corresponding to each of the enterprise portraits to generate each evaluation feature vector; The evaluation feature vectors corresponding to each enterprise portrait are averaged to obtain the corresponding enterprise portrait vector.

9. A data processing electronic device, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 4.

10. A computer readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 4 is implemented.

11. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 4 is implemented.

Images