WO2020029400A1 - Project recommendation method and apparatus, and computer device and storage medium - Google Patents

Abstract

A project recommendation method and apparatus, and a computer device and a storage medium. The method comprises: performing grouping according to enterprise data of multiple enterprises to obtain multiple enterprise groups; analyzing enterprise data in each enterprise group to obtain enterprise feature data corresponding to the enterprise group; and if a project recommendation is required, determining, according to enterprise data of a newly introduced enterprise and the enterprise feature data of the enterprise groups, an enterprise group to which the newly introduced enterprise belongs, and performing project recommendation according to the enterprise group to which the newly introduced enterprise belongs.

Description

Project recommendation method, device, computer equipment and storage medium

This application claims priority from a Chinese patent application filed with the Chinese Patent Office on August 7, 2018, with application number 201810892197.2, and the invention name is "Project Recommended Method, Device, Computer Equipment, and Storage Medium", the entire contents of which are incorporated by reference. In this application.

Technical field

The present application relates to the field of computer technology, and in particular, to an item recommendation method, device, computer equipment, and storage medium.

Background technique

In attracting investment, a newly introduced company generally needs to know which government projects it can apply for. However, currently all eligible government projects are screened manually. This will not only bring a large workload to the staff, but also reduce the screening efficiency, especially when the number of newly introduced enterprises, government projects, etc. is large, the screening efficiency will be lower.

Summary of the invention

This application provides a project recommendation method, device, computer equipment, and storage medium to reduce the time spent in project screening and improve the efficiency of project recommendation.

In a first aspect, the present application provides a project recommendation method, which includes: obtaining enterprise data of a plurality of enterprises; filtering out a predetermined type of enterprise data from the enterprise data of each of the enterprises, and Type of enterprise data is normalized to obtain processed enterprise data; according to a preset clustering algorithm, clustered processing is performed on the processed enterprise data of all the enterprises to divide a plurality of the enterprises into multiple Enterprise groups, wherein each of the enterprise groups includes enterprise data of at least one of the enterprises; and statistical analysis is performed on the enterprise data of all the enterprises in each of the enterprise groups to obtain the correspondence of each of the enterprise groups Enterprise characteristic data of the company; when project recommendation is needed, obtain enterprise data of newly introduced enterprises; determine the enterprise to which the newly introduced enterprises belong according to the enterprise data of the newly introduced enterprises and the enterprise characteristic data of each of the enterprise groups Group; and performing project recommendation to the newly introduced enterprise according to the enterprise group to which the newly introduced enterprise belongs.

In a second aspect, the present application provides an item recommendation device, which includes: a data acquisition unit for acquiring enterprise data of a plurality of enterprises; a normalization unit for filtering out enterprise data of each of the enterprises A preset type of enterprise data, and normalizing the preset type of enterprise data to obtain processed enterprise data; a clustering unit, configured to process all the enterprises according to a preset clustering algorithm Clustering of the subsequent enterprise data to divide a plurality of the enterprises into a plurality of enterprise groups, wherein each of the enterprise groups includes enterprise data of at least one of the enterprises; an analysis unit is configured to Performing statistical analysis on the enterprise data of all the enterprises in the enterprise group to obtain the enterprise characteristic data corresponding to each of the enterprise groups; the data obtaining unit is further configured to obtain the newly introduced enterprise's Enterprise data; a determining unit, configured to determine, according to the enterprise data of the newly introduced enterprises and the enterprise characteristic data of each of the enterprise groups, to which the newly introduced enterprises belong Enterprise group; and a recommendation unit for introducing the new business enterprise group belongs, for the introduction of new business to the item recommendation.

According to a third aspect, the present application further provides a computer device including a memory, a processor, and a computer program stored on the memory and executable on the processor. The processor is implemented when the computer program is executed. The item recommendation method provided by the first aspect.

According to a fourth aspect, the present application also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program, when executed by a processor, causes the processor to execute the first aspect. The item recommendation method described.

The application provides a project recommendation method, device, computer equipment and storage medium. This method performs clustering processing based on historical enterprise data of multiple enterprises to divide the enterprise data of multiple historical enterprises into multiple enterprise groups, and obtains the enterprise characteristic data of each enterprise group through statistical analysis. Of two business groups. When there is a newly introduced company, compare the similarity between the enterprise data of the newly introduced enterprise and the enterprise characteristic data of each enterprise group to find the enterprise group to which the newly introduced enterprise belongs, so as to facilitate the recommendation of the company to the newly introduced enterprise according to the owned enterprise group. Projects that the enterprises in the group have applied for. This method can automatically introduce newly introduced enterprises to classify the enterprise group, and complete the project recommendation according to the belonging enterprise group, which greatly saves the time spent on project screening and improves the efficiency of project recommendation. At the same time, it does not require manual review and saves a lot of labor.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to explain the technical solutions of the embodiments of the present application more clearly, the drawings used in the description of the embodiments are briefly introduced below. Obviously, the drawings in the following description are some embodiments of the present application. For ordinary technicians, other drawings can be obtained based on these drawings without paying creative work.

FIG. 1 is a schematic flowchart of an item recommendation method according to an embodiment of the present application; FIG.

FIG. 2 is a specific schematic flowchart of an item recommendation method according to an embodiment of the present application; FIG.

FIG. 3 is a specific schematic flowchart of an item recommendation method according to an embodiment of the present application; FIG.

FIG. 4 is a specific schematic flowchart of an item recommendation method according to an embodiment of the present application; FIG.

FIG. 5 is a specific schematic flowchart of an item recommendation method according to an embodiment of the present application; FIG.

6 is a schematic block diagram of an item recommendation device according to an embodiment of the present application;

FIG. 7 is a specific schematic block diagram of an item recommendation device according to an embodiment of the present application; FIG.

FIG. 8 is a specific schematic block diagram of an item recommendation device according to an embodiment of the present application; FIG.

FIG. 9 is a specific schematic block diagram of an item recommendation device according to an embodiment of the present application; FIG.

FIG. 10 is a specific schematic block diagram of an item recommendation device according to an embodiment of the present application; FIG.

FIG. 11 is a schematic block diagram of a computer device according to an embodiment of the present application.

detailed description

In the following, the technical solutions in the embodiments of the present application will be clearly and completely described with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, but not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

Please refer to FIG. 1, which is a schematic flowchart of an item recommendation method according to an embodiment of the present application. The project recommendation method can be applied to a project recommendation system. The project recommendation system is installed in a terminal, where the terminal may be a terminal such as a tablet computer, a laptop computer, a desktop computer, or a server. As shown in FIG. 1, the item recommendation method includes steps S101 to S107.

S101. Obtain enterprise data of multiple enterprises.

For example, in order to increase the accuracy of subsequent division of the enterprise group, 1000 companies can be selected and the enterprise data of these 1000 companies can be used as the data object for generating the enterprise group.

In an embodiment, the enterprise data may include enterprise data of quantified data type, enterprise data of category data type, and the like. Among them, the enterprise data of this quantitative data type may be, for example, the total revenue of the enterprise, the net profit, the total number of employees, the registered capital, the amount of projects obtained by government projects, and the like. The enterprise data of the category data type may be, for example, an enterprise name, an industry to which the enterprise belongs, a business category, a project identifier of a government project that the enterprise has applied for, and the like. It can be understood that the specific content of the enterprise data is not limited to the content listed above, and may also include other content, which is not specifically limited here.

S102. Filter out a preset type of enterprise data from the enterprise data of each of the enterprises, and perform normalization processing on the preset type of enterprise data to obtain processed enterprise data.

In this embodiment, the preset type may be, for example, a quantization data type and a category data type. The terminal filters out the enterprise data of a preset type from the enterprise data of each enterprise. For example, the enterprise data such as the total revenue, net profit, and total number of employees are screened from the enterprise data of each enterprise. , Net profit, total number of employees and other units may not be uniform, the magnitude of the number is quite different, so in order to facilitate the subsequent clustering algorithm, first the total revenue, net profit, total number of employees and other quantitative data types of corporate data Normalize the processing to obtain the processed enterprise data corresponding to each enterprise.

S103. Perform cluster processing on the processed enterprise data of all the enterprises according to a preset clustering algorithm to divide a plurality of the enterprises into a plurality of enterprise groups, where each of the enterprise groups includes at least one The enterprise data of the enterprise.

In one embodiment, the preset clustering algorithm may be a K-means clustering algorithm. The terminal performs cluster processing on the processed enterprise data of each enterprise generated in step S102 according to the K-means clustering algorithm, thereby dividing multiple enterprises into multiple enterprise groups. It is understandable that each enterprise group includes enterprise data of at least one enterprise. There is a high degree of similarity between the enterprise data of multiple enterprises in each enterprise group, and a low similarity between the enterprise data of multiple enterprises in different enterprise groups.

In one embodiment, when the preset clustering algorithm is a K-means clustering algorithm, since the K-means clustering algorithm needs to set the enterprise data of K companies as the initial clustering center in advance, therefore, the obtained in step S101 The enterprise data of multiple enterprises may include preset enterprise data of multiple enterprise representatives. That is to say, the developer screens and marks multiple companies as business representatives in advance. In this way, according to a preset clustering algorithm, clustering processing is performed on the processed enterprise data of all the enterprises to divide a plurality of the enterprises into multiple enterprise groups, which specifically includes: The processed enterprise data of a plurality of enterprise representatives is an initial clustering center, and the processed enterprise data of a plurality of the enterprises is clustered to divide the plurality of enterprises into a plurality of enterprise groups.

S104. Perform statistical analysis on the enterprise data of all the enterprises in each of the enterprise groups to obtain enterprise characteristic data corresponding to each of the enterprise groups.

After dividing multiple enterprise groups, statistical analysis is performed on the enterprise data of multiple enterprises in each enterprise group, and then the enterprise characteristic data of each enterprise group can be obtained, that is, the portrait of each enterprise group is obtained.

For example, the A enterprise group includes 10 companies and the corresponding enterprise data of the 10 companies. The company data includes the company's total revenue. Then, the average value of the total revenue of the 10 enterprises can be statistically analyzed, and the average value of the total revenue of the 10 enterprises can be used as the characteristic data of the total enterprise revenue of the A enterprise group. For example, if the average value of the total revenue of 10 companies is 110 million, then the characteristic data of the total revenue in the enterprise characteristic data of the A enterprise group is 110 million.

For another example, if the enterprise data includes the project identifiers of the projects that the company has applied for, the terminal will count the project identifiers of the projects that 10 companies in the A enterprise group have applied for, and calculate the application rate of the project corresponding to each project identifier. . For example, 5 out of 10 companies have applied for the project corresponding to the project identifier “a101”, and 8 have applied for the project corresponding to the project identifier “b201”, then the project corresponding to the “a101” project identifier The application rate is 50%, and the application rate of the project corresponding to the "b201" logo is 80%. After statistically analyzing the application rate of the project corresponding to each project identifier in the A enterprise group, the project identifier with the highest application rate can be selected as the characteristic item identifier in the enterprise characteristic data of the A enterprise group. For example, when the project ID of "b201" is used as the characteristic project ID, it indicates that the enterprise of the A enterprise group has an advantage in applying for the government project of "b201". Of course, it is also possible to select some project identifiers whose application rate meets the preset conditions as the characteristic project identifiers in the enterprise characteristic data of the A enterprise group. For example, the preset condition may be that the application rate is 50% or more, or the preset condition is Among the application rates corresponding to all project identifiers in the A enterprise group, the first 3 corresponding project identifiers with higher application rates are used as characteristic project identifiers of the A enterprise group, and so on. The preset condition can be set according to actual needs. It should be noted that the enterprise characteristic data of the enterprise group is not limited to the above-mentioned total revenue characteristic data and characteristic item identification, and may also include other characteristic data, which is not specifically limited here.

S105. When project recommendation is required, obtain enterprise data of the newly introduced enterprise.

When a newly introduced company wants to know which projects can be applied for, the terminal first obtains the enterprise data of the newly introduced company.

S106. Determine an enterprise group to which the newly introduced enterprise belongs according to the enterprise data of the newly introduced enterprise and enterprise characteristic data of each of the enterprise groups.

Specifically, in an embodiment, as shown in FIG. 2, FIG. 2 is a specific schematic flowchart of an item recommendation method according to an embodiment of the present application. This step S106 specifically includes steps S1061 and S1062.

S1061. Calculate similarities between the enterprise data of the newly introduced enterprises and the enterprise characteristic data of each of the enterprise groups, respectively.

S1062. Acquire the enterprise group with the highest similarity to the enterprise data of the newly introduced enterprise as the enterprise group to which the newly introduced enterprise belongs.

For example, if the terminal is divided into five enterprise groups in step S103, the terminal calculates the similarity between the newly introduced enterprise data and the enterprise characteristic data of the five enterprise groups, and then calculates the five similarities. The enterprise group with the highest degree of similarity is selected as the enterprise group to which the newly introduced enterprise belongs. This completes the operation of tagging newly introduced enterprises according to the enterprise group. For example, assuming that an enterprise characteristic data of an enterprise group to which the newly introduced enterprise belongs is a “technology-based enterprise”, then the method of the present application can quickly determine that the newly introduced enterprise is a technology-based enterprise.

S107. Perform project recommendation to the newly introduced enterprise according to the enterprise group to which the newly introduced enterprise belongs.

After the enterprise group to which the newly introduced enterprise belongs is determined, project recommendation can be made to the newly introduced enterprise according to the owned enterprise group.

Specifically, in an embodiment, as shown in FIG. 3, FIG. 3 is a specific schematic flowchart of an item recommendation method according to an embodiment of the present application. In this embodiment, the enterprise data includes the project identification of the project applied by the enterprise. This step S107 specifically includes steps S1071 and S1072.

S1071. Obtain the identifier of the item to be recommended in the enterprise group to which the newly introduced enterprise belongs.

S1072. Recommend the identifier of the item to be recommended to the newly introduced enterprise to complete the item recommendation.

The identification of the item to be recommended may include the following two situations:

In the first case, the to-be-recommended project identifier may be the project identifier of all projects that have been applied for by an enterprise in the enterprise group to which the newly introduced enterprise belongs. Then, acquiring the identifiers of the items to be recommended in the enterprise group to which the newly-introduced enterprise belongs specifically includes: acquiring the project identifiers of all the projects that have been applied for by the enterprises in the enterprise group to which the newly-introduced enterprise belongs as the identifiers of the items to be recommended.

For example, if the newly-introduced enterprise group includes 10 enterprises, and these 10 enterprises have applied for 30 government projects, then the project identifiers of the 30 government projects can be used as project identifiers to be recommended and recommended to the new Introduce businesses.

In the second case, the identifier of the item to be recommended may also be a characteristic item identifier of the enterprise group. The characteristic item is identified as an enterprise characteristic data of a corresponding enterprise group. The characteristic project identifier may include a project identifier whose project application rate satisfies a preset condition, or may include two or more project identifiers whose project application rate satisfies a preset condition, which is not specifically limited herein. In addition, the preset condition may be, for example, that the characteristic item identification is the project identification corresponding to the item with the highest application rate in the enterprise group; the preset condition may be, for example, that the characteristic item identification is that the application application rate in the enterprise group exceeds a preset threshold The project identifier corresponding to the project, for example, the preset threshold may be 50%; the preset condition may be, for example, the characteristic project identifier is the project identifier corresponding to the first 3 projects with a higher project application rate in the enterprise group. It can be understood that the three preset conditions listed above are only for illustrative purposes and cannot be used to limit the technical solution. The preset conditions can be set according to actual needs.

At this time, obtaining the to-be-recommended item identification in the enterprise group to which the newly-introduced enterprise belongs includes specifically obtaining the characteristic item identification of the enterprise group to which the newly-introduced enterprise belongs as the to-be-recommended item identification. In this way, some project identifiers with a high application rate in the enterprise group to which the newly-introduced enterprise belongs can be recommended to the newly-introduced enterprise, making the project recommendation more targeted and improving the quality and accuracy of the project recommendation.

Of course, the method for project recommendation according to the enterprise group to which the newly introduced enterprise belongs is not limited to the above two methods, and may also be other methods, which are not specifically limited here.

In an embodiment, as shown in FIG. 4, FIG. 4 is a specific schematic flowchart of an item recommendation method provided by an embodiment of the present application. In this embodiment, steps S1073 to S1075 are further included before step S1072.

S1073. Acquire a classification model corresponding to each of the item recommendation identifiers stored in advance.

Generally speaking, each project has project application conditions. Newly introduced companies may not meet the project application conditions corresponding to all project identifications to be recommended. In order to improve the accuracy of project recommendations and the quality of recommended projects, Before the identification recommendation is introduced to the newly introduced enterprise, a classification model corresponding to the identification of each to-be-recommended item stored in advance needs to be obtained. Here, the developer will calculate the project application conditions corresponding to all project IDs in all enterprise groups in advance, and write a corresponding classification model according to the project application conditions corresponding to each project ID, and classify the corresponding classification model for each project ID. Stored in the terminal. The classification model may be a model for classification based on a random forest model.

S1074. Use the classification model to determine whether the enterprise data of the newly introduced enterprise meets the project application conditions of the corresponding project recommendation identifier.

Specifically, the terminal inputs the enterprise data of the newly introduced enterprise as an input value of the classification model into the classification model corresponding to each item to be recommended, and then determines whether the enterprise data of the newly introduced enterprise meets the corresponding identification of the item to be recommended through the classification model. Conditions for project application.

If the enterprise data of the newly introduced company meets the project application conditions of the corresponding project identification to be recommended, step S1072 is executed, that is, the step of recommending the project identification to be recommended to the newly introduced enterprise to complete the project recommendation is performed.

If the enterprise data of the newly introduced enterprise does not meet the project application conditions of the corresponding project identification to be recommended, step S1075 is performed.

S1075. Discard the corresponding identifier of the item to be recommended.

When the project application conditions of the project identifier to be recommended are not met, the corresponding project identifier to be recommended is discarded, that is, the discarded project identifier to be recommended is not recommended to the newly introduced enterprise. In this way, the identification of the items to be recommended can be further filtered, and the quality and accuracy of the recommended items can be improved.

In an embodiment, as shown in FIG. 5, FIG. 5 is a specific schematic flowchart of an item recommendation method according to an embodiment of the present application. In this embodiment, steps S1076 to S1079 are further included before step S1072.

S1076. Obtain enterprise data including the identifier of the item to be recommended from an enterprise group to which the newly introduced enterprise belongs.

S1077. Based on the K nearest neighbor algorithm, obtain K enterprise data with high similarity to the enterprise data of the newly introduced enterprise from the enterprise data including the identifier of the item to be recommended.

S1078. Obtain an item amount corresponding to the item identifier to be recommended from the K enterprise data with high similarity.

S1079. Calculate the average value of the amount of K items as the average item amount of the items to be recommended.

In this embodiment, before recommending the to-be-recommended project identifier to the newly introduced enterprise, it is necessary to obtain the enterprise data of the enterprise corresponding to the to-be-recommended project identifier from the enterprise group to which it belongs, and then calculate and obtain the Among the enterprise data of the company corresponding to the recommended project identifier, the enterprise data of the K companies that have a high degree of similarity to the enterprise data of the newly introduced enterprise, and then obtain the project amount corresponding to the project identifier to be recommended in the enterprise data of the K companies , And then average the project amounts corresponding to the K to-be-recommended project identifiers to obtain an average project amount of each to-be-recommended project identifier.

In this way, when step S1072 is performed, that is, when the recommendation of the to-be-recommended project identifier is recommended to the newly introduced enterprise to complete the project recommendation, step S10721 is specifically performed: the to-be-recommended project identifier and the corresponding average project amount are recommended to The newly introduced companies complete project recommendations. In other words, when sending the to-be-recommended project identifier to the newly introduced company, the average project amount corresponding to the to-be-recommended project identifier is also recommended to the newly-introduced company, so that the newly-introduced company knows how much it can get if it applies for the to-be-recommended project. Of the project amount.

It can be understood that the technical solutions shown in FIG. 4 and FIG. 5 can be integrated in the same embodiment. For example, after executing step S1074, if it is determined that the enterprise data of the newly introduced enterprise meets the corresponding items to be recommended For the identified project application conditions, steps S1076 to S1079 are performed first, and then step S10721 is performed.

The project recommendation method in this embodiment can automatically introduce newly introduced enterprises to classify the enterprise group, and complete the project recommendation based on the projects applied by the enterprises in the enterprise group to which they belong, which greatly saves the time spent in project screening and improves project recommendation. Efficiency, while also improving the quality of recommended items.

An embodiment of the present application further provides an item recommendation device, and the item recommendation device is configured to execute any one of the foregoing item recommendation methods. Specifically, please refer to FIG. 6, which is a schematic block diagram of an item recommendation device according to an embodiment of the present application. The item recommendation device 300 may be installed in a terminal. The terminal may be, for example, a terminal such as a tablet computer, a laptop computer, a desktop computer, or a server.

As shown in FIG. 6, the item recommendation device 300 includes a data acquisition unit 301, a normalization unit 302, a clustering unit 303, an analysis unit 304, a determination unit 305, and a recommendation unit 306.

The data acquiring unit 301 is configured to acquire enterprise data of multiple enterprises.

The normalization unit 302 is configured to filter out enterprise data of a preset type from the enterprise data of each of the enterprises, and perform normalization processing on the enterprise data of the preset types to obtain processed enterprise data.

A clustering unit 303 is configured to perform cluster processing on processed enterprise data of all the enterprises according to a preset clustering algorithm, so as to divide a plurality of the enterprises into a plurality of enterprise groups. The enterprise group includes enterprise data of at least one of the enterprises.

The analysis unit 304 is configured to obtain enterprise characteristic data corresponding to each of the enterprise groups by performing statistical analysis on enterprise data of all the enterprises in each of the enterprise groups.

The data acquiring unit 301 is further configured to acquire enterprise data of a newly introduced enterprise when a project recommendation is required.

A determining unit 305 is configured to determine an enterprise group to which the newly introduced enterprise belongs according to the enterprise data of the newly introduced enterprise and the enterprise characteristic data of each of the enterprise groups.

Specifically, in an embodiment, as shown in FIG. 7, FIG. 7 is a specific schematic block diagram of an item recommendation device provided by an embodiment of the present application. The determination unit 305 includes a similarity calculation sub-unit 3051 and a group acquisition sub-unit 3052.

A similarity calculation subunit 3051 is configured to calculate a similarity between the enterprise data of the newly introduced enterprises and the enterprise characteristic data of each of the enterprise groups, respectively.

The group acquisition subunit 3052 is configured to acquire an enterprise group with the highest similarity to the enterprise data of the newly introduced enterprise as the enterprise group to which the newly introduced enterprise belongs.

The recommendation unit 306 is configured to perform project recommendation to the newly introduced enterprise according to the enterprise group to which the newly introduced enterprise belongs.

Specifically, in an embodiment, as shown in FIG. 8, FIG. 8 is a specific schematic block diagram of an item recommendation device according to an embodiment of the present application. In this embodiment, the enterprise data includes the project identification of the project applied by the enterprise. The recommendation unit 306 includes an identification acquisition subunit 3061 and a recommendation subunit 3062.

The identifier acquisition subunit 3061 is configured to acquire an identifier of an item to be recommended in an enterprise group to which the newly introduced enterprise belongs.

In an embodiment, the identifier acquiring subunit 3061 is specifically configured to acquire the project identifiers of all the projects that have been applied for by the enterprises in the enterprise group to which the newly-introduced enterprise belongs as project identifiers to be recommended.

In another embodiment, the enterprise characteristic data includes a characteristic item identifier, and the characteristic item identifier is an identifier corresponding to a project whose project application rate in the enterprise group meets a preset condition. The identifier obtaining subunit 3061 is specifically configured to obtain a characteristic item identifier of an enterprise group to which the newly-introduced enterprise belongs as an item identifier to be recommended.

A recommendation subunit 3062 is configured to recommend the identifier of the item to be recommended to the newly introduced enterprise to complete the item recommendation.

In an embodiment, as shown in FIG. 9, FIG. 9 is a specific schematic block diagram of an item recommendation device according to an embodiment of the present application. The recommendation unit 306 further includes a model acquisition subunit 3063, a determination subunit 3064, and a discarding unit 3065.

The model acquisition subunit 3063 is configured to acquire a classification model corresponding to each of the to-be-recommended item identifiers stored in advance.

A judging subunit 3064 is configured to judge, through the classification model, whether the enterprise data of the newly introduced enterprise meets a project application condition of a corresponding project identifier to be recommended.

The recommendation subunit 3062 is configured to recommend the to-be-recommended project identifier to the newly-introduced enterprise if the enterprise data of the newly-introduced enterprise meets the project application conditions of the corresponding to-be-recommended project identifier.

The discarding unit 3065 is configured to discard the corresponding to-be-recommended project identifier if the enterprise data of the newly introduced enterprise does not meet the project application conditions of the corresponding to-be-recommended project identifier.

In an embodiment, as shown in FIG. 10, FIG. 10 is a specific schematic block diagram of an item recommendation device provided by an embodiment of the present application. The recommendation unit 306 further includes a data acquisition subunit 3066.

A data acquisition subunit 3066, configured to acquire enterprise data including the identifier of the item to be recommended from the enterprise group to which the newly introduced enterprise belongs; based on the K-nearest neighbor algorithm, acquire from the enterprise data including the identifier of the item to be recommended K enterprise data having a high degree of similarity with the enterprise data of the newly introduced enterprise; obtaining the project amount corresponding to the item identifier to be recommended from the K enterprise data having a high degree of similarity; and calculating K said The average value of the item amounts is taken as the average item amount of the item to be recommended.

At this time, the recommendation subunit 3062 is specifically configured to recommend the identifier of the item to be recommended and the corresponding average item amount to the newly introduced enterprise to complete the item recommendation.

It should be noted that those skilled in the art can clearly understand that the specific implementation process of the above-mentioned item recommendation device 300 and each unit may refer to the corresponding description in the foregoing item recommendation method embodiment. For the convenience and brevity of description, in This will not be repeated here.

The project recommendation device 300 in this embodiment can automatically introduce newly introduced enterprises to classify the enterprise group, and complete the project recommendation based on the projects applied by the enterprises in the enterprise group to which they belong, which greatly saves the time spent in project screening and improves the project. The efficiency of recommendations also improves the quality of recommended items.

The above item recommendation device can be implemented in the form of a computer program, which can be run on a computer device as shown in FIG. 11.

Please refer to FIG. 11, which is a schematic block diagram of a computer device according to an embodiment of the present application. The computer equipment 500 may be a terminal such as a tablet computer, a laptop computer, a desktop computer, or a server.

Referring to FIG. 11, the computer device 500 includes a processor 502, a memory, and a network interface 505 connected through a system bus 501. The memory may include a non-volatile storage medium 503 and an internal memory 504.

The non-volatile storage medium 503 can store an operating system 5031 and a computer program 5032. The computer program 5032 includes program instructions. When the program instructions are executed, the processor 502 can execute an item recommendation method. The processor 502 is used to provide computing and control capabilities to support the operation of the entire computer device 500. The internal memory 504 provides an environment for running the computer program 5032 in the non-volatile storage medium 503. When the computer program 5032 is executed by the processor 502, the processor 502 can execute an item recommendation method. The network interface 505 is used for network communication, such as sending assigned tasks. Those skilled in the art can understand that the structure shown in FIG. 11 is only a block diagram of a part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer equipment 500 to which the scheme of the present application is applied. The specific computer equipment 500 may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

Wherein, the processor 502 is configured to run a computer program 5032 stored in a memory to achieve the following functions: obtaining enterprise data of multiple enterprises; filtering out a predetermined type of enterprise data from the enterprise data of each of the enterprises And performing normalization processing on the preset type of enterprise data to obtain processed enterprise data; according to a preset clustering algorithm, cluster processing is performed on the processed enterprise data of all the enterprises to divide multiple Each of the enterprises is divided into a plurality of enterprise groups, wherein each of the enterprise groups includes enterprise data of at least one of the enterprises; statistical analysis is performed on the enterprise data of all the enterprises in each of the enterprise groups to obtain Enterprise characteristic data corresponding to each of the enterprise groups; when project recommendation is needed, enterprise data of newly introduced enterprises are obtained; and according to the enterprise data of the newly introduced enterprises and the enterprise characteristic data of each of the enterprise groups, the The enterprise group to which the newly-introduced enterprise belongs; and a project recommendation to the newly-introduced enterprise according to the enterprise-group to which the newly-introduced enterprise belongs.

In an embodiment, when the processor 502 executes determining the enterprise group to which the newly introduced enterprise belongs according to the enterprise data of the newly introduced enterprise and the enterprise characteristic data of each of the enterprise groups, the following functions are specifically implemented: calculation The similarity between the enterprise data of the newly introduced enterprises and the enterprise characteristic data of each of the enterprise groups; and acquiring the enterprise group with the highest similarity to the enterprise data of the newly introduced enterprises as the newly introduced enterprises The business group to which it belongs.

In one embodiment, when the processor 502 executes project recommendation to the newly introduced enterprise according to the enterprise group to which the newly introduced enterprise belongs, the processor 502 specifically implements the following function: Recommend a project identification; and recommend the project recommendation to be recommended to the newly introduced enterprise to complete a project recommendation.

In an embodiment, the enterprise characteristic data includes a characteristic item identifier, and the characteristic item identifier is an identifier corresponding to a project whose project application rate in the enterprise group meets a preset condition; the processor 502 executes to obtain the newly introduced data. When identifying an item to be recommended in an enterprise group to which an enterprise belongs, the following function is specifically implemented: acquiring a characteristic item identification of the enterprise group to which the newly introduced enterprise belongs as an identification of the item to be recommended.

In another embodiment, when the processor 502 executes acquiring the to-be-recommended project identifier in the enterprise group to which the newly-introduced enterprise belongs, it specifically implements the following function: acquiring an application that has been applied for by an enterprise in the enterprise group to which the newly-introduced enterprise belongs The project IDs of all projects are used as the project IDs to be recommended.

In one embodiment, before executing the recommendation of the to-be-recommended item identifier to the newly introduced enterprise to complete the item recommendation, the processor 502 also implements the following function: obtaining a pre-stored Classification model; judging by the classification model whether the enterprise data of the newly introduced enterprise meets the project application conditions of the corresponding project identification to be recommended; if the enterprise data of the newly introduced enterprise meets the project application conditions of the corresponding project identification , Performing the step of recommending the identifier of the item to be recommended to the newly introduced enterprise to complete the item recommendation.

In an embodiment, before executing the recommendation of the to-be-recommended project identification to the newly introduced enterprise to complete the project recommendation, the processor 502 also implements the following function: obtaining from the enterprise group to which the newly introduced enterprise belongs includes: The enterprise data of the item identification to be recommended; based on the K-nearest neighbor algorithm, obtaining K enterprise data with high similarity to the enterprise data of the newly introduced enterprise from the enterprise data including the identification of the item to be recommended; from the Obtain the item amount corresponding to the item to-be-recommended item identifier from the K enterprise data with a high degree of similarity; and calculate an average value of the item amount of K to be the average item amount of the item to-be-recommended item identification. Accordingly, when the processor 502 executes recommending the to-be-recommended item identification to the newly introduced enterprise to complete the item recommendation, it specifically implements the following function: recommending the to-be-recommended item identification and the corresponding average item amount to the Newly introduced companies to complete project recommendations.

It should be understood that, in the embodiment of the present application, the processor 502 may be a central processing unit, and the processor 502 may also be other general-purpose processors, digital signal processors, application specific integrated circuits, ready-made programmable gate arrays, or other programmable logic. Devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor, or the processor may be any conventional processor.

A person of ordinary skill in the art can understand that all or part of the processes in the embodiment of the method for project recommendation described above can be completed by instructing related hardware through a computer program. The computer program may be stored in a computer-readable storage medium. The computer program is executed by at least one processor in the computer system to implement the process steps of the embodiment including the item recommendation method as described above.

The computer-readable storage medium may be various media that can store program codes, such as a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a magnetic disk, or an optical disk.

Those of ordinary skill in the art may realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. In several embodiments provided in this application, the disclosed apparatus and method may be implemented in other ways. For example, the device embodiments described above are merely schematic. The division of each unit is only a kind of logical function division. In actual implementation, there can be another division manner. The steps in the method of the embodiment of the present application can be adjusted, combined, and deleted according to actual needs. The units in the apparatus of the embodiment of the present application may be combined, divided, and deleted according to actual needs. In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist separately physically, or two or more units may be integrated into one unit.

When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of this application is essentially a part that contributes to the existing technology, or all or part of the technical solution may be embodied in the form of a software product, which is stored in a storage medium Included are instructions for causing a computer device (which may be a personal computer, a terminal, or a network device, etc.) to perform all or part of the steps of the method described in the embodiments of the present application.

The above is only a specific implementation of this application, but the scope of protection of this application is not limited to this. Any person skilled in the art can easily think of various equivalents within the technical scope disclosed in this application. Modifications or replacements, and these modifications or replacements should be covered by the protection scope of this application. Therefore, the protection scope of this application shall be subject to the protection scope of the claims.

Claims (20)

1. A project recommendation method, which includes:

   Get corporate data from multiple companies;

   Filtering out a preset type of enterprise data from the enterprise data of each said enterprise, and normalizing the preset type of enterprise data to obtain processed enterprise data;

   Perform cluster processing on the processed enterprise data of all the enterprises according to a preset clustering algorithm to divide a plurality of the enterprises into a plurality of enterprise groups, wherein each of the enterprise groups includes at least one of the enterprise groups Enterprise data of the enterprise;

   Performing statistical analysis on enterprise data of all the enterprises in each of the enterprise groups to obtain enterprise characteristic data corresponding to each of the enterprise groups;

   When project recommendation is required, obtain enterprise data of newly introduced enterprises;

   Determining an enterprise group to which the newly introduced enterprise belongs according to the enterprise data of the newly introduced enterprise and the enterprise characteristic data of each of the enterprise groups; and

   Project recommendation is made to the newly introduced enterprise according to the enterprise group to which the newly introduced enterprise belongs.
2. The project recommendation method according to claim 1, wherein determining the enterprise group to which the newly introduced enterprise belongs according to the enterprise data of the newly introduced enterprise and the enterprise characteristic data of each of the enterprise groups comprises: calculating The similarity between the enterprise data of the newly introduced enterprises and the enterprise characteristic data of each of the enterprise groups; and acquiring the enterprise group with the highest similarity to the enterprise data of the newly introduced enterprises as the newly introduced enterprises The business group to which it belongs.
3. The project recommendation method according to claim 1, wherein the performing a project recommendation to the newly introduced enterprise according to an enterprise group to which the newly introduced enterprise belongs, comprising: Recommend a project identification; and recommend the project recommendation to be recommended to the newly introduced enterprise to complete a project recommendation.
4. The item recommendation method according to claim 3, wherein the enterprise characteristic data includes a characteristic item identifier, and the characteristic item identifier is an identifier corresponding to a project whose project application rate in the enterprise group meets a preset condition;

   The acquiring the identifier of an item to be recommended in an enterprise group to which the newly-introduced enterprise belongs includes acquiring the characteristic item identifier of the enterprise group to which the newly-introduced enterprise belongs as an identifier of the item to be recommended.
5. The method for project recommendation according to claim 3, wherein the acquiring an identifier of an item to be recommended in an enterprise group to which the newly-introduced enterprise belongs includes acquiring an application that has been applied for by an enterprise in an enterprise group to which the newly-introduced enterprise belongs. The project ID of all projects is used as the project ID to be recommended.
6. The method for item recommendation according to claim 3, wherein before the recommending the to-be-recommended item identification to the newly introduced enterprise to complete the item recommendation, further comprising: obtaining each of the to-be-recommended items stored in advance Identify the corresponding classification model; use the classification model to determine whether the enterprise data of the newly introduced enterprise meets the project application conditions for the corresponding project identification; if the enterprise data of the newly introduced enterprise meets the corresponding project identification For project application conditions, the step of recommending the identifier of the project to be recommended to the newly introduced enterprise to complete the project recommendation is performed.
7. The project recommendation method according to claim 3, wherein before the recommending the project recommendation identifier to the newly introduced enterprise to complete the project recommendation, further comprising: from the enterprise group to which the newly introduced enterprise belongs. Acquiring enterprise data including the identifier of the item to be recommended; based on the K-nearest neighbor algorithm, acquiring K enterprise data with high similarity to the enterprise data of the newly introduced enterprise from the enterprise data including the identifier of the item to be recommended; Obtaining the project amount corresponding to the identifier of the item to be recommended from the data of the K companies with a high degree of similarity; and calculating an average value of the amount of the K items as the average project amount of the identifier of the item to be recommended;

   The recommending the to-be-recommended project identifier to the newly-introduced enterprise to complete the project recommendation includes recommending the to-be-recommended project identifier and the corresponding average project amount to the newly-introduced enterprise to complete the project recommendation.
8. The project recommendation method according to claim 1, wherein the plurality of enterprises include a plurality of preset enterprise representatives; and the processed clustered enterprise data of all the enterprises are clustered according to a preset clustering algorithm. Processing to divide a plurality of the enterprises into a plurality of enterprise groups, including: according to a preset clustering algorithm and using the processed enterprise data of a plurality of the enterprise representatives as an initial clustering center, The processed enterprise data is clustered to divide a plurality of the enterprises into a plurality of enterprise groups.
9. An item recommendation device includes:

   A data acquisition unit for acquiring enterprise data of multiple enterprises;

   A normalization unit, configured to filter out preset types of enterprise data from the enterprise data of each of the enterprises, and perform normalization processing on the preset types of enterprise data to obtain processed enterprise data;

   A clustering unit, configured to perform cluster processing on processed enterprise data of all the enterprises according to a preset clustering algorithm, so as to divide a plurality of the enterprises into a plurality of enterprise groups, where each of the enterprises The cluster includes enterprise data of at least one of the enterprises;

   An analysis unit, configured to perform statistical analysis on enterprise data of all the enterprises in each of the enterprise groups to obtain enterprise characteristic data corresponding to each of the enterprise groups;

   The data obtaining unit is further configured to obtain enterprise data of a newly introduced enterprise when a project recommendation is required;

   A determining unit, configured to determine an enterprise group to which the newly introduced enterprise belongs according to the enterprise data of the newly introduced enterprise and enterprise characteristic data of each of the enterprise groups; and

   The recommendation unit is configured to perform project recommendation to the newly introduced enterprise according to an enterprise group to which the newly introduced enterprise belongs.
10. A computer device includes a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein when the processor executes the computer program, the following steps are implemented: acquiring multiple enterprises The enterprise data of each enterprise; filtering out the enterprise data of a preset type from the enterprise data of each of the enterprises, and normalizing the enterprise data of the preset types to obtain processed enterprise data; Class algorithm to perform cluster processing on processed enterprise data of all the enterprises to divide a plurality of the enterprises into a plurality of enterprise groups, wherein each of the enterprise groups includes enterprise data of at least one of the enterprises ; Through statistical analysis of enterprise data of all the enterprises in each of the enterprise groups to obtain enterprise characteristic data corresponding to each of the enterprise groups; when project recommendation is needed, obtain enterprise data of newly introduced enterprises; according to Determining the enterprise data to which the newly introduced enterprise belongs and the enterprise data of each newly introduced enterprise And according to the new introduction of a corporate group owned enterprises, the introduction of new business to the project recommendations.
11. The computer device according to claim 10, wherein the processor executes when determining the enterprise group to which the newly-introduced enterprise belongs based on the enterprise data of the newly-introduced enterprise and enterprise characteristic data of each of the enterprise groups, The following steps are implemented: calculating the similarity between the enterprise data of the newly introduced enterprises and the enterprise characteristic data of each of the enterprise groups; and obtaining the enterprise group with the highest similarity to the enterprise data of the newly introduced enterprises as The enterprise group to which the newly introduced enterprise belongs.
12. The computer device according to claim 10, wherein when the processor executes project recommendation to the newly-introduced enterprise according to the enterprise group to which the newly-introduced enterprise belongs, the following steps are implemented: obtaining the ownership of the newly-introduced enterprise An identification of the item to be recommended in the enterprise group of; and recommending the identification of the item to be recommended to the newly introduced enterprise to complete the item recommendation.
13. The computer device according to claim 12, wherein the enterprise characteristic data includes a characteristic item identifier, and the characteristic item identifier is an identifier corresponding to a project whose project application rate in the enterprise group meets a preset condition; the processor When obtaining the identifier of the item to be recommended in the enterprise group to which the newly-introduced enterprise belongs is executed, the following steps are implemented: acquiring the characteristic item identifier of the enterprise group to which the newly-introduced enterprise belongs as the identifier of the item to be recommended.
14. The computer device according to claim 12, wherein when the processor executes to obtain an identifier of a to-be-recommended item in an enterprise group to which the newly-introduced enterprise belongs, the following steps are implemented: The project IDs of all the projects that the enterprise has applied for are to be recommended project IDs.
15. The computer device according to claim 12, wherein before the processor executes recommending the to-be-recommended project identification to the newly introduced enterprise to complete the project recommendation, the processor further implements the step of: acquiring each of the previously stored The classification model corresponding to the identification of the project to be recommended; the classification model is used to determine whether the enterprise data of the newly introduced enterprise meets the project application conditions of the corresponding identification of the project to be recommended; if the enterprise data of the newly introduced enterprise meets the corresponding to be recommended The project application condition of the project identification, the step of recommending the project identification to be recommended to the newly introduced enterprise to complete the project recommendation.
16. A computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, causes the processor to perform the following steps: obtaining enterprise data of multiple enterprises; A preset type of enterprise data is filtered out of the enterprise data of each of the enterprises, and normalized processing is performed on the preset type of enterprise data to obtain processed enterprise data; according to a preset clustering algorithm, all Performing cluster processing on the processed enterprise data of the enterprise to divide a plurality of the enterprises into a plurality of enterprise groups, wherein each of the enterprise groups includes enterprise data of at least one of the enterprises; Perform statistical analysis on the enterprise data of all the enterprises in the enterprise group to obtain the enterprise characteristic data corresponding to each of the enterprise groups; when project recommendation is needed, obtain the enterprise data of the newly introduced enterprises; according to the newly introduced enterprises Determining the enterprise group to which the newly introduced enterprise belongs, and the enterprise characteristic data of each of the enterprise groups; and according to the Introduction of a corporate group owned enterprises, the introduction of enterprise project to the new recommendation.
17. The computer-readable storage medium of claim 16, wherein the computer program, when executed by a processor, determines the newly-introduced based on the enterprise data of the newly-introduced enterprises and the enterprise characteristic data of each of the enterprise groups. When the enterprise group to which the enterprise belongs, the processor executes the following steps: calculating the similarity between the enterprise data of the newly introduced enterprises and the enterprise characteristic data of each of the enterprise groups; and obtaining the similarity with the newly introduced enterprises. The enterprise group with the highest similarity in the enterprise data is used as the enterprise group to which the newly introduced enterprise belongs.
18. The computer-readable storage medium of claim 16, wherein the computer program, when executed by a processor, causes the processor to perform an item recommendation to the newly introduced enterprise based on an enterprise group to which the newly introduced enterprise belongs. The following steps are performed: obtaining an identifier of a project to be recommended in the enterprise group to which the newly introduced enterprise belongs; and recommending the identifier of the project to be recommended to the newly introduced enterprise to complete a project recommendation.
19. The computer-readable storage medium according to claim 18, wherein the enterprise characteristic data includes a characteristic item identifier, and the characteristic item identifier is an identifier corresponding to a project whose project application rate in the enterprise group meets a preset condition; The computer program, when executed by a processor, obtains an identifier of a to-be-recommended item in an enterprise group to which the newly-introduced enterprise belongs to cause the processor to perform the following steps: obtain a characteristic item identifier of the enterprise-group to which the newly-introduced enterprise belongs as a recommendation to be recommended Project ID.
20. The computer-readable storage medium of claim 18, wherein the computer program, when executed by a processor, obtains an identifier of an item to be recommended in an enterprise group to which the newly introduced enterprise belongs, causing the processor to perform the following steps: The project identifiers of all the projects applied by the enterprises in the enterprise group to which the newly introduced enterprise belongs are used as the project identifiers to be recommended.

Images