CN117725196A - Method and system for recommending projects according to enterprise information - Google Patents
Method and system for recommending projects according to enterprise information Download PDFInfo
- Publication number
- CN117725196A CN117725196A CN202410002508.9A CN202410002508A CN117725196A CN 117725196 A CN117725196 A CN 117725196A CN 202410002508 A CN202410002508 A CN 202410002508A CN 117725196 A CN117725196 A CN 117725196A
- Authority
- CN
- China
- Prior art keywords
- information
- enterprise
- project
- fusion
- acquiring
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 230000004927 fusion Effects 0.000 claims abstract description 135
- 238000012549 training Methods 0.000 claims abstract description 26
- 238000012545 processing Methods 0.000 claims description 18
- 230000011218 segmentation Effects 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 13
- 239000011159 matrix material Substances 0.000 claims description 9
- 238000007637 random forest analysis Methods 0.000 claims description 7
- 230000006870 function Effects 0.000 claims description 6
- 238000013145 classification model Methods 0.000 claims description 5
- 238000012706 support-vector machine Methods 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 239000013598 vector Substances 0.000 description 6
- 238000012216 screening Methods 0.000 description 5
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 238000003066 decision tree Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Landscapes
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention relates to the technical field of project declaration, and particularly discloses a method and a system for recommending projects according to enterprise information. According to the method, the first fusion characteristic value is obtained according to the historical project information, then the second fusion characteristic value is obtained according to the enterprises to be applied, then whether the ratio of the second fusion characteristic value to the first fusion characteristic value meets the preset characteristic value or not is judged, if yes, the information of the historical declaration project corresponding to the first fusion characteristic value is used as a reference to conduct project recommendation on the current enterprises to be applied, the ratio of the second fusion characteristic value obtained after training through detailed data serving as a sample to the first fusion characteristic value is calculated, if the ratio is close to 1, the higher the similarity of the two enterprises is, the lower the similarity of the two enterprises is, and if the ratio is not close to the lower the similarity of the two enterprises, the user selects the enterprises with high similarity to be selected as references in the enterprises when referring to the information of the applied enterprises, and therefore errors in project declaration can be reduced through accurate data.
Description
Technical Field
The invention relates to the technical field of project declaration, in particular to a method and a system for recommending projects according to enterprise information.
Background
Along with the acceleration of economic development, a large number of matched services are needed to meet the high-efficiency operation of enterprises, the existing enterprises generally adopt a reference mode to quickly obtain the applied information in the process of reporting the projects, then the projects are reported by the enterprises according to similar information as references to be matched with the application, and the random references can lead to errors in reporting the whole projects, so that the problem that a visitor intensively accesses the same database to collapse is solved by a method for recommending the projects according to the enterprise information.
Disclosure of Invention
The invention aims to provide a method and a system for recommending items according to enterprise information, so as to solve the technical problems in the background technology.
In order to achieve the above purpose, the present invention provides the following technical solutions:
a method of making project recommendations based on enterprise information, comprising:
acquiring historical project information of an enterprise, wherein the historical project information comprises declaration information and financial information;
extracting enterprise operation range information in each declaration information, and acquiring first camping category keywords of a plurality of enterprises according to the enterprise operation range information;
acquiring financial statement information according to the financial information, and acquiring corresponding first project fund information and first enterprise tax information according to the financial statement information;
inputting the first camping category keywords, the first project fund information and the first enterprise tax information into a first feature fusion model for training to obtain a first fusion feature value;
acquiring a second operation category keyword, second project fund information and second enterprise tax information of an enterprise to be applied currently based on the first operation category keyword, the first project fund information and the first enterprise tax information as labels;
inputting the second operation category keywords, second project fund information and second enterprise tax information into a second feature fusion model for training to obtain a second fusion feature value;
judging whether the ratio of the second fusion characteristic value to the first fusion characteristic value meets a preset characteristic value or not;
if yes, the information of the historical declaration project corresponding to the first fusion characteristic value is used as a reference to conduct project recommendation on the project enterprise to be currently applied.
Preferably, the step of acquiring the historical project information of the enterprise includes:
acquiring historical project submitting information of an enterprise, and performing text analysis on the historical project submitting information to obtain a plurality of text segmentation units and a plurality of digital segmentation units;
inputting the text segmentation units into a classification model, extracting a catalog of project application through a random forest, and acquiring corresponding reporting information of successful project reporting according to the catalog of the project application;
inputting the digital segmentation unit into a support vector machine to classify and screen the project application filling numbers to obtain financial declaration numbers;
and defining the text information corresponding to the financial declaration number as financial information.
Preferably, the step of obtaining the first camping category keywords of the plurality of enterprises according to the enterprise operation scope information includes:
acquiring business license information of a corresponding reporting enterprise according to the reporting information, and extracting business scope information of the enterprise according to the business license information;
preprocessing a text corresponding to the business scope information to obtain a standard business keyword;
and classifying the business scope of the standard business keywords based on a preset business list to obtain first-class keywords.
Preferably, the step of inputting the first camping category keyword, the first project fund information and the first enterprise tax information into a first feature fusion model to train to obtain a first fusion feature value includes:
acquiring a plurality of first camping category keywords, and performing coding processing on the plurality of first camping category keywords to obtain a plurality of keyword coding values;
acquiring a plurality of first project fund information, and carrying out coding processing on the plurality of first project fund information to obtain a plurality of project fund coding values;
acquiring a plurality of first enterprise tax information, and carrying out coding processing on the plurality of first enterprise tax information to obtain a plurality of enterprise tax coding values;
inputting a plurality of keyword coding values, a plurality of project fund coding values and a plurality of enterprise tax coding values into a first feature fusion model for training to obtain a first fusion feature value, wherein the function of the first feature fusion model is as follows:
wherein,expressed as a first fusion characteristic value, +.>Expressed as a plurality of key code values, +.>Expressed as a plurality of key code values, +.>Expressed as a plurality of key code values, i is the number of the plurality of code values, where i=1, 2, 3.
Preferably, the step of obtaining the second operation category keyword, the second project fund information and the second enterprise tax information of the currently-applied project enterprise based on the first operation category keyword, the first project fund information and the first enterprise tax information as labels includes:
constructing a comparison matrix according to the first camping category keywords, the first project fund information and the first enterprise tax information in the historical project information of the enterprise, wherein the comparison mode of the comparison matrix is pairwise comparison;
extracting corresponding keyword characteristic values, project fund characteristic values and enterprise tax characteristic values according to the first warp category keywords, the first project fund information and the first enterprise tax information;
establishing a corresponding reference tag table according to the keyword characteristic value, the project fund characteristic value and the enterprise tax characteristic value;
and acquiring a second operation category keyword, second project fund information and second enterprise tax information of the enterprise of the current to-be-applied project based on the reference label table.
Preferably, before the step of determining whether the ratio of the second fusion feature value to the first fusion feature value meets the preset feature value, the method includes:
calculating a fusion characteristic ratio according to the second fusion characteristic value and the first fusion characteristic value, wherein the calculation formula is as follows:
wherein,representing fusion feature ratio, ++>Representing a second fusion characteristic value,/->Representing a first fusion feature value;
the fusion feature ratio is defined as the ratio of the second fusion feature value to the first fusion feature value.
The application also provides a system for recommending items according to enterprise information, comprising:
the first acquisition module is used for acquiring historical project information of an enterprise, wherein the historical project information comprises declaration information and financial information;
the first extraction module is used for extracting enterprise operation range information in each declaration message and acquiring first camping category keywords of a plurality of enterprises according to the enterprise operation range information;
the second acquisition module is used for acquiring financial statement information according to the financial information, and acquiring corresponding first project fund information and first enterprise tax information according to the financial statement information;
the first fusion module is used for inputting the first camping category keywords, the first project fund information and the first enterprise tax information into a first feature fusion model for training to obtain a first fusion feature value;
the third acquisition module is used for acquiring a second operation category keyword, second project fund information and second enterprise tax information of the currently-applied project enterprise based on the first operation category keyword, the first project fund information and the first enterprise tax information as labels;
the second fusion module is used for inputting the second operation category keywords, the second project fund information and the second enterprise tax information into a second feature fusion model for training to obtain a second fusion feature value;
the first judging module is used for judging whether the ratio of the second fusion characteristic value to the first fusion characteristic value meets a preset characteristic value or not;
if yes, the information of the historical declaration project corresponding to the first fusion characteristic value is used as a reference to conduct project recommendation on the project enterprise to be currently applied.
Preferably, the first fusion module includes:
the first acquisition unit is used for acquiring a plurality of first camping category keywords and carrying out coding processing on the plurality of first camping category keywords to obtain a plurality of keyword coding values;
the second acquisition unit is used for acquiring a plurality of first project fund information and carrying out coding processing on the plurality of first project fund information to obtain a plurality of project fund coding values;
the third acquisition unit is used for acquiring a plurality of first enterprise tax information and carrying out coding processing on the plurality of first enterprise tax information to obtain a plurality of enterprise tax coding values;
the first training unit is used for inputting a plurality of keyword coding values, a plurality of project fund coding values and a plurality of enterprise tax coding values into the first feature fusion model for training to obtain a first fusion feature value, wherein the function of the first feature fusion model is as follows:
wherein,expressed as a first fusion characteristic value, +.>Expressed as a plurality of key code values, +.>Expressed as a plurality of key code values, +.>Expressed as a plurality of key code values, i is the number of the plurality of code values, where i=1, 2, 3.
The present application also provides a computer device comprising a memory storing a computer program and a processor implementing the steps of the above method when executing the computer program.
The present application also provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the above method.
The beneficial effects of this application are: according to the method, the first acquired first management category keywords, the first project fund information and the first enterprise tax information are acquired according to historical project information and are input into a first feature fusion model to be trained to obtain a first fusion feature value, then the second management category keywords, the second project fund information and the second enterprise tax information are input into the second feature fusion model to be trained to obtain a second fusion feature value, if the ratio of the second fusion feature value to the first fusion feature value meets a preset feature value, the information of a historical reporting project corresponding to the first fusion feature value is used as a reference to conduct project recommendation on a current enterprise to be applied, the second fusion feature value obtained after training through detailed data is used as a sample is calculated to obtain a ratio with the first fusion feature value, if the ratio is close to 1, the higher the similarity of the two enterprises is, otherwise, the lower the similarity of the two enterprises is not close, and further a user can choose the enterprise with the higher similarity in a plurality of enterprises as a reference when referring to the applied enterprise information, and accordingly error reporting of project data can be reduced.
Drawings
FIG. 1 is a flow chart of a method according to an embodiment of the present application.
Fig. 2 is a schematic system structure of an embodiment of the present application.
Fig. 3 is a schematic diagram of an internal structure of a computer device according to an embodiment of the present application.
The realization, functional characteristics and advantages of the present application will be further described with reference to the embodiments, referring to the attached drawings.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
1-3, the present application provides a method for recommending items according to enterprise information, comprising:
s1, acquiring historical project information of an enterprise, wherein the historical project information comprises declaration information and financial information;
s2, extracting enterprise operation range information in each declaration message, and acquiring first camping category keywords of a plurality of enterprises according to the enterprise operation range information;
s3, acquiring financial statement information according to the financial information, and acquiring corresponding first project fund information and first enterprise tax information according to the financial statement information;
s4, inputting the first camping category keywords, the first project fund information and the first enterprise tax information into a first feature fusion model for training to obtain a first fusion feature value;
s5, acquiring a second operation category keyword, second project fund information and second enterprise tax information of the currently-applied project enterprise based on the first operation category keyword, the first project fund information and the first enterprise tax information as labels;
s6, inputting the second operation category keywords, second project fund information and second enterprise tax information into a second feature fusion model for training to obtain a second fusion feature value;
s7, judging whether the ratio of the second fusion characteristic value to the first fusion characteristic value meets a preset characteristic value or not;
if yes, the information of the historical declaration project corresponding to the first fusion characteristic value is used as a reference to conduct project recommendation on the project enterprise to be currently applied.
As described in the above steps S1-S7, with the acceleration of economic development, a large amount of supporting services are required to meet the requirement of efficient operation of enterprises, but the existing enterprises generally adopt a reference mode to quickly obtain the applied information in the process of reporting the projects, then the applied information is matched according to the enterprise reporting projects of similar information as references, the random references can cause errors in the whole project reporting, based on the errors, the historical project information of the enterprises is acquired firstly, wherein the historical project information comprises reporting information and financial information, and because the main information in the project reporting process is the reporting information and the financial information, a large amount of reporting enterprises can be quickly acquired according to the financial information, and then after one screening, the information of the enterprises to be applied can be quickly matched with the information of the historic applied enterprises according to the reporting information, wherein the specific steps are as follows: firstly extracting enterprise operation range information in each reporting information, acquiring first enterprise category keywords according to the enterprise operation range information, thus being capable of rapidly judging the operation ranges of the applied enterprises and the enterprises to be applied based on the keywords, further being capable of reducing reference errors caused by data deviation through specific data, then acquiring financial statement information according to the financial statement information, acquiring corresponding first project fund information and first enterprise tax information according to the financial statement information, providing corresponding first project fund information and tax information according to the reporting project, further being capable of acquiring qualification of the applied projects, further being capable of intuitively taking the specific first project fund information and the first enterprise tax information as reference basis, and not appearing reference deviation, then inputting the first enterprise category keywords, the first project fund information and the first enterprise tax information into a first feature fusion model for training, obtaining a first fused feature value, being capable of comprehensively reflecting the applied integrated value based on the first project fund information and the first enterprise tax information, then being capable of fusing the second enterprise feature value and the second enterprise tax information to be used as a preset feature value, and whether the first enterprise fund information and the second enterprise tax information are fused to obtain a feature value, then fusing the first enterprise feature value and the second enterprise feature value to be used as a preset application feature value, and whether the first enterprise feature value is required to be fused with the second feature value is met, if the comparison result is met, the information of the historical declaration item corresponding to the first fusion characteristic value is used as a reference to conduct item recommendation on the enterprise of the currently-to-be-applied item, the ratio of the second fusion characteristic value obtained after training through the detailed data serving as a sample to the first fusion characteristic value is calculated, if the ratio is close to 1, the higher the similarity of the two enterprises is, the lower the similarity of the two enterprises is, and further when the user refers to the information of the applied enterprise, the enterprise with the high similarity is selected from a plurality of enterprises to serve as the reference, so that the error of item declaration can be reduced through accurate data.
In one embodiment, the step S1 of obtaining historical project information of the enterprise includes:
s101, acquiring historical project submitting information of an enterprise, and performing text analysis on the historical project submitting information to obtain a plurality of text segmentation units and a plurality of digital segmentation units;
s102, inputting the text segmentation units into a classification model, extracting a catalog of project application through a random forest, and acquiring corresponding reporting information of successful project reporting according to the catalog of the project application;
s103, inputting the digital segmentation unit into a support vector machine to classify and screen the project application filling numbers to obtain financial declaration numbers;
s104, defining the text information corresponding to the financial declaration number as financial information.
As described in the above steps S101-S104, when acquiring the declaration information, firstly acquiring the historical project submitting information of the enterprise, and performing text analysis on the historical project submitting information to obtain a plurality of text segmentation units and digital segmentation units, wherein the text segmentation units can be explicit vocabularies, the digital segmentation units are financial digital information after slitting and screening, the text segmentation units are input into a classification model, the classification model can be logistic regression, decision trees, random forests, support vector machines and the like, the random forests are selected to obtain catalogues of project applications, as each random forest is constructed based on the characteristics of a random subset, a part of characteristics are selected randomly on each node to split, the split sub-node samples are purer through multiple random splitting and extraction, the samples are also infinitely close to the required screening result, in the proposal, the text segmentation units are used as random subsets on each decision tree, then the split key words are split, the extracted key words are close to the extracted key terms, the random forest is accurately classified according to the acquired by the support vector machines, the corresponding to the acquired data of the application can be more than the reference vectors, the application can be accurately classified according to the support vectors, the application can be obtained, the application data can be accurately classified according to the support vectors after the application are more than the corresponding to the search vectors, the application data can be accurately obtained, the application can be accurately classified according to the application data, the application can be obtained, and the application data can be accurately obtained by the corresponding to the support vectors, and the application is accurately obtained by the application is accurately based on the support the corresponding to the data, the data of different categories in the scheme are a plurality of financial reporting numbers, the hyperplane is determined by the support vector, the data point closest to the hyperplane is the data needing screening, the data point closest to the hyperplane is the financial information screened out in the scheme, the text information corresponding to the financial reporting numbers is defined as the financial information, and therefore the reporting information and the financial information after accurate screening can be used as real reference basis for the enterprises to be applied for later.
In one embodiment, the step S2 of obtaining the first camping category keywords of the plurality of enterprises according to the enterprise operation scope information includes:
s201, acquiring business license information of a corresponding reporting enterprise according to the reporting information, and extracting business scope information of the enterprise according to the business license information;
s202, preprocessing a text corresponding to the business scope information to obtain a standard business keyword;
s203, classifying business ranges of the standard business keywords based on a preset business list to obtain first-class keywords.
As described in the above steps S201-S203, since the declaration information is filled in according to the business license information of the declaration enterprise, the reference data can be more accurately obtained according to the enterprise, then the corresponding business license information of the declaration enterprise is obtained according to the declaration information, the business scope information of the enterprise is extracted according to the business license information, then the text corresponding to the business scope information is preprocessed to obtain the standard business keywords, and then the business scope classification is performed on the standard business keywords based on the preset business list to obtain the first business category keywords, so that the business scope of the historical applied enterprise can be accurately obtained, and then the enterprise to be applied can rapidly perform the business attribute positioning according to the business scope, and further the project application data of the field can be accurately obtained.
In one embodiment, the step S4 of inputting the first camping category keyword, the first project fund information and the first enterprise tax information into the first feature fusion model to train to obtain a first fusion feature value includes:
s401, acquiring a plurality of first camping category keywords, and performing coding processing on the plurality of first camping category keywords to obtain a plurality of keyword coding values;
s402, acquiring a plurality of first project fund information, and carrying out coding processing on the plurality of first project fund information to obtain a plurality of project fund coding values;
s403, acquiring a plurality of first enterprise tax information, and carrying out coding processing on the plurality of first enterprise tax information to obtain a plurality of enterprise tax code values;
s404, inputting a plurality of keyword coding values, a plurality of project fund coding values and a plurality of enterprise tax coding values into a first feature fusion model for training to obtain a first fusion feature value, wherein the function of the first feature fusion model is as follows:
wherein,expressed as a first fusion characteristic value, +.>Expressed as a plurality of key code values, +.>Expressed as a plurality of key code values, +.>Expressed as a plurality of keyword encoding values, i is a number of the plurality of encoding values, wherein i=1, 2, 3..n。
As described in the above steps S401-S404, a plurality of first-class keywords are obtained, and the plurality of first-class keywords are encoded to obtain a plurality of keyword encoding values, then a plurality of first project fund information is obtained, and the plurality of first project fund information is encoded to obtain a plurality of project fund encoding values, then a plurality of first enterprise tax information is obtained, and a plurality of first enterprise tax information is encoded to obtain a plurality of enterprise tax encoding values, and then the plurality of keyword encoding values, the plurality of project fund encoding values and the plurality of enterprise tax encoding values are input into a first feature fusion model to be trained, so that the first fusion feature value of the comprehensive attribute obtained by the important reference data can numerically simulate the comprehensive feature of the applied enterprise, and further whether the enterprise is similar to the enterprise to be applied or not can be rapidly judged according to the comprehensive feature, thereby improving the speed of acquiring the project recommendation.
In one embodiment, the step S5 of obtaining the second operation category keyword, the second project fund information and the second enterprise tax information of the currently-to-be-applied project enterprise based on the first operation category keyword, the first project fund information and the first enterprise tax information as labels includes:
s501, constructing a comparison matrix according to the first camping category keywords, the first project fund information and the first enterprise tax information in the historical project information of the enterprise, wherein the comparison mode of the comparison matrix is pairwise comparison;
s502, extracting corresponding keyword characteristic values, project fund characteristic values and enterprise tax characteristic values according to the first camping category keywords, the first project fund information and the first enterprise tax information;
s503, establishing a corresponding reference label table according to the keyword characteristic value, the project fund characteristic value and the enterprise tax characteristic value;
s504, acquiring a second business category keyword, second project fund information and second enterprise tax information of the enterprise of the current to-be-applied project based on the reference label table.
As described in the above steps S501-S504, a comparison matrix is constructed according to the first camping category keyword, the first project fund information and the first enterprise tax information in the historical project information of the enterprise, where the comparison mode of the comparison matrix is two-by-two comparison, where the comparison matrix is two sequences or data between sets, each element represents whether two elements are matched, then a corresponding keyword feature value, a project fund feature value and an enterprise tax feature value are extracted according to the first camping category keyword, the first project fund information and the first enterprise tax information, so that after the feature attribute is obtained, a corresponding reference tag table can be established according to the feature attribute, and then a second operation category keyword, a second project fund information and a second enterprise tax information of the currently applied project enterprise can be obtained based on the reference tag table, so that important reference data can be obtained according to the applied enterprise as a basis.
In one embodiment, before the step S7 of determining whether the ratio of the second fused feature value to the first fused feature value meets the preset feature value, the method includes:
s8, calculating a fusion characteristic ratio according to the second fusion characteristic value and the first fusion characteristic value, wherein a calculation formula is as follows:
wherein,representing fusion feature ratio, ++>Representing a second fusion characteristic value,/->Representing a first fusion feature value;
s9, defining the fusion characteristic ratio as the ratio of the second fusion characteristic value to the first fusion characteristic value.
And (3) as described in the steps S8-S9, calculating the fusion characteristic ratio through the second fusion characteristic value and the first fusion characteristic value, judging whether the ratio is close to 1, if so, indicating that the similarity of two enterprises is higher, otherwise, the similarity of the two enterprises is lower if not close, and further, when a user refers to the information of the applied enterprises, selecting the enterprises with high similarity from the enterprises as references, thereby reducing errors in project declaration through accurate data.
The application also provides a system for recommending items according to enterprise information, comprising:
the first acquisition module 1 is used for acquiring historical project information of an enterprise, wherein the historical project information comprises declaration information and financial information;
the first extraction module 2 is used for extracting enterprise operation range information in each declaration message and acquiring first-class keywords of a plurality of enterprises according to the enterprise operation range information;
the second acquisition module 3 is used for acquiring financial statement information according to the financial information, and acquiring corresponding first project fund information and first enterprise tax information according to the financial statement information;
the first fusion module 4 is used for inputting the first camping category keyword, the first project fund information and the first enterprise tax information into a first feature fusion model for training to obtain a first fusion feature value;
the third obtaining module 5 is configured to obtain a second operation category keyword, second project fund information and second enterprise tax information of the currently-to-be-applied project enterprise based on the first operation category keyword, the first project fund information and the first enterprise tax information as labels;
the second fusion module 6 is configured to input the second operation category keyword, the second project fund information and the second enterprise tax information into a second feature fusion model for training, so as to obtain a second fusion feature value;
the first judging module 7 is configured to judge whether the ratio of the second fusion characteristic value to the first fusion characteristic value meets a preset characteristic value;
if yes, the information of the historical declaration project corresponding to the first fusion characteristic value is used as a reference to conduct project recommendation on the project enterprise to be currently applied.
Preferably, the first fusion module includes:
the first acquisition unit is used for acquiring a plurality of first camping category keywords and carrying out coding processing on the plurality of first camping category keywords to obtain a plurality of keyword coding values;
the second acquisition unit is used for acquiring a plurality of first project fund information and carrying out coding processing on the plurality of first project fund information to obtain a plurality of project fund coding values;
the third acquisition unit is used for acquiring a plurality of first enterprise tax information and carrying out coding processing on the plurality of first enterprise tax information to obtain a plurality of enterprise tax coding values;
the first training unit is used for inputting a plurality of keyword coding values, a plurality of project fund coding values and a plurality of enterprise tax coding values into the first feature fusion model for training to obtain a first fusion feature value, wherein the function of the first feature fusion model is as follows:
wherein,expressed as a first fusion characteristic value, +.>Expressed as a plurality of key code values, +.>Expressed as a plurality of key code values, +.>Represented as a plurality of key code values,i is the number of a plurality of coded values, where i=1, 2, 3.
As shown in fig. 3, the present application further provides a computer device, which may be a server, and the internal structure of which may be as shown in fig. 3. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the computer is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used for all data required for the process of the method of making project recommendations based on the enterprise information. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of making project recommendations based on enterprise information.
Those skilled in the art will appreciate that the architecture shown in fig. 3 is merely a block diagram of a portion of the architecture in connection with the present application and is not intended to limit the computer device to which the present application is applied.
An embodiment of the present application further provides a computer readable storage medium, on which a computer program is stored, where the computer program when executed by a processor implements any one of the above methods and systems for recommending items according to enterprise information.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium provided herein and used in embodiments may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual speed data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, apparatus, article or method that comprises the element.
The foregoing description is only of the preferred embodiments of the present invention and is not intended to limit the scope of the invention, and all equivalent structures or equivalent processes using the descriptions and drawings of the present invention or directly or indirectly applied to other related technical fields are included in the scope of the invention.
Claims (10)
1. A method for recommending items based on enterprise information, comprising:
acquiring historical project information of an enterprise, wherein the historical project information comprises declaration information and financial information;
extracting enterprise operation range information in each declaration information, and acquiring first camping category keywords of a plurality of enterprises according to the enterprise operation range information;
acquiring financial statement information according to the financial information, and acquiring corresponding first project fund information and first enterprise tax information according to the financial statement information;
inputting the first camping category keywords, the first project fund information and the first enterprise tax information into a first feature fusion model for training to obtain a first fusion feature value;
acquiring a second operation category keyword, second project fund information and second enterprise tax information of an enterprise to be applied currently based on the first operation category keyword, the first project fund information and the first enterprise tax information as labels;
inputting the second operation category keywords, second project fund information and second enterprise tax information into a second feature fusion model for training to obtain a second fusion feature value;
judging whether the ratio of the second fusion characteristic value to the first fusion characteristic value meets a preset characteristic value or not;
if yes, the information of the historical declaration project corresponding to the first fusion characteristic value is used as a reference to conduct project recommendation on the project enterprise to be currently applied.
2. The method for recommending items based on information of an enterprise of claim 1, wherein the step of obtaining historical item information of the enterprise comprises:
acquiring historical project submitting information of an enterprise, and performing text analysis on the historical project submitting information to obtain a plurality of text segmentation units and a plurality of digital segmentation units;
inputting the text segmentation units into a classification model, extracting a catalog of project application through a random forest, and acquiring corresponding reporting information of successful project reporting according to the catalog of the project application;
inputting the digital segmentation unit into a support vector machine to classify and screen the project application filling numbers to obtain financial declaration numbers;
and defining the text information corresponding to the financial declaration number as financial information.
3. The method of claim 1, wherein the step of obtaining a first camping category keyword for a plurality of businesses based on the business context information comprises:
acquiring business license information of a corresponding reporting enterprise according to the reporting information, and extracting business scope information of the enterprise according to the business license information;
preprocessing a text corresponding to the business scope information to obtain a standard business keyword;
and classifying the business scope of the standard business keywords based on a preset business list to obtain first-class keywords.
4. The method for recommending items according to the enterprise information of claim 1, wherein the step of inputting the first camping category keyword, the first item fund information and the first enterprise tax information into a first feature fusion model for training to obtain a first fusion feature value comprises the steps of:
acquiring a plurality of first camping category keywords, and performing coding processing on the plurality of first camping category keywords to obtain a plurality of keyword coding values;
acquiring a plurality of first project fund information, and carrying out coding processing on the plurality of first project fund information to obtain a plurality of project fund coding values;
acquiring a plurality of first enterprise tax information, and carrying out coding processing on the plurality of first enterprise tax information to obtain a plurality of enterprise tax coding values;
inputting a plurality of keyword coding values, a plurality of project fund coding values and a plurality of enterprise tax coding values into a first feature fusion model for training to obtain a first fusion feature value, wherein the function of the first feature fusion model is as follows:
wherein,expressed as a first fusion characteristic value, +.>Expressed as a plurality of key code values, +.>Expressed as a plurality of key code values, +.>Expressed as a plurality of key code values, i is the number of the plurality of code values, where i=1, 2, 3.
5. The method for recommending items according to the business information of claim 1, wherein the step of acquiring the second operation category keyword, the second item fund information and the second business tax information of the currently applied item business based on the first operation category keyword, the first item fund information and the first business tax information as tags comprises:
constructing a comparison matrix according to the first camping category keywords, the first project fund information and the first enterprise tax information in the historical project information of the enterprise, wherein the comparison mode of the comparison matrix is pairwise comparison;
extracting corresponding keyword characteristic values, project fund characteristic values and enterprise tax characteristic values according to the first warp category keywords, the first project fund information and the first enterprise tax information;
establishing a corresponding reference tag table according to the keyword characteristic value, the project fund characteristic value and the enterprise tax characteristic value;
and acquiring a second operation category keyword, second project fund information and second enterprise tax information of the enterprise of the current to-be-applied project based on the reference label table.
6. The method for recommending items according to the enterprise information according to claim 1, wherein before the step of determining whether the ratio of the second fused feature value to the first fused feature value satisfies a preset feature value, the method comprises:
calculating a fusion characteristic ratio according to the second fusion characteristic value and the first fusion characteristic value, wherein the calculation formula is as follows:
wherein,representing fusion feature ratio, ++>Representing a second fusion characteristic value,/->Representing a first fusion feature value;
the fusion feature ratio is defined as the ratio of the second fusion feature value to the first fusion feature value.
7. A system for making project recommendations based on enterprise information, comprising:
the first acquisition module is used for acquiring historical project information of an enterprise, wherein the historical project information comprises declaration information and financial information;
the first extraction module is used for extracting enterprise operation range information in each declaration message and acquiring first camping category keywords of a plurality of enterprises according to the enterprise operation range information;
the second acquisition module is used for acquiring financial statement information according to the financial information, and acquiring corresponding first project fund information and first enterprise tax information according to the financial statement information;
the first fusion module is used for inputting the first camping category keywords, the first project fund information and the first enterprise tax information into a first feature fusion model for training to obtain a first fusion feature value;
the third acquisition module is used for acquiring a second operation category keyword, second project fund information and second enterprise tax information of the currently-applied project enterprise based on the first operation category keyword, the first project fund information and the first enterprise tax information as labels;
the second fusion module is used for inputting the second operation category keywords, the second project fund information and the second enterprise tax information into a second feature fusion model for training to obtain a second fusion feature value;
the first judging module is used for judging whether the ratio of the second fusion characteristic value to the first fusion characteristic value meets a preset characteristic value or not;
if yes, the information of the historical declaration project corresponding to the first fusion characteristic value is used as a reference to conduct project recommendation on the project enterprise to be currently applied.
8. The system for item recommendation based on enterprise information of claim 7, wherein the first fusion module comprises:
the first acquisition unit is used for acquiring a plurality of first camping category keywords and carrying out coding processing on the plurality of first camping category keywords to obtain a plurality of keyword coding values;
the second acquisition unit is used for acquiring a plurality of first project fund information and carrying out coding processing on the plurality of first project fund information to obtain a plurality of project fund coding values;
the third acquisition unit is used for acquiring a plurality of first enterprise tax information and carrying out coding processing on the plurality of first enterprise tax information to obtain a plurality of enterprise tax coding values;
the first training unit is used for inputting a plurality of keyword coding values, a plurality of project fund coding values and a plurality of enterprise tax coding values into the first feature fusion model for training to obtain a first fusion feature value, wherein the function of the first feature fusion model is as follows:
wherein,expressed as a first fusion characteristic value, +.>Expressed as a plurality of key code values, +.>Expressed as a plurality of key code values, +.>Expressed as a plurality of key code values, i is the number of the plurality of code values, where i=1, 2, 3.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 6 when the computer program is executed.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410002508.9A CN117725196A (en) | 2024-01-02 | 2024-01-02 | Method and system for recommending projects according to enterprise information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410002508.9A CN117725196A (en) | 2024-01-02 | 2024-01-02 | Method and system for recommending projects according to enterprise information |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117725196A true CN117725196A (en) | 2024-03-19 |
Family
ID=90207035
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410002508.9A Pending CN117725196A (en) | 2024-01-02 | 2024-01-02 | Method and system for recommending projects according to enterprise information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117725196A (en) |
-
2024
- 2024-01-02 CN CN202410002508.9A patent/CN117725196A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109271627B (en) | Text analysis method, apparatus, computer device and storage medium | |
| CN110458324B (en) | Method and device for calculating risk probability and computer equipment | |
| CN110674319A (en) | Label determination method and device, computer equipment and storage medium | |
| CN112347340B (en) | Information searching method, device and computer equipment | |
| CN110362798B (en) | Method, apparatus, computer device and storage medium for judging information retrieval analysis | |
| CN106909609B (en) | Method for determining similar character strings, method and system for searching duplicate files | |
| CN112231418A (en) | Power standard knowledge graph construction method and device, computer equipment and medium | |
| CN111159982B (en) | Document editing method, device, electronic equipment and computer readable storage medium | |
| CN113868419B (en) | Text classification method, device, equipment and medium based on artificial intelligence | |
| CN111859916B (en) | Method, device, equipment and medium for extracting key words of ancient poems and generating poems | |
| CN112286934A (en) | Database table importing method, device, equipment and medium | |
| CN114357174B (en) | Code classification system and method based on OCR and machine learning | |
| CN112052672B (en) | Address text-based unit area identification method and device and computer equipment | |
| CN113849644A (en) | Text classification model configuration method and device, computer equipment and storage medium | |
| CN111460268B (en) | Method and device for determining database query request and computer equipment | |
| CN117725196A (en) | Method and system for recommending projects according to enterprise information | |
| CN115408995A (en) | Structured analysis method and system for project electronic document | |
| CN115186240A (en) | Social network user alignment method, device and medium based on relevance information | |
| CN114154480A (en) | Information extraction method, device, equipment and storage medium | |
| CN113743982A (en) | Advertisement putting scheme recommendation method and device, computer equipment and storage medium | |
| CN113901817A (en) | Document classification method and device, computer equipment and storage medium | |
| CN113239128B (en) | Data pair classification method, device, equipment and storage medium based on implicit characteristics | |
| CN112347738B (en) | Bidirectional encoder characterization quantity model optimization method and device based on referee document | |
| CN117034864B (en) | Visual labeling method, visual labeling device, computer equipment and storage medium | |
| CN117786190A (en) | Construction method, device, equipment and medium for detection and inspection industry knowledge base |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication |