CN114331230B - Full-chain full-flow intelligent scientific and creative service data processing method and system - Google Patents
Full-chain full-flow intelligent scientific and creative service data processing method and system Download PDFInfo
- Publication number
- CN114331230B CN114331230B CN202210243920.0A CN202210243920A CN114331230B CN 114331230 B CN114331230 B CN 114331230B CN 202210243920 A CN202210243920 A CN 202210243920A CN 114331230 B CN114331230 B CN 114331230B
- Authority
- CN
- China
- Prior art keywords
- service
- data
- enterprise
- demand
- dimension
- 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.)
- Active
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 14
- 238000003745 diagnosis Methods 0.000 claims abstract description 53
- 238000000034 method Methods 0.000 claims abstract description 40
- 230000008569 process Effects 0.000 claims abstract description 31
- 238000007726 management method Methods 0.000 claims abstract description 28
- 238000012545 processing Methods 0.000 claims abstract description 15
- 238000005065 mining Methods 0.000 claims abstract description 5
- 230000004927 fusion Effects 0.000 claims description 52
- 239000013598 vector Substances 0.000 claims description 27
- 238000010276 construction Methods 0.000 claims description 12
- 238000004519 manufacturing process Methods 0.000 claims description 12
- 238000012549 training Methods 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 11
- 230000004044 response Effects 0.000 claims description 11
- 230000002860 competitive effect Effects 0.000 claims description 10
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 6
- 238000002372 labelling Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000013523 data management Methods 0.000 abstract description 6
- 230000006870 function Effects 0.000 abstract description 6
- 238000012544 monitoring process Methods 0.000 abstract description 2
- 230000000007 visual effect Effects 0.000 abstract description 2
- 238000007418 data mining Methods 0.000 abstract 1
- 238000005516 engineering process Methods 0.000 description 10
- 238000004458 analytical method Methods 0.000 description 4
- 230000009466 transformation Effects 0.000 description 4
- 238000010521 absorption reaction Methods 0.000 description 3
- 238000012790 confirmation Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 230000029087 digestion Effects 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 230000003631 expected effect Effects 0.000 description 3
- 238000001914 filtration Methods 0.000 description 3
- 238000007689 inspection Methods 0.000 description 3
- 238000012946 outsourcing Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000012827 research and development Methods 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 230000004913 activation Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003032 molecular docking Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a full-chain full-flow intelligent scientific and creative service data processing method and system, and belongs to the technical field of information mining and information management. The requirement diagnosis is carried out on the scientific and invasive enterprises through an intelligent data mining means, the on-line management of the whole process of the requirement service of the scientific and invasive enterprises by the scientific and invasive mall is provided, and the follow-up process monitoring and the follow-up data management are facilitated. Starting from enterprise requirements, a service mode of a scientific and creative mall is provided, modular management is carried out on each stage of enterprise service, service contracts are generated and can be input into a contract management module of the system, the system can automatically generate service orders according to service contents of the contracts, and full-flow and full-chain service tracking is achieved. The data processing and system can provide intelligent and visual full-chain full-flow scientific data management for investment institutions, service institutions with investment functions, incubators, park operation institutions and government scientific service departments.
Description
Technical Field
The invention belongs to the technical field of information mining and information management, and particularly relates to a full-chain full-flow intelligent scientific and creative service data processing method and system.
Background
At present, in the process of carrying out scientific and creative services, a service requiring party in a common service mode carries out requirement mining, releases required services and provides corresponding contact ways, a service providing party contacts the requiring party through the contact ways, and the specific cooperation and transaction processes are carried out on line. However, in this process, whether the two parties of the service cooperate or not and the large amount of data generated by the demand side and the supply side during cooperation all need to be recorded and managed specially, and the data of the whole service flow cannot be managed and tracked effectively. In the scientific and creative service, a large amount of data is subjected to service docking and management by a specially-assigned person, the period is long, the data management efficiency is low, and the service data generated in the whole service period is not clear. For some investment enterprises, multiple enterprises need to be subjected to wind control management in the investment process, and due to chaos and unclear data management and untimely management data tracking, on one hand, the great data processing pressure can be caused to data management personnel, and meanwhile, the investment and service risks in the investment and service processes are increased.
Disclosure of Invention
The invention aims to solve the problems in the prior art and provides a full-chain full-flow intelligent scientific and creative service data processing method and system.
The invention is realized by the following technical scheme:
the full-chain full-flow intelligent scientific and creative service data processing method comprises the following steps:
entering the resident enterprise information, classifying the enterprise categories, filling the enterprise information base mainly comprising the enterprise basic information, enterprise products, technologies, markets, finance and other related information, labeling the tags according to the subdivision industry, areas and the like where the enterprise is located, and entering the enterprise information into the corresponding database.
The enterprise demand intelligent diagnosis specifically comprises a diagnosis model construction process and an enterprise demand diagnosis process,
in the construction of the diagnosis model, source training data are obtained in the corresponding industry according to the industry type of the enterprise; the acquired data at least comprises six-dimensional large-class data of enterprise basic data, enterprise financing data, enterprise operation data, enterprise production awareness data, enterprise label data and enterprise competitive product data, and the service requirement classes comprise achievement transaction service, data service, achievement conversion service, entrepreneurship service and professional service.
Filtering and preprocessing the acquired source data under the industry category, extracting key information effective to demand analysis, and eliminating noise and invalid information; extracting deep fusion characteristics of enterprise data; performing word vector extraction on the preprocessed enterprise text data according to preset data dimensions by an enterprise, performing deep fusion on the acquired enterprise data word vector characteristics of multiple dimensions, performing convolution operation on a first dimension characteristic through two branches, wherein the first branch comprises three convolutional layers, the second branch comprises one convolutional layer, and obtaining word vector fusion characteristics under the dimensions through the convolutional layer processing of the two branches; obtaining the correlation fusion characteristics of second dimension information and first dimension information, performing fusion add calculation on the word vector characteristics of the second dimension after the convolution operation of a third branch and the characteristics obtained by the convolution of the second branch of the first dimension characteristics, and finally performing concat calculation on the word vector fusion characteristics under the first dimension and the obtained correlation fusion characteristics among the dimensions, wherein the fusion operation is performed on the characteristics among the dimension characteristics, and finally obtaining the fusion characteristics of the dimension and the depth correlation characteristics among the dimensions; constructing a demand diagnosis model by using the finally obtained dimension fusion characteristics and the depth correlation characteristics among the dimensions; the number of specific samples and the process of model training are prior art and will not be described herein.
In enterprise demand diagnosis, the constructed recognition model is used for carrying out actual enterprise demand diagnosis, and demand service matched with the current stage demand of an enterprise is obtained.
The invention provides a mall mode service according to enterprise requirements, confirms and adjusts the requirement diagnosis result by combining the diagnosis result, and provides a personalized mall service module by combining the actual requirements of the enterprise;
a service demand party of an enterprise selects and issues demands in a corresponding service demand category in a scientific and creative mall, it is assumed that the enterprise A has a demand trading service demand exemplarily, the demands can be issued under the demand trading service in the scientific and creative mall, specific issued content comprises service demand type, demand detailed description, an existing basis, an existing condition, an expected effect, whether a broker issues, whether broker service is accepted, whether digestion and absorption capacity of the prior art exists, whether the enterprise has cooperation with other scientific research units, and the enterprise can select issued content items according to the own demand trading demand when issuing demands. After the enterprise issues enterprise requirements in a scientific and creative mall platform, when other enterprise technologies and services are matched with the enterprise technologies and services, the enterprise carries out requirement response on a requirement response page, after response is successful, a system can automatically generate a service order according to service contents of a contract, data generated in the service process and the service contract can be input into a data and contract management module of the system, state information of the service process carries out data recording of a service stage according to the requirement state, and the data recording comprises bidding in, service in, solved, unresolved and expired tags, and the system can automatically classify the data recording under a service column corresponding to a service management module according to the service requirement category, and provides subsequent service tracking and data backtracking. After the service contract is completed, the order is synchronously finished, and the enterprise scientific and creative service of the whole process and the whole chain is realized.
Similar to the achievement service transaction service, other types of services such as data service can be selected directly according to the required service, and a service order is generated according to the required type quantity and the like.
Under the service demand category, the data service comprises a financing data service, an industry map service and a customized data service; the achievement transformation service comprises policy consultation service, technical intermediary service and intellectual property service; the startup service comprises: business-creating consultation, policy service, science and technology finance, manpower service, internet service, carrier service, industrial and commercial finance and tax, legal service and software development; the professional services comprise product research and development, laboratory services, inspection and detection, verification and evaluation, equity financing and production outsourcing services.
The full chain full flow intelligent scientific and creative service data processing system comprises:
and the resident enterprise information input module is used for carrying out enterprise category division, the filling content of the enterprise information base mainly comprises enterprise basic information, enterprise products, technologies, markets, finance and other related information, and meanwhile, label marking is carried out according to the subdivision industry, the area and the like where the enterprise is located, and the enterprise information is input into the corresponding database.
The enterprise demand intelligent diagnosis module specifically comprises a diagnosis model construction module and an enterprise demand diagnosis module,
in the construction of the diagnosis model, source training data are obtained in the corresponding industry according to the industry type of the enterprise; the acquired data at least comprises six-dimensional large-class data of enterprise basic data, enterprise financing data, enterprise operation data, enterprise production awareness data, enterprise label data and enterprise competitive product data, and the service requirement classes comprise achievement transaction service, data service, achievement conversion service, entrepreneurship service and professional service. Filtering and preprocessing the acquired source data under the industry category, extracting key information effective to demand analysis, and eliminating noise and invalid information; extracting deep fusion characteristics of enterprise data; performing word vector extraction on the preprocessed enterprise text data according to preset data dimensions by an enterprise, performing deep fusion on the acquired enterprise data word vector characteristics of multiple dimensions, performing convolution operation on a first dimension characteristic through two branches, wherein the first branch comprises three convolutional layers, the second branch comprises one convolutional layer, and obtaining word vector fusion characteristics under the dimensions through the convolutional layer processing of the two branches; obtaining the correlation fusion characteristics of second dimension information and first dimension information, performing fusion add calculation on the word vector characteristics of the second dimension after the convolution operation of a third branch and the characteristics obtained by the convolution of the second branch of the first dimension characteristics, and finally performing concat calculation on the word vector fusion characteristics under the first dimension and the obtained correlation fusion characteristics among the dimensions, wherein the fusion operation is performed on the characteristics among the dimension characteristics, and finally obtaining the fusion characteristics of the dimension and the depth correlation characteristics among the dimensions; constructing a demand diagnosis model by using the finally obtained dimension fusion characteristics and the depth correlation characteristics among the dimensions; the number of specific samples and the process of model training are prior art and will not be described herein.
In enterprise demand diagnosis, the constructed recognition model is used for carrying out actual enterprise demand diagnosis, and demand service matched with the current stage demand of an enterprise is obtained.
The invention provides a mall mode service according to enterprise requirements, which comprises a requirement confirmation module, a service data, a contract, an order recording and tracking module, wherein the requirement confirmation module confirms and adjusts a requirement diagnosis result by combining the diagnosis result and provides a personalized mall service module by combining the actual requirements of an enterprise;
the system comprises a service data, contract, order recording and tracking module, a service demand party of an enterprise selects and issues demands in a corresponding service demand category in a scientific and creative mall, an exemplary assumption A is that the enterprise has a demand for a result transaction service, the demand can be issued under the result transaction service in the scientific and creative mall, specific issued content comprises service demand type, demand detail, an existing basis, an existing condition, an expected effect, whether a broker issues, whether broker service is accepted, whether the digestion and absorption capacity of the prior art is available, whether the enterprise has cooperation with other scientific research units, and the enterprise can select issued content items according to the own demand for the result transaction when issuing demands. After an enterprise issues enterprise requirements in a scientific and creative mall platform, when other enterprise technologies and services are matched with the enterprise technologies and services, demand response is conducted on a demand response page, after response is successful, a system can automatically generate service orders according to service contents of contracts, data and service contracts generated in the service process can be input into a data and contract management module of the system, state information of the service process is subjected to data recording of a service stage through a demand state, and the data recording comprises bidding competition, bidding selection, service, solved, unresolved and expired tags, and the system can automatically classify the data recording under corresponding service fields of a service management module according to service requirement categories, and provide subsequent service tracking and data backtracking. And after the service contract is completed, the order synchronization is finished, and the enterprise scientific and creative service of the whole flow and the whole chain is realized.
Similar to the achievement service transaction service, other types of services such as data service can be selected directly according to the required service, and a service order is generated according to the required type quantity and the like.
Under the service demand category, the data service comprises investment and financing data service, industry map service and customized data service; the achievement transformation service comprises policy consultation service, technical intermediary service and intellectual property service; the startup service comprises: business-creating consultation, policy service, science and technology finance, manpower service, internet service, carrier service, industrial and commercial finance and tax, legal service and software development; the professional services comprise product research and development, laboratory services, inspection and detection, verification and evaluation, equity financing and production outsourcing services.
Besides, the application also provides a computing device and a computer-readable storage medium of the full-chain full-flow intelligent scientific and creative service data processing method, which are characterized by comprising a processor and a memory, wherein the memory stores computer executable instructions capable of being executed by the processor, and the processor executes the computer executable instructions to realize the enterprise demand intelligent diagnosis method. When invoked and executed by a processor, the computer-executable instructions cause the processor to implement the enterprise demand data processing method described above.
Compared with the prior art, the invention has the beneficial effects that: enterprise requirements are diagnosed through intelligent enterprise requirements, the full-flow online management of the scientific and industrial mall serving the requirements of the scientific and industrial enterprise is provided, and follow-up flow monitoring and follow-up data management are facilitated. Starting from enterprise requirements, a service mode of a scientific and creative mall is provided, modular management is carried out on each stage of enterprise service, service contracts are generated and can be input into a contract management module of the system, and the system can automatically generate service orders according to service contents of the contracts. After the order is generated, the system can automatically classify the service under the corresponding service column of the service management module according to the service requirement category, and provide subsequent service tracking and cash withdrawal management. And the enterprise scientific and creative service of the whole process and the whole chain is realized. The data processing and system provides intelligent and visual full-chain full-flow management for investment institutions or service institutions with investment functions, incubators, park operation institutions and the like, timely tracks important progress items of enterprises, facilitates all levels of investment institutions to check related conditions, reduces dependence on investment managers and post-investment responsible persons, and reduces investment risks.
Drawings
FIG. 1 is a flow chart of the application for data processing of the scientific and creative service;
FIG. 2 is a schematic diagram of a deep correlation feature extraction network between dimensions in an intelligent diagnosis model of the present application.
Detailed Description
The invention is described in further detail below with reference to the accompanying drawings:
the full-chain full-flow intelligent scientific and creative service data processing method can be specifically shown in the attached drawing 1, and specifically comprises the following steps:
entering the resident enterprise information, classifying the enterprise categories, filling the enterprise information base mainly comprising the enterprise basic information, enterprise products, technologies, markets, finance and other related information, labeling the tags according to the subdivision industry, areas and the like where the enterprise is located, and entering the enterprise information into the corresponding database.
The method comprises the steps of enterprise demand intelligent diagnosis, specifically comprising a diagnosis model construction process and an enterprise demand diagnosis process, wherein in the diagnosis model construction, source training data are obtained in corresponding industries according to the industry types of the enterprises; the acquired data at least comprises six-dimensional large-class data of enterprise basic data, enterprise financing data, enterprise operation data, enterprise production knowledge data, enterprise tag data and enterprise competitive product data. The six-dimensional large-class data and the specifically contained data subclass information are shown in the following table:
| data dimension | Subclass of data |
| Enterprise base data | Enterprise name, enterprise full name, basic information, time of establishment, region, registered capital, personnel size |
| Enterprise financing data | Financing rounds, financing time, financing amount, investment organization |
| Business operation data | Brief introduction of main business, product sale condition and enterprise product type |
| Enterprise informed product data | Patent, trademark, copyright and soft work |
| Enterprise tag data | Large category of industry, application scene, financing situation |
| Enterprise competitive product data | Competitor basic data, competitor financing data, competitor operation data |
The method collects 10 ten thousand large and medium-sized enterprises as source data samples, extracts service data containing the corresponding stages of the data, and sets a plurality of specific service subclasses under each specific service requirement class, wherein the service requirement classes comprise data service, operation consultation, entrepreneurst service and professional service, and are shown in the following table:
filtering and preprocessing the acquired source data under the industry category, extracting key information effective to demand analysis, and eliminating noise and invalid information; extracting deep fusion characteristics of enterprise data; performing word vector extraction on the preprocessed enterprise text data according to preset data dimensions by an enterprise, performing deep fusion on the acquired enterprise data word vector characteristics of multiple dimensions, performing convolution operation on a first dimension characteristic through two branches, wherein the first branch comprises three convolutional layers, the second branch comprises one convolutional layer, and obtaining word vector fusion characteristics under the dimensions through the convolutional layer processing of the two branches; obtaining the correlation fusion characteristics of second dimension information and first dimension information, performing fusion add calculation on the word vector characteristics of the second dimension after the convolution operation of a third branch and the characteristics obtained by the convolution of the second branch of the first dimension characteristics, and finally performing concat calculation on the word vector fusion characteristics under the first dimension and the obtained correlation fusion characteristics among the dimensions, wherein the fusion operation is performed on the characteristics among the dimension characteristics, and finally obtaining the fusion characteristics of the dimension and the depth correlation characteristics among the dimensions; constructing a demand diagnosis model by using the finally obtained dimension fusion characteristics and the depth correlation characteristics among the dimensions;
in this embodiment and referring specifically to fig. 2, the first branch of the first dimension feature is passed through a three-layer structure with convolution kernels of 1 × 1 and 5 × 5 and 1 × 1, and the second branch convolution kernel is 1 × 1. The third branch is a three-layer structure with convolution kernels of 1 × 1, 5 × 5 and 1 × 1, so that not only can own dimensional data be fused through different channels to obtain fusion characteristics under different receptive fields, but also different dimensional characteristic fusion is performed through a plurality of channels with different dimensions, and the depth semantic characteristics with high word vector characteristic correlation can be obtained. Similar characteristics among other dimensions are subjected to fusion characteristic processing in the same process, so that the accuracy of model analysis can be greatly improved.
After the input word vectors are fused through the feature fusion channel, the features with higher latitude are generated, so that the pooling layer operation and the full-connection layer calculation are subsequently performed, and finally the requirement is output through the classification layerAs a result, wherein the activation function employs a Relu activation function and the loss function employs a multi-class cross entropy (cross entropy) loss function:
wherein K is the number of label values of the required classes in model training, y is a real label for a sample point i, yi, K =1, otherwise, is equal to 0, i is the number of samples, the probability that the sample i belongs to the label K is pi, K, N is the total number of samples,
loss values for training.
In enterprise demand diagnosis, the constructed recognition model is used for carrying out actual enterprise demand diagnosis, and a demand service class matched with the current stage demand of an enterprise is obtained. The number of specific samples and the process of model training are prior art and will not be described herein.
The method comprises the steps of requirement confirmation and adjustment, namely confirming and adjusting a requirement diagnosis result by combining a diagnosis result, and providing mall mode service according to enterprise requirements by combining actual requirements of an enterprise;
the invention provides a business mall type service module, a plurality of service plates and labels are arranged under the business mall module, and enterprises select service requirement categories according to own requirements, wherein the service requirement categories comprise various achievement transaction services, data services, achievement transformation services, entrepreneurship services and professional services;
a service demand party of an enterprise selects and issues demands in a corresponding service demand category in a scientific and creative mall, it is assumed that the enterprise A has a demand trading service demand exemplarily, the demands can be issued under the demand trading service in the scientific and creative mall, specific issued content comprises service demand type, demand detailed description, an existing basis, an existing condition, an expected effect, whether a broker issues, whether broker service is accepted, whether digestion and absorption capacity of the prior art exists, whether the enterprise has cooperation with other scientific research units, and the enterprise can select issued content items according to the own demand trading demand when issuing demands.
The system can automatically classify the service into a service column corresponding to a service management module according to the service requirement category and provide subsequent service tracking and data backtracking. And after the service contract is completed, the order synchronization is finished, and the enterprise scientific and creative service of the whole flow and the whole chain is realized.
Similar to the achievement service transaction service, other types of services such as data service can be selected directly according to the required service, and a service order is generated according to the required type quantity and the like.
Under the service demand category, the data service comprises investment and financing data service, industry map service and customized data service; the achievement transformation service comprises policy consultation service, technical intermediary service and intellectual property service; the startup service comprises: business-creating consultation, policy service, science and technology finance, manpower service, internet service, carrier service, industrial and commercial finance and tax, legal service and software development; the professional services comprise product research and development, laboratory services, inspection and detection, verification and evaluation, equity financing and production outsourcing services.
In addition, the application also provides a full-chain full-flow intelligent scientific and creative service data processing method and a full-chain full-flow intelligent scientific and creative service data processing system, which are characterized by comprising a processor and a memory, wherein the memory stores computer executable instructions capable of being executed by the processor, and the processor executes the computer executable instructions to realize the enterprise demand intelligent diagnosis method. When invoked and executed by a processor, the computer-executable instructions cause the processor to implement the enterprise demand data processing method described above.
In the description of the present invention, it is to be noted that, unless otherwise explicitly specified or limited, the terms "connected" and "connected" are to be interpreted broadly, e.g., as being fixed or detachable or integrally connected; can be mechanically or electrically connected; may be directly connected or indirectly connected through an intermediate. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
In the description of the present invention, unless otherwise specified, the terms "upper", "lower", "left", "right", "inner", "outer", and the like, indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, are merely for convenience of description and simplification of description, and do not indicate or imply that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be construed as limiting the present invention.
Finally, it should be noted that the above-mentioned technical solution is only one embodiment of the present invention, and it will be apparent to those skilled in the art that various modifications and variations can be easily made based on the application method and principle of the present invention disclosed, and the method is not limited to the above-mentioned specific embodiment of the present invention, so that the above-mentioned embodiment is only preferred, and not restrictive.
Claims (8)
1. A full-chain full-flow intelligent scientific and creative service data processing method is characterized by comprising the following steps: entering resident enterprise information, classifying the resident enterprises, wherein the filling content of an enterprise information base comprises enterprise basic information, enterprise financing data, enterprise management data, enterprise production known data, enterprise label data and enterprise competitive product data, labeling the labels according to the subdivision industries and areas where the enterprises are located, and entering the enterprise information into a corresponding database;
the enterprise demand intelligent diagnosis specifically comprises a diagnosis model construction process and an enterprise demand diagnosis process, and the intelligent enterprise demand diagnosis model is constructed by acquiring historical enterprise data samples to carry out data deep mining; in enterprise demand diagnosis, the built diagnosis model is used for carrying out demand diagnosis on the resident enterprise to obtain a demand service class matched with the current stage demand of the enterprise; the obtained historical enterprise data sample at least comprises six-dimensional large-class data of enterprise basic data, enterprise financing data, enterprise operation data, enterprise known production data, enterprise tag data and enterprise competitive product data;
the construction of the diagnosis model specifically comprises the following steps: in the construction of a diagnosis model, preprocessing sample source training data; acquiring source training data in a corresponding industry according to the industry category to which the enterprise belongs; the acquired data at least comprises six-dimensional large-class data of enterprise basic data, enterprise financing data, enterprise operation data, enterprise production awareness data, enterprise label data and enterprise competitive product data, and the service requirement class comprises achievement transaction service, data service, achievement conversion service, entrepreneurship service and professional service;
performing word vector extraction on the preprocessed enterprise text data according to a preset data dimension, performing deep fusion on the acquired enterprise data word vector characteristics of multiple dimensions, and specifically performing convolution operation on a first dimension characteristic through two branches, wherein the first branch comprises three convolutional layers, the second branch comprises one convolutional layer, and the word vector fusion characteristic under the dimension is obtained through processing of the convolutional layers of the two branches;
obtaining the correlation fusion characteristics of second dimension information and first dimension information, performing fusion add calculation on the word vector characteristics of the second dimension after the convolution operation of a third branch and the characteristics obtained by the convolution of the second branch of the first dimension characteristics, and finally performing concat calculation on the word vector fusion characteristics under the first dimension and the obtained correlation fusion characteristics among the dimensions, wherein the fusion operation is performed on the characteristics among the dimension characteristics, and finally obtaining the fusion characteristics of the dimension and the depth correlation characteristics among the dimensions;
constructing a demand diagnosis model by using the finally obtained dimension fusion characteristics and the depth correlation characteristics among the dimensions;
after the requirement type of the enterprise is obtained, providing mall mode service for the enterprise according to the obtained requirement, and confirming and adjusting the requirement service type by the enterprise according to the result obtained by diagnosis; specifically, a plurality of service plates and tags are arranged under a scientific and creative mall module, and an enterprise issues service requirements on a requirement issuing page;
when the services of other enterprises are matched with the issued service requirements, the demand response is carried out on the demand response page, after the response is successful, a service order is automatically generated according to the service content of the contract, and data and contract management modules are input into the data and contract management module in the service process and the service contract;
the service generation data and the service contract are both input into a data and contract management module, the state information of the service process carries out data recording of the service stage through the demand state, the data recording is automatically classified under the corresponding service column of the service management module according to the service demand type, and subsequent service tracking and data backtracking are provided;
and after the service contract is completed, the order synchronization is finished, and the enterprise scientific and creative service of the whole flow and the whole chain is realized.
2. The intelligent scientific service data processing method according to claim 1, characterized in that: a plurality of service plates and labels are arranged in the mall service, and the service plates and the labels comprise one or more of achievement transaction service, data service, achievement conversion service, entrepreneurship service and professional service.
3. The intelligent scientific service data processing method according to claim 1, characterized in that: and the state information of the service process carries out data recording of the service stage through the demand state, wherein the data recording comprises bidding competition, bidding selection, serving, solved, unresolved and expired tags.
4. A full chain full flow intelligent scientific and creative service data processing system is characterized by comprising: the resident enterprise information input module is used for classifying resident enterprises, filling contents of an enterprise information base comprise enterprise basic information, enterprise financing data, enterprise management data, enterprise known production data, enterprise label data and enterprise competitive product data, labeling is carried out according to subdivision industries and areas where the enterprises are located, and the enterprise information is input into a corresponding database;
the enterprise demand intelligent diagnosis module specifically comprises a diagnosis model construction process and an enterprise demand diagnosis process, and constructs an intelligent enterprise demand diagnosis model by acquiring historical enterprise data samples to perform data deep mining; in enterprise demand diagnosis, the built diagnosis model is used for carrying out demand diagnosis on the resident enterprise to obtain demand service matched with the current stage demand of the enterprise; the obtained historical enterprise data sample at least comprises six-dimensional large-class data of enterprise basic data, enterprise financing data, enterprise operation data, enterprise known production data, enterprise tag data and enterprise competitive product data;
the construction of the diagnosis model specifically comprises the following steps: in the construction of a diagnosis model, source training data are preprocessed;
acquiring source training data in a corresponding industry according to the industry category to which the enterprise belongs; the acquired data at least comprises six-dimensional large-class data of enterprise basic data, enterprise financing data, enterprise operation data, enterprise production awareness data, enterprise label data and enterprise competitive product data, and the service requirement class comprises achievement transaction service, data service, achievement conversion service, entrepreneurship service and professional service;
performing word vector extraction on the preprocessed enterprise text data according to a preset data dimension, performing deep fusion on the acquired enterprise data word vector characteristics of multiple dimensions, and specifically performing convolution operation on a first dimension characteristic through two branches, wherein the first branch comprises three convolutional layers, the second branch comprises one convolutional layer, and the word vector fusion characteristic under the dimension is obtained through processing of the convolutional layers of the two branches;
obtaining the correlation fusion characteristics of second dimension information and first dimension information, performing fusion add calculation on the word vector characteristics of the second dimension after the convolution operation of a third branch and the characteristics obtained by the convolution of the second branch of the first dimension characteristics, and finally performing concat calculation on the word vector fusion characteristics under the first dimension and the obtained correlation fusion characteristics among the dimensions, wherein the fusion operation is performed on the characteristics among the dimension characteristics, and finally obtaining the fusion characteristics of the dimension and the depth correlation characteristics among the dimensions;
constructing a demand diagnosis model by using the finally obtained dimension fusion characteristics and the depth correlation characteristics among the dimensions;
the mall service module is used for providing mall mode service for the enterprises according to the obtained requirements after the requirement categories of the enterprises are obtained, and the enterprises confirm and adjust the requirement service categories according to the results obtained by diagnosis;
specifically, a plurality of service plates and tags are arranged under a scientific and creative mall module, and an enterprise issues service requirements on a requirement issuing page;
the system comprises a service data, contract and order recording and tracking module, a demand response is carried out in a demand release page when the service of other enterprises is matched with the released service demand, after the response is successful, the system can automatically generate a service order according to the service content of the contract, and the data generated in the service process and the service contract are both recorded into a data and contract management module of the system;
the data and contract management module is recorded with service generation data and service contracts, the state information of the service process carries out data recording of the service stage through the demand state, the system automatically classifies the data recording under the corresponding service column of the service management module according to the service demand type, and provides subsequent service tracking and data backtracking;
and after the service contract is completed, the order synchronization is finished, and the enterprise scientific and creative service of the whole flow and the whole chain is realized.
5. The intelligent scientific service data processing system according to claim 4, wherein: a plurality of service plates and labels are arranged under the mall service module, and enterprises select service requirement categories according to own requirements, wherein the service requirement categories comprise one or more of achievement transaction service, data service, achievement conversion service, entrepreneurship service and professional service.
6. The intelligent scientific service data processing system according to claim 4, wherein: and the state information of the service process carries out data recording of the service stage through the demand state, wherein the data recording comprises bidding competition, bidding selection, serving, solved, unresolved and expired tags.
7. A computer device comprising a processor and a memory, the memory storing computer-executable instructions executable by the processor, the processor executing the computer-executable instructions to implement the method of any one of claims 1 to 3.
8. A computer-readable storage medium having computer-executable instructions stored thereon which, when invoked and executed by a processor, cause the processor to perform the method of any of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210243920.0A CN114331230B (en) | 2022-03-14 | 2022-03-14 | Full-chain full-flow intelligent scientific and creative service data processing method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210243920.0A CN114331230B (en) | 2022-03-14 | 2022-03-14 | Full-chain full-flow intelligent scientific and creative service data processing method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114331230A CN114331230A (en) | 2022-04-12 |
| CN114331230B true CN114331230B (en) | 2022-06-21 |
Family
ID=81033887
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210243920.0A Active CN114331230B (en) | 2022-03-14 | 2022-03-14 | Full-chain full-flow intelligent scientific and creative service data processing method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114331230B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116797186B (en) * | 2023-08-25 | 2023-12-15 | 上海甄零科技有限公司 | Promise management method, device, equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109784669A (en) * | 2018-12-24 | 2019-05-21 | 北京航天智造科技发展有限公司 | Based on the mating cloud manufacturing service system with resource-sharing business of industrial collaboration |
| CN109934680A (en) * | 2019-03-15 | 2019-06-25 | 广东省科技基础条件平台中心 | A kind of " internet+" scientific and technological crowd grinds service innovation and application system |
| CN111861739A (en) * | 2019-04-29 | 2020-10-30 | 重庆市科学技术研究院 | Scientific research achievement conversion transaction service system |
| CN112364638A (en) * | 2020-10-13 | 2021-02-12 | 北京工业大学 | Personality identification method based on social text |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109657944A (en) * | 2018-12-06 | 2019-04-19 | 新疆麦肯锡信息科技有限公司 | Enterprise's Life cycle intelligent Service system |
| CN113065698A (en) * | 2021-03-25 | 2021-07-02 | 珠海大横琴科技发展有限公司 | Service processing method and device |
-
2022
- 2022-03-14 CN CN202210243920.0A patent/CN114331230B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109784669A (en) * | 2018-12-24 | 2019-05-21 | 北京航天智造科技发展有限公司 | Based on the mating cloud manufacturing service system with resource-sharing business of industrial collaboration |
| CN109934680A (en) * | 2019-03-15 | 2019-06-25 | 广东省科技基础条件平台中心 | A kind of " internet+" scientific and technological crowd grinds service innovation and application system |
| CN111861739A (en) * | 2019-04-29 | 2020-10-30 | 重庆市科学技术研究院 | Scientific research achievement conversion transaction service system |
| CN112364638A (en) * | 2020-10-13 | 2021-02-12 | 北京工业大学 | Personality identification method based on social text |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114331230A (en) | 2022-04-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7672915B2 (en) | Method and system for labelling unlabeled data records in nodes of a self-organizing map for use in training a classifier for data classification in customer relationship management systems | |
| Kumar et al. | Machine learning (ML) technologies for digital credit scoring in rural finance: A literature review | |
| CN112380870A (en) | User intention analysis method and device, electronic equipment and computer storage medium | |
| Hosseinnia Shavaki et al. | Applications of deep learning into supply chain management: a systematic literature review and a framework for future research | |
| CN114331230B (en) | Full-chain full-flow intelligent scientific and creative service data processing method and system | |
| Kureljusic et al. | Forecasting in financial accounting with artificial intelligence–A systematic literature review and future research agenda | |
| CN115293537A (en) | Enterprise policy matching degree evaluation method and system based on big data and artificial intelligence | |
| CN115309864A (en) | Intelligent sentiment classification method and device for comment text, electronic equipment and medium | |
| Li et al. | Credit risk prediction model for listed companies based on CNN-LSTM and Attention mechanism | |
| CN113902569A (en) | Method for identifying the proportion of green assets in digital assets and related products | |
| CN116402625B (en) | Customer evaluation method, apparatus, computer device and storage medium | |
| CN114331226B (en) | Intelligent enterprise demand diagnosis method and system and storage medium | |
| Shi et al. | A general neural framework for classification rule mining | |
| Khan et al. | Review of city pricing system analysis based on big data | |
| Mahalle et al. | Data Acquisition and Preparation | |
| Ha et al. | Deep Learning Models for Predicting Monthly TAIEX to Support Making Decisions in Index Futures Trading | |
| Asim et al. | Supporting Management Disciplines for Research and Development in Public Organizations | |
| CN110399988A (en) | Equipment portrait generation method and system | |
| Mombeini et al. | New fuzzy logic approach for the capability assessment of renewable energy technologies: Case of Iran | |
| CN115952259B (en) | Intelligent generation method of enterprise portrait tag | |
| Kaipio | Default prediction modeling of Swedish SMEs with machine learning | |
| CN113837861A (en) | User grouping-based collection urging method and device, storage medium and equipment | |
| Mashood et al. | ARTIFICIAL INTELLIGENCE RECENT TRENDS AND APPLICATIONS IN INDUSTRIES | |
| SANTOSH et al. | ANALYZING LARGE SCALE BUSINESS DATA TO PREDICT COMPANY'S GROWTH USING AN INTEGRATED HYBRID APPROACH OF DATA REDUCTION UNIT AND CONVOLUTIONAL NEURAL NETWORKS | |
| Chen et al. | Research on Extraction Method of Credit Risk Analysis of Corporate Bonds Based on Convolutional Neural Network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| EE01 | Entry into force of recordation of patent licensing contract | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20220412 Assignee: Liantai Kechuang (Tianjin) Co.,Ltd. Assignor: Tianjin Lianchuang Technology Development Co.,Ltd. Contract record no.: X2023120000051 Denomination of invention: A data processing method and system for intelligent science and technology innovation services throughout the entire chain and process Granted publication date: 20220621 License type: Common License Record date: 20231222 |
|
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20220412 Assignee: Tianjin Liankai Technology Co.,Ltd. Assignor: Tianjin Lianchuang Technology Development Co.,Ltd. Contract record no.: X2023980054259 Denomination of invention: A data processing method and system for intelligent science and technology innovation services throughout the entire chain and process Granted publication date: 20220621 License type: Common License Record date: 20231227 |
|
| EE01 | Entry into force of recordation of patent licensing contract | ||
| EE01 | Entry into force of recordation of patent licensing contract | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20220412 Assignee: Tianjin United Chuangxing Technology Development Co.,Ltd. Assignor: Tianjin Lianchuang Technology Development Co.,Ltd. Contract record no.: X2023980054801 Denomination of invention: A data processing method and system for intelligent science and technology innovation services throughout the entire chain and process Granted publication date: 20220621 License type: Common License Record date: 20240102 |
|
| EE01 | Entry into force of recordation of patent licensing contract | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20220412 Assignee: Yunneng Zhongchuang Investment Management (Tianjin) Co.,Ltd. Assignor: Tianjin Lianchuang Technology Development Co.,Ltd. Contract record no.: X2024980000234 Denomination of invention: A data processing method and system for intelligent science and technology innovation services throughout the entire chain and process Granted publication date: 20220621 License type: Common License Record date: 20240105 Application publication date: 20220412 Assignee: Tianjin 1919 Technology Co.,Ltd. Assignor: Tianjin Lianchuang Technology Development Co.,Ltd. Contract record no.: X2024980000180 Denomination of invention: A data processing method and system for intelligent science and technology innovation services throughout the entire chain and process Granted publication date: 20220621 License type: Common License Record date: 20240104 |
|
| EE01 | Entry into force of recordation of patent licensing contract | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20220412 Assignee: Tianjin Xingdu Space Network Technology Co.,Ltd. Assignor: Tianjin Lianchuang Technology Development Co.,Ltd. Contract record no.: X2024980000344 Denomination of invention: A data processing method and system for intelligent science and technology innovation services throughout the entire chain and process Granted publication date: 20220621 License type: Common License Record date: 20240109 |
|
| EE01 | Entry into force of recordation of patent licensing contract | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20220412 Assignee: Tianjin Huihe Investment Management Co.,Ltd. Assignor: Tianjin Lianchuang Technology Development Co.,Ltd. Contract record no.: X2024980000705 Denomination of invention: A data processing method and system for intelligent science and technology innovation services throughout the entire chain and process Granted publication date: 20220621 License type: Common License Record date: 20240112 Application publication date: 20220412 Assignee: TIANJIN YONGRUI BUSINESS INFORMATION CONSULTATION CO.,LTD. Assignor: Tianjin Lianchuang Technology Development Co.,Ltd. Contract record no.: X2024980000704 Denomination of invention: A data processing method and system for intelligent science and technology innovation services throughout the entire chain and process Granted publication date: 20220621 License type: Common License Record date: 20240112 Application publication date: 20220412 Assignee: Gongneng Enterprise Management Consulting (Tianjin) Co.,Ltd. Assignor: Tianjin Lianchuang Technology Development Co.,Ltd. Contract record no.: X2024980000518 Denomination of invention: A data processing method and system for intelligent science and technology innovation services throughout the entire chain and process Granted publication date: 20220621 License type: Common License Record date: 20240111 |