Intelligent information pushing method and intelligence information pushing system
By obtaining the list of public entities and the name of R&D projects, generating multiple business collections, and matching text and keywords according to project requirements, the problem of high noise in information push in existing software is solved, and accurate information push to technology companies is achieved, and user experience and software promotion effect is improved.
Patent Information
- Application Number
- CN202510659237.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-21
- Publication Date
- 2025-08-29
AI Technical Summary
When existing enterprise service software pushes information, there is a massive amount of information mixed with low-value information, which affects the user experience and software promotion of technology companies.
By obtaining the list of public entities and the name of the R&D project, multiple business collections are generated, and text and keyword matching are matched according to the project requirements, accurate information push is achieved and noisy information is avoided.
It has realized accurate information push to technology companies, improved user experience, and promoted further penetration and promotion of software products.
Smart Images
Figure CN120561375A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of intelligent information push, and in particular to an intelligent information push method and an intelligence information push system. Background Art
[0002] Existing enterprise service software faces numerous bottlenecks when responding to frequently changing business needs, and the user experience for enterprises needs to be gradually upgraded. For example, industrial policy service software targets technology companies, which are exposed to vast amounts of information daily. High-quality industry information can help these companies efficiently access industry trends. However, the existing software model of pushing massive amounts of information, while providing intelligence to technology companies, also contains a significant amount of low-value information. This not only impacts the user experience for these companies but also hinders the further penetration and promotion of software products.
[0003] Therefore, the industry needs to design an intelligence information push software to optimize the information intelligent push method and solve the above technical problems. Summary of the Invention
[0004] The technical problem to be solved by the present invention is: how to design an intelligent information push solution that can achieve accurate information push to technology companies.
[0005] To solve the above problems, in the first aspect, an embodiment of the present invention proposes a method for intelligent information push, which includes: S1, obtaining a list of public entities and the names of R&D topics corresponding to the list of public entities; S2, generating multiple corresponding business sets based on the list of public entities; S3, generating intelligent information push results based on the project requirement text, the name of the R&D topic, and the multiple business sets. The list of public entities is a public list that can be obtained by engineers in this field through technical means; if the name of the R&D topic of an enterprise meets the project requirement text, the name of the enterprise will appear in the list of public entities, and the list of public entities will appear in the total public list.
[0006] A further technical solution is that the step S1 of obtaining a list of public entities and the names of R&D topics corresponding to the list of public entities includes: S11 of obtaining a list of public entities of a recent version and the names of R&D topics corresponding to the list of public entities, using the current date as a reference time. The list of public entities of a recent version can be the most recently disclosed list of public entities or the lists of public entities disclosed several times in recent times, and engineers in this field can obtain it through technical means.
[0007] Its further technical solution is that the acquisition of the R&D subject names corresponding to the list of public entities includes: S101, taking the current date as the base time, acquiring the public list of the adjacent version; S102, identifying the funding amounts in the public list, excluding the funding amounts that are less than the preset value to obtain the target amount, and using the list corresponding to the target amount as the public entity list; S103, acquiring the funding title field corresponding to the public entity list; S104, extracting the non-topic field and the R&D subject field from the funding title field, splitting the non-topic field into the funding name and the project direction, and then classifying them according to the project direction, and directly converting the R&D subject field into the R&D subject name corresponding to the public entity list. In the above solution, the public list of the adjacent version is used to carry the public entity list, that is, the content of the public list is more comprehensive; the target amount is a funding amount with a relatively large value, and there is a public entity list that can correspond to the target amount in the public list.
[0008] Its further technical solution is that S2 generates corresponding multiple business sets based on the list of public entities, including: S201, judging the attributes of each enterprise on the list of public entities according to preset attribute classification rules, if the enterprise on the list of public entities belongs to a listed company, obtaining the first list belonging to the listed company, extracting A business, B business, and C business from the adjacent versions of the annual financial reports of each enterprise on the first list according to preset weights, and merging them as the first business set; S202, if the enterprise on the list of public entities does not belong to a listed company and has an official website, obtaining the corresponding second list, extracting up to M businesses from the official websites of each enterprise on the second list, and merging them as the second business set; S203, if the enterprise on the list of public entities does not belong to a listed company and does not have an official website, obtaining the corresponding third list, converting the subject names of each enterprise on the third list into individual businesses, and merging them as the third business set; S204, merging the first business set, the second business set, and the third business set to generate multiple business sets. In the above scheme, the preset weights can be freely defined, such as weights based on the business units' sales in the annual financial report. For example, if, based on the most recent annual financial report, business A accounts for 50% of sales, business B accounts for 20%, business C accounts for 10%, business D accounts for 5%, and business E accounts for 5%, then only the top three businesses, ABC, are counted and directly merged to form the first business set. The specific method for identifying or extracting the sales of business ABC is technically feasible for engineers in this field. Furthermore, the method extracts up to M businesses from the official websites of each company on the second list. This specifically refers to a maximum of M businesses per company, i.e., setting a business cap for each company using M. Furthermore, the project names of each company on the third list are converted into individual businesses, i.e., using "project names" to directly represent the companies on the third list. This allows listed companies, companies with websites, and companies without websites to be represented by the first, second, and third business sets, further facilitating in-depth analysis of the software system.
[0009] Its further technical solution is that the S3 generates information intelligent push results according to the project requirement text, the R&D topic name and multiple business sets, including: S301, obtaining the project requirement text, and filtering out the keyword information from the project requirement text according to the preset filtering rules; S302, calculating the matching degree between the keyword information and the R&D topic name; S303, sorting all the matching degrees from high to low to obtain the matching sorting result; S304, extracting the secondary key information whose ranking is not higher than the preset proportion in the matching sorting result, and matching the R&D topic name corresponding to the secondary key information with the first business set, according to the preset matching rules. The second business set and the third business set are matched to obtain N businesses that meet the preset matching rules; S305, the enterprises in the enterprise member database are matched with the N businesses, and after matching, N enterprises in the database corresponding to the N businesses that meet the preset matching rules are obtained, and a corresponding relationship between the N enterprises in the database and the names of the research and development topics is established based on the matching relationship between the N enterprises in the database and the names of the research and development topics; S306, based on the corresponding relationship between the N enterprises in the database and the names of the research and development topics, a corresponding relationship between the N enterprises in the database and the project requirements text is established, and based on the corresponding relationship, the project directions corresponding to the project requirements text are pushed to the N enterprises in the database respectively, thereby generating an intelligent information push result. Among them, the project requirements text comes from public information, that is, the conditions required for the enterprise to obtain the funding amount; according to the preset screening rules, that is, from the project requirements text of several hundred or several thousand words, keyword information related to the industry name is screened out. Furthermore, calculating the degree of matching between the keyword information and the name of the research and development topic is something that engineers in this field can achieve, for example, obtaining the degree of matching after performing semantic matching.
[0010] In the above scheme, the secondary key information with a ranking not higher than a preset ratio among the matching sorting results is extracted, and the preset ratio can be any value less than one-third; preferably, the secondary key information with a ranking not higher than one-fifth among the matching sorting results is extracted. Furthermore, the enterprise member database is specifically the enterprise that needs to be served by the intelligence information push system of this application, and does not belong to the same concept as the enterprise in the list of public entities; further, the project direction corresponding to the project requirement text is pushed to N enterprises in the database respectively. The project direction corresponding to the project requirement text here is highly matched with the needs of the enterprise member database, which effectively avoids the noise of information push and makes the technical means of intelligent information push more easily accepted by the enterprises in the enterprise member database, which is also conducive to the further promotion of the intelligence information push system.
[0011] In a second aspect, this application proposes an intelligence information push system, which is used to implement the intelligent information push method described in the first aspect. Furthermore, the intelligence information push system also includes a declaration notification module, a project announcement module, an industrial policy module, a project inquiry module, and a policy tool module. Compared to existing software systems, the intelligence information push system can achieve precise information push to technology companies.
[0012] During the process of developing the software system, the inventor discovered that the existing software systems in the industry are limited in promotion because they adopt a model of pushing massive amounts of information, which contains a lot of low-value information. The core reason for this phenomenon is that the noise of information push is too loud, and the industry has not yet proposed specific technical means to solve the above problems and meet the real needs of corporate customers. Therefore, this application proposes an intelligent information push method and an intelligence information push system. It no longer pushes information from the perspective of the companies in the database itself, but uses the list of public entities as the source, attaches importance to the correspondence between the project requirement text and the companies in the database, and gradually explores and pushes project directions that are more suitable for the companies in the database. Compared with existing software systems, it is easier to be accepted by companies in the corporate membership database.
[0013] To sum up, the existing model of software pushing massive amounts of information, while bringing intelligence to technology companies, also contains a lot of low-value information; this not only affects the user experience of technology companies, but also affects the further penetration and promotion of software products; based on this, the solution described in this application can achieve accurate information push to technology companies. BRIEF DESCRIPTION OF THE DRAWINGS
[0014] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.
[0015] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.
[0016] Figure 1 This is a main flow chart of the information intelligent push method provided by an embodiment of the present invention.
[0017] Figure 2 This is a sub-flowchart of the information intelligent push method provided by an embodiment of the present invention.
[0018] Figure 3 This is another sub-flowchart of the information intelligent push method provided by an embodiment of the present invention.
[0019] Figure 4 A simplified schematic diagram of the electronic device provided in an embodiment of the present invention. DETAILED DESCRIPTION
[0020] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.
[0021] It will be understood that when used in this specification and the appended claims, the terms “include” and “comprising” indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or other features, integers, steps, operations, elements, components and / or collections thereof.
[0022] It should also be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, the singular forms "a", "an" and "the" are intended to include the plural forms unless the context clearly indicates otherwise.
[0023] It should be further understood that the term "and / or" used in the present description and the appended claims refers to one or any combination and all possible combinations of the associated listed items, and includes these combinations.
[0024] As used in this specification and the appended claims, the term "if" can be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]," depending on the context.
[0025] In this specification and the appended claims, there may be multiple ways of expressing the same technical feature or professional term, such as adopting different forms of expression such as superordinate generalization, subordinate limitation or synonym replacement; those skilled in the art can clearly understand the essentially same technical meaning pointed to by different ways of expression based on their professional knowledge and in combination with the overall content of the specification and the drawings; the differences between different ways of expression are only reflected in the diversity at the textual level, and do not constitute a substantial modification or restriction of the technical solution, and will not affect the certainty of the scope of protection of the claims of this patent and the full disclosure of the technical content of the specification.
[0026] Example 1
[0027] See also Figures 1 to 3 As shown, an embodiment of the present invention proposes an intelligent information push method, which includes: S1, obtaining a list of public entities and the names of R&D topics corresponding to the list of public entities; S2, generating multiple corresponding business sets based on the list of public entities; S3, generating intelligent information push results based on the project requirement text, the name of the R&D topic, and the multiple business sets. The list of public entities is a public list that can be obtained by engineers in this field through technical means; if the name of the R&D topic of an enterprise meets the project requirement text, the name of the enterprise will appear in the list of public entities, and the list of public entities will appear in the total public list.
[0028] In one embodiment, the step S1 of obtaining a list of public entities and the names of research and development topics corresponding to the list of public entities includes: S11 of obtaining a list of public entities of a recent version and the names of research and development topics corresponding to the list of public entities, using the current date as a reference time. The list of public entities of a recent version may be the most recently disclosed list of public entities or the lists of public entities disclosed several times in recent times, and engineers in this field may obtain the list through technical means.
[0029] In one embodiment, the obtaining of the R&D topic names corresponding to the list of public entities includes: S101, taking the current date as the base time, obtaining the public list of the adjacent version; S102, identifying the funding amounts in the public list, excluding the funding amounts less than the preset values to obtain the target amounts, and using the list corresponding to the target amounts as the public entity list; S103, obtaining the funding title field corresponding to the public entity list; S104, extracting the non-topic field and the R&D topic field from the funding title field, splitting the non-topic field into the funding name and the project direction, and then classifying them according to the project direction, and directly converting the R&D topic field into the R&D topic name corresponding to the public entity list. In the above scheme, the public list of the adjacent version is used to carry the public entity list, that is, the content of the public list is more comprehensive; the target amount is a funding amount with a relatively large value, and there is a public entity list that can correspond to the target amount in the public list. Furthermore, splitting the non-topic fields into fund names and project directions and then classifying them according to project directions is conducive to classification from the perspective of project directions, thereby enriching the accumulation of project directions over time and providing support for project directions for subsequent intelligent information push.
[0030] During the process of developing the software system, the inventor discovered that the existing software systems in the industry are limited in promotion because they adopt a model of pushing massive amounts of information, which contains a lot of low-value information. The core reason for this phenomenon is that the noise of information push is too loud, and the industry has not yet proposed specific technical means to solve the above problems and meet the real needs of corporate customers. Therefore, this application proposes an intelligent information push method and an intelligence information push system. It no longer pushes information from the perspective of the companies in the database itself, but uses the list of public entities as the source, attaches importance to the correspondence between the project requirement text and the companies in the database, and gradually explores and pushes project directions that are more suitable for the companies in the database. Compared with existing software systems, it is easier to be accepted by companies in the corporate membership database.
[0031] In one embodiment, the S2 generates corresponding multiple business sets based on the list of public entities, including: S201, judging the attributes of each enterprise on the list of public entities according to preset attribute classification rules, if the enterprise on the list of public entities belongs to a listed company, obtaining a first list belonging to the listed company, extracting A business, B business, and C business from the adjacent versions of the annual financial reports of each enterprise on the first list according to preset weights, and merging them as a first business set; S202, if the enterprise on the list of public entities does not belong to a listed company and has an official website, obtaining a corresponding second list, extracting up to M businesses from the official websites of each enterprise on the second list, and merging them as a second business set; S203, if the enterprise on the list of public entities does not belong to a listed company and does not have an official website, obtaining a corresponding third list, converting the subject names of each enterprise on the third list into individual businesses, and merging them as a third business set; S204, merging the first business set, the second business set, and the third business set to generate multiple business sets. In the above scheme, the preset weights can be freely defined weights, such as weights based on the proportion of businesses in the financial annual report; for example, according to the latest financial annual report, business A accounts for 50% of sales, business B accounts for 20% of sales, business C accounts for 10% of sales, business D accounts for 5% of sales, and business E accounts for 5% of sales. Then, only the top three ABC businesses are counted, and the three are directly merged as the first business set. The specific method of identifying or extracting the sales of ABC business can be achieved by engineers in this field through technical means. Furthermore, the extraction of up to M businesses from the official websites of each enterprise in the second list specifically refers to up to M businesses of a single enterprise, that is, setting the business upper limit of a single enterprise by M. Furthermore, among the attributes of each enterprise in the list of public disclosure entities, the attributes are divided into three types: listed companies, non-listed companies with websites, and non-listed companies without websites; the subject names of each enterprise in the third list are converted into individual businesses, that is, the "subject name" is used to directly represent the enterprises in the third list. In this way, listed companies, non-listed companies with websites, and non-listed companies without websites can all be represented by the first business set, the second business set, and the third business set. The analysis of the business set is more conducive to the in-depth analysis of the software system.
[0032] In one embodiment, the method is used for an enterprise member database, and the enterprises in the enterprise member database are in-library enterprises; the S3 generates information intelligent push results based on the project requirement text, the R&D topic name and multiple business sets, including: S301, obtaining the project requirement text, and filtering out keyword information from the project requirement text according to preset filtering rules; S302, calculating the degree of match between the keyword information and the R&D topic name; S303, sorting all the matching degrees from high to low to obtain a matching sorting result; S304, extracting the secondary key information whose ranking is not higher than a preset ratio from the matching sorting results, and sorting the R&D topic name corresponding to the secondary key information according to the preset filtering rules. Assume that the matching rules are matched with the first business set, the second business set, and the third business set to obtain N businesses that meet the preset matching rules; S305, the enterprises in the enterprise member database are matched with the N businesses, and after matching, N enterprises in the database corresponding to the N businesses that meet the preset matching rules are obtained. Based on the matching relationship between the N enterprises in the database and the N businesses, a corresponding relationship is established between the N enterprises in the database and the names of the research and development topics; S306, based on the corresponding relationship between the N enterprises in the database and the names of the research and development topics, a corresponding relationship is established between the N enterprises in the database and the project requirements text, and based on this corresponding relationship, the project direction corresponding to the project requirements text is pushed to the N enterprises in the database, thereby generating an intelligent information push result. Among them, the project requirements text comes from public information, that is, the conditions required for the enterprise to obtain the funding amount; according to the preset screening rules, that is, from the project requirements text of several hundred or several thousand words, keyword information related to the industry name is filtered out. Furthermore, calculating the degree of match between the keyword information and the name of the research and development topic is something that engineers in this field can achieve, for example, by performing semantic matching to obtain the degree of match.
[0033] In the above scheme, the secondary key information whose ranking is not higher than the preset proportion is extracted from the matching sorting results, and the R&D topic name corresponding to the secondary key information is matched with the first business set, the second business set, and the third business set according to the preset matching rules to obtain N businesses that meet the preset matching rules; the specific mode of "according to the preset matching rules" is as follows: the semantics of the R&D topic name corresponds to "business content" belonging to the business, the first business set corresponds to "A business content, B business content, C business content" belonging to the business, the second business set corresponds to "at most M business contents" belonging to the business, and the third business set corresponds to "single business" belonging to the business. Therefore, the semantics of the R&D topic name and the semantics of the business set can be corresponded. Based on the semantics of the R&D topic name, N businesses that meet the preset matching rules can be selected from the first business set, the second business set, and the third business set.
[0034] Furthermore, the secondary key information refers to the part of keywords among all the keyword information that "does not match well" with the names of the R&D topics; in S303 and S304, the inventor took into account that the list of public entities means that the budget has been released, so there are some companies that are not so matched with the names of the R&D topics, but can still be announced in the list of public entities and obtain funding amounts. This intelligence information is pushed to the companies in the database, and its value is much higher than conventional information push. Therefore, compared with the existing technology, it is more easily accepted by the companies in the corporate member database.
[0035] In the above scheme, the secondary key information with a ranking not higher than a preset ratio among the matching sorting results is extracted, and the preset ratio can be any value less than one-third; preferably, the secondary key information with a ranking not higher than one-fifth among the matching sorting results is extracted. Furthermore, the enterprise member database is specifically the enterprise that needs to be served by the intelligence information push system of this application, and does not belong to the same concept as the enterprise in the list of public entities; further, the project direction corresponding to the project requirement text is pushed to N enterprises in the database respectively. The project direction corresponding to the project requirement text here is highly matched with the needs of the enterprise member database, which effectively avoids the noise of information push and makes the technical means of intelligent information push more easily accepted by the enterprises in the enterprise member database, which is also conducive to the further promotion of the intelligence information push system.
[0036] In one embodiment, the present application proposes an intelligence information push system, which is used to implement the intelligent information push method described in any of the above embodiments. Furthermore, the intelligence information push system also includes a declaration notification module, a project announcement module, an industrial policy module, a project inquiry module, and a policy tool module.
[0037] To sum up, the existing model of software pushing massive amounts of information, while bringing intelligence to technology companies, also contains a lot of low-value information; this not only affects the user experience of technology companies, but also affects the further penetration and promotion of software products; based on this, the solution described in this application can achieve accurate information push to technology companies.
[0038] Example 2
[0039] See also Figure 4 , Figure 4This is a block diagram of an electronic device provided by the present invention. This electronic device can be a terminal or a server. A terminal can be a smartphone, tablet computer, laptop computer, desktop computer, personal digital assistant, wearable device, or other electronic device with communication capabilities. The device includes a processor 111, a communication interface 112, a memory 113, and a communication bus 114. The processor 111, communication interface 112, and memory 113 communicate with each other via the communication bus 114.
[0040] The memory 113 is used to store computer programs.
[0041] In one embodiment of the present invention, the processor 111 is configured to implement the method provided by any one of the aforementioned method embodiments when executing a program stored in the memory 113 .
[0042] It should be understood that in the embodiment of the present application, the processor 111 may be a central processing unit (CPU), and the processor 502 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.
[0043] Those skilled in the art will appreciate that all or part of the steps in the method of the above-described embodiment can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. The computer program is executed by at least one processor in the computer system to implement the steps in the method of the above-described embodiment.
[0044] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the components and steps of each example according to their functions. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions, but such implementation should not be considered to be beyond the scope of the present invention.
[0045] In the several embodiments provided herein, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the various units is merely a logical functional division, and actual implementation may employ other division methods. For example, units or components may be combined or integrated into another system, or some features may be omitted or not implemented.
[0046] The steps in the methods of the embodiments of the present invention may be adjusted in order, combined, or deleted as needed. The units in the devices of the embodiments of the present invention may be combined, divided, or deleted as needed. Furthermore, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit.
[0047] If this integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the existing technology, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a personal computer, terminal, or network device, etc.) to execute all or part of the steps of the method described in various embodiments of the present invention.
[0048] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0049] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, to the extent such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to encompass such changes and modifications.
[0050] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and such modifications or substitutions are intended to be within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be subject to the scope of protection of the claims.
Claims
1. A method for intelligent information push, characterized in that: The intelligent information push method includes: S1, obtain the list of public entities and the names of the research and development topics corresponding to the list of public entities; S2, generating corresponding multiple business sets based on the public subject list; S3 generates intelligent information push results based on project requirement text, R&D topic name, and multiple business sets.
2. The method for intelligent information push according to claim 1, characterized in that: The S1, obtaining a list of public entities and the names of R&D topics corresponding to the list of public entities, includes: S11, taking the current date as the reference time, obtaining the list of publicizing entities of the adjacent versions, and obtaining the names of the research and development topics corresponding to the list of publicizing entities.
3. The method for intelligent information push according to claim 2, characterized in that: The obtaining of the research and development topic names corresponding to the list of public entities includes: S101, using the current date as the base time, obtain the public list of the upcoming versions; S102, identifying the funding amounts in the publicized total list, excluding funding amounts less than a preset value to obtain a target amount, and using the list corresponding to the target amount as the publicized subject list; S103, obtaining the funding title field corresponding to the publicized subject list; S104, extract the non-topic field and the R&D topic field from the funding title field, split the non-topic field into the funding name and project direction, and then classify them according to the project direction, and directly convert the R&D topic field into the R&D topic name corresponding to the list of public entities.
4. The method for intelligent information push according to claim 3, characterized in that: The S2 generates corresponding multiple business sets based on the public subject list, including: S201: Determine the attributes of each enterprise on the list of public disclosure entities based on a preset attribute classification rule. If the enterprise on the list of public disclosure entities is a listed company, obtain a first list of listed companies, and extract business A, business B, and business C from the adjacent annual reports of each enterprise on the first list based on preset weights. Combine the extracted business A, business B, and business C into a first business set. S202: If the enterprise on the public disclosure list is not a listed company and has an official website, obtain the corresponding second list, extract up to M businesses from the official website of each enterprise on the second list, and merge them into a second business set; S203: If the enterprise on the public subject list is not a listed company and does not have an official website, obtain the corresponding third list, convert the subject name of each enterprise on the third list into a single business, and merge them into a third business set; S204: Merge the first service set, the second service set, and the third service set to generate multiple service sets.
5. The method for intelligent information push according to claim 4, characterized in that: S3 generates intelligent information push results based on the project requirement text, R&D topic name, and multiple business sets, including: S301, obtaining a project requirement text, and filtering out keyword information from the project requirement text according to a preset filtering rule; S302, calculating the matching degree between the keyword information and the R&D topic name; S303, sorting all matching degrees from high to low to obtain a matching sorting result; S304: Extracting secondary key information from the matching ranking results that is ranked no higher than a preset ratio, matching the R&D topic names corresponding to the secondary key information with the first business set, the second business set, and the third business set according to a preset matching rule, to obtain N businesses that meet the preset matching rule; S305: Match the enterprises in the enterprise member database with the N businesses, and obtain N enterprises in the database corresponding to the N businesses that meet the preset matching rules. Based on the matching relationship between the N enterprises in the database and the N businesses, a corresponding relationship between the N enterprises in the database and the names of the R&D topics is established; S306, establish a correspondence between N companies in the inventory and the project requirement text based on the correspondence between N companies in the inventory and the names of R&D topics, and push the project directions corresponding to the project requirement text to the N companies in the inventory based on the correspondence, thereby generating an intelligent information push result.
6. An intelligence information push system, characterized in that: The intelligence information push system is used to implement the information intelligent push method according to any one of claims 1 to 5.
7. The method for intelligent information push according to claim 6, characterized in that: The intelligence information push system also includes a declaration notification module, a project publicity module, an industrial policy module, a project inquiry module, and a policy tool module.