CN112488842A - Investment institution recommendation method and device - Google Patents
Investment institution recommendation method and device Download PDFInfo
- Publication number
- CN112488842A CN112488842A CN202011467198.6A CN202011467198A CN112488842A CN 112488842 A CN112488842 A CN 112488842A CN 202011467198 A CN202011467198 A CN 202011467198A CN 112488842 A CN112488842 A CN 112488842A
- Authority
- CN
- China
- Prior art keywords
- investment
- institution
- invested
- institutions
- recommendation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 28
- 230000006399 behavior Effects 0.000 claims abstract description 18
- 238000012163 sequencing technique Methods 0.000 claims abstract description 4
- 230000007246 mechanism Effects 0.000 claims description 48
- 238000003032 molecular docking Methods 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 5
- 230000008520 organization Effects 0.000 description 31
- 230000000875 corresponding effect Effects 0.000 description 21
- 238000011161 development Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000002195 synergetic effect Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/06—Asset management; Financial planning or analysis
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Human Resources & Organizations (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention relates to a recommendation method and a recommendation device for investment institutions, wherein different operation behaviors of items to be invested by the investment institutions are increased based on characteristic weight values of the items to be invested, and first recommendation investment institution results which are sorted according to weight ratios are determined based on the characteristic weight values, so that the investment recommendation based on contents is realized; the method comprises the steps that through obtaining historical investment institutions associated with items to be invested and determining results of second recommended investment institutions based on the sequence of association degrees among the historical investment institutions, collaborative-based investment recommendation is achieved; the investment recommendation based on relevance is realized by acquiring the description keywords of the item to be invested and determining the result of the third recommended investment institution based on the keyword proportion of the description keywords in the investment services of the investment institution; and comprehensively sequencing based on the weight occupied by the results of the three investment institutions to obtain the final recommended investment institution result. The accuracy of the recommendation result is ensured, and omnibearing service is provided for both investment parties.
Description
Technical Field
The invention belongs to the technical field of computer recommendation, and particularly relates to a recommendation method and device for an investment institution.
Background
The recommendation algorithm is an algorithm in computer profession, and what a user may like is presumed through some mathematical algorithms, and at present, the place where the recommendation algorithm is applied is mainly electronic commerce, and other goods that the user may like are presumed through some mathematical algorithms by using purchasing and browsing behaviors of the user. These years have also been used by many different industries to recommend content of interest to users over a network. Commonly used recommendation algorithms include content-based, collaboration-based, association rule-based, utility-based, knowledge-based, and the like.
At present, in the first-level market investment field of the financial industry, a content-based recommendation method is mainly applied to recommend investment institutions to entrepreneurial enterprises, investment preferences and institution feature labels of the investment institutions are extracted in a network data and form collection mode, the entrepreneurial enterprises are subjected to feature description with the same definition, the matching degree of the entrepreneurial enterprises and the investment institutions is calculated, and then the proper investment institutions are recommended for the enterprises. The existing recommendation mode is single in form and poor in matching effect due to low accuracy, and the requirement of enterprise development is difficult to adapt.
Disclosure of Invention
In order to solve the problems of low accuracy and poor matching effect in the prior art, the invention provides an investment institution recommendation method and device, which have the characteristics of higher accuracy, better matching effect and the like.
According to the embodiment of the invention, the investment institution recommendation method comprises the following steps:
respectively describing the characteristics of the investment institutions and the items to be invested based on preset labels, and matching the corresponding investment institutions based on the characteristic description of the items to be invested;
adding feature weight values of the items to be invested based on different operation behaviors of the items to be invested by the investment institutions, and determining first recommended investment institution results sorted according to weight ratios based on the feature weight values;
acquiring historical investment institutions associated with the items to be invested, and determining a second recommended investment institution result based on the sequence of the association degree among the historical investment institutions;
acquiring description keywords of the item to be invested, and determining a third investment institution recommending result based on the keyword proportion of the description keywords in the investment business of the investment institution;
and comprehensively ranking the investment institutions contained in the investment institutions respectively based on the weight of the first recommended investment institution result, the second recommended investment institution result and the third recommended investment institution result to obtain a final recommended investment institution result.
Further, the preset tag at least comprises: industry field, regional preference, round stage, billable amount, currency, institution category, major investment style, post-investment cooperation opportunities, and decision cycle.
Further, the preset tag further includes: the grade of the industry field, the specific province and city of the region preference, the stage and turn of the turn stage and the specific amount of the billable amount.
Further, the different operation behaviors of the investment institution on the item to be invested comprises:
viewing the item to be invested, viewing the corresponding business plan book and leaving the investment intention.
Further, the describing the characteristics of the investment institution and the project to be invested respectively based on the preset labels comprises:
and collecting information submitted by the investment institutions participating in the cooperation through the forms to extract corresponding characteristics.
Further, the describing the characteristics of the investment institution and the project to be invested based on the preset labels further comprises:
the features of the investment institutions active in the market are obtained by disclosing network data.
Further, the describing the characteristics of the investment institution and the project to be invested based on the preset labels further comprises:
and acquiring characteristics contained in the behavior data of the investment institution on the platform by constructing a project docking platform.
Furthermore, the docking platform is a wechat applet, and the wechat applet is connected with information of a speculative mechanism and a project to be invested.
Further, the describing the characteristics of the investment institution and the project to be invested based on the preset labels further comprises:
and comprehensively tracking the viewing, screening, searching and following of the speculative mechanism based on the WeChat small program, and increasing a characteristic weight value corresponding to the item to be invested based on different operation behaviors of the investment mechanism.
According to the embodiment of the invention, the investment institution recommendation device comprises:
the characteristic recommendation module is used for respectively describing the characteristics of the investment institutions and the items to be invested based on preset labels and matching the corresponding investment institutions based on the characteristic description of the items to be invested;
adding feature weight values of the items to be invested based on different operation behaviors of the items to be invested by the investment institutions, and determining first recommended investment institution results sorted according to weight ratios based on the feature weight values;
the collaborative recommendation module is used for acquiring historical investment institutions associated with the items to be invested and determining results of second recommended investment institutions based on the sequence of the association degrees among the historical investment institutions;
the associated recommendation module is used for acquiring the description keywords of the item to be invested and determining a third investment institution recommendation result based on the keyword proportion of the description keywords in the investment business of the investment institution; and
and the comprehensive recommendation module is used for comprehensively sequencing the investment institutions respectively contained based on the weight of the first recommended investment institution result, the second recommended investment institution result and the third recommended investment institution result to obtain a final recommended investment institution result.
The invention has the beneficial effects that: respectively describing the characteristics of the investment institutions and the items to be invested based on preset labels, and matching the corresponding investment institutions based on the characteristic description of the items to be invested; based on the characteristic weight values of the investment institution and the items to be invested, which are added according to different operation behaviors of the investment institution to the items to be invested, and based on the characteristic weight values, determining the first recommended investment institution results which are sorted according to the weight ratio, thereby realizing the investment recommendation based on the content; the method comprises the steps that through obtaining historical investment institutions associated with items to be invested and determining results of second recommended investment institutions based on the sequence of association degrees among the historical investment institutions, collaborative-based investment recommendation is achieved; the investment recommendation based on relevance is realized by acquiring the description keywords of the item to be invested and determining the result of the third recommended investment institution based on the keyword proportion of the description keywords in the investment services of the investment institution; and comprehensively sorting the investment institutions contained in the investment institutions respectively based on the weight of the first recommended investment institution result, the second recommended investment institution result and the third recommended investment institution result to obtain a final recommended investment institution result. The results are combined and sequenced in a weighting mode in a comprehensive mode of the three recommendation modes, the accuracy of the recommendation results is guaranteed, and all-round service is provided for both investment parties.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow chart of an investment institution recommendation method provided in accordance with an exemplary embodiment;
FIG. 2 is a block diagram providing a description of the features of a mechanism according to an exemplary embodiment;
fig. 3 is a schematic diagram of a speculative institution recommendation device provided in accordance with an exemplary embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be described in detail below. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from the examples given herein without any inventive step, are within the scope of the present invention.
Referring to fig. 1, an embodiment of the present invention provides an investment institution recommendation method, specifically including:
101. respectively describing the characteristics of the investment institutions and the items to be invested based on preset labels, and matching the corresponding investment institutions based on the characteristic description of the items to be invested;
102. adding feature weight values of the items to be invested based on different operation behaviors of the items to be invested by the investment institutions, and determining first recommended investment institution results sorted according to weight ratios based on the feature weight values;
103. acquiring historical investment institutions associated with the items to be invested, and determining a second recommended investment institution result based on the ranking of the association degree among the historical investment institutions;
104. acquiring description keywords of the item to be invested, and determining a third recommended investment institution result based on the keyword proportion of the description keywords in the investment services of the investment institution;
105. and comprehensively sorting the investment institutions contained in the investment institutions respectively based on the weight of the first recommended investment institution result, the second recommended investment institution result and the third recommended investment institution result to obtain a final recommended investment institution result.
Specifically, as a possible implementation manner of the above embodiment, firstly, feature-based recommendation is performed, and the description of the investment institution and the investment project features is performed with reference to the description label of the features shown in fig. 2, where the first-level description includes: industry field, regional preference, round stage, billable amount, currency, institution category, major investment style, post-investment cooperation opportunities, and decision cycle. The corresponding secondary characteristic description comprises the grade of the industry field, the specific province and city of the regional preference, the stage of the turn stage and the turn and the specific sum of the billable amount. The above features can be obtained in three ways:
1) the collection of forms is submitted by cooperative investment institutions;
2) obtaining characteristics of active investment institutions in the market through public network data;
3) the characteristics of the investors are obtained through behavior data of the investors on a private project docking platform;
the first two of these are conventional descriptions, and the description of the third is described below: the project docking platform can be a WeChat applet and displays various conditions of the investment institutions and financing projects thereof, wherein a part of labels of the enterprises and the financing projects thereof and investment preference labels of the investment institutions can realize one-to-one correspondence: after the authorized investment organization contacts a proper item in a list checking, screening, searching and following mode, different operation behaviors of the investment personnel of the organization can be tracked, and the characteristic weight value corresponding to the contacted item is correspondingly increased for the investment personnel according to different behaviors.
For example: when an institution investor looks up a project, the project belongs to the online medical service (secondary industry) of the medical industry (primary industry), the project is in Beijing City, the project belongs to the middle and later stages (financing stage), 1 million yuan (financing amount) RMB (financing currency type) in a D round (round) is wanted to be financed, and at the moment, 1 is added to the weighted value of the corresponding characteristic of the investment institution;
similarly, for a business plan that viewed the item (with a higher level of interest), 3 is added to the weight values of the corresponding features; for the features with the investment intention left, adding 10 to the weight values of the corresponding features; for the application and the enterprise to arrange the conference communication, adding 20 to the weighted values of the corresponding characteristics; when the investment institution performs screening and searching actions on the platform, the weighting values of the characteristics are also increased, for example: when an investment institution screens, selecting and screening a project of online medical service (secondary industry) of the medical industry (primary industry), and adding 10 to the weight value of the feature of the investment institution; similarly, when the institution investor searches for a keyword, if the keyword is an institution feature, adding 20 to the weight value of the corresponding feature; after the mechanism characteristics and the weight values are obtained through the 3 methods, a following mechanism characteristic description table is obtained:
| organization id | Name of organization | Basic information (omission) | Features of the mechanism | Weighted value | Weight ratio |
| 001 | Mechanism first | Omit | A1 | 50 | 25％ |
| A2 | 20 | 10％ | |||
| A3 | 10 | 5％ | |||
| A4 | 80 | 40％ | |||
| A6 | 10 | 5％ | |||
| A8 | 20 | 10％ | |||
| A9 | 10 | 5％ | |||
| 002 | Mechanism B | Omit | A1 | 50 | 25％ |
| A2 | 30 | 15％ | |||
| A5 | 10 | 5％ | |||
| A7 | 20 | 10％ | |||
| A9 | 90 | 45％ | |||
| 003 | Mechanism C | Omit | A3 | 70 | 35％ |
| A4 | 30 | 15％ | |||
| A6 | 10 | 5％ | |||
| A8 | 40 | 20％ | |||
| A9 | 50 | 25％ |
Thus, the basic data source of the investment institution preference data is obtained through the three description methods, the characteristics of the investment institution and the corresponding weight value of the investment institution are extracted through the corresponding computing platform, and the characteristics and the corresponding weight value are stored in the data storage layer. Thus, when an investment organization invests for a project to be invested of an enterprise, the characteristics of the enterprise and the financing project thereof are transmitted, the characteristics of the investment organization are used in a recommendation system to perform corresponding recommendation calculation, and a recommendation result is obtained and fed back to a corresponding user to check, for example: the items are characterized by A1, A5 and A9, and recommendation results are obtained and sorted by searching the mechanism with the highest weight ratio of the characteristics among the mechanism characteristics. It can be found that:
the weight ratio of A1+ A5+ A9 of the mechanism A is 25% + 0% + 5% + 30%;
the weight ratio of A1+ A5+ A9 of the mechanism B is 25% + 5% + 45% + 75%;
the mechanism a1+ a5+ a9 has a weight ratio of 0% + 0% + 25% to 25%. Thus, the sequential recommendation results are: organization b (75%), organization a (30%), organization c (25%).
Recommendations are then made based on the collaboration between the investment institutions: since each investment institution invests in a plurality of projects, and each project acquires investment participation of the plurality of institutions in different periods in the development process, the past investment cases of each investment institution can be analyzed, and the association degree between the institutions can be found.
For example: the institution A invests projects B1, B2, B3, B5, B6, B7, B8, B11, B15 and B20; (10 items);
institution B invested in projects B2, B3, B4, B6, B9, B10, B11, B12, B13, B14, B16, B18(12 projects);
institution C invests projects B2, B4, B6, B8, B10, B13, B16 and B19(8 projects);
the mechanism is characterized in that projects B1, B3, B5, B7, B9, B11, B13, B15, B17 and B19(10 projects) are invested;
the projects of the corporate investment of the organization A and the organization B are B2, B3, B6 and B11(4 projects), which account for 40 percent of the total investment projects (10 projects) of the organization A and 33 percent of the total investment projects (12 projects) of the organization B, so that the association degree of the organization A to the organization B is 40 percent, and the association degree of the organization B to the organization A is 33 percent. By analogy, a relevance table between organizations can be established:
when a user matches an investment organization with an enterprise financing project through a small program, the past investment organization of the enterprise is inquired through an enterprise database and is transmitted to a recommendation system, and the recommendation system calculates the recommended investment organization in an investment organization association data table through a corresponding recommendation algorithm and returns the recommended investment organization to the user.
For example: the investment institutions in past projects have a mechanism, and the association degree of the mechanism from the mechanism to the mechanism A can reach 60% through the association degree of mechanism cooperation, so that the mechanism A is recommended to the enterprise as the investment institution for financing consideration.
And then recommending based on the association between the enterprise invested by the organization: in order to improve the success rate of investment, a mechanism generally invests in a new enterprise with synergistic effect with an invested enterprise when investing, so that both the invested enterprise and a to-be-invested enterprise can be increased, and the synergistic effect between the two enterprises is calculated based on business description of the enterprise. For example: the enterprise B1 invested in organization A obtains the following keyword description by analyzing the development business description: c1, C3, C4, C5, and similar keyword descriptions of other enterprises invested in the same, the obtained keyword descriptions are as follows:
the B1 enterprise invested in agency a has the following business keyword descriptions: c1, C3, C4, C5;
the B2 enterprise invested in agency a has the following business keyword descriptions: c1, C2, C3, C4;
the B3 enterprise invested in agency a has the following business keyword descriptions: c3, C5;
the B3 enterprise invested in institution B has the following business keyword descriptions: c3, C5;
the B4 enterprise invested in institution B has the following business keyword descriptions: c1, C2, C3;
the B5 enterprise invested in institution B has the following business keyword descriptions: c4, C5, C6;
the B2 enterprise invested in institution c has the following business keyword descriptions: c1, C2, C3, C4;
the B4 enterprise invested in institution c has the following business keyword descriptions: c1, C2, C3;
the B6 enterprise invested in institution c has the following business keyword descriptions: c2, C5, C6;
by adopting a description mode similar to the characteristics of the organization, the times and the proportion of the business keyword description of the enterprise invested by the organization can be recorded:
| mechanism | Service key word | Number of occurrences | Ratio of occupation of |
| Mechanism first | C1 | 2 | 20％ |
| C2 | 1 | 10％ | |
| C3 | 3 | 30％ | |
| C4 | 2 | 20％ | |
| C5 | 2 | 20％ | |
| Mechanism B | C1 | 1 | 12.5％ |
| C2 | 1 | 12.5％ | |
| C3 | 2 | 25％ | |
| C4 | 1 | 12.5％ | |
| C5 | 2 | 25％ | |
| C6 | 1 | 12.5％ | |
| Mechanism C | C1 | 2 | 20％ |
| C2 | 3 | 30％ | |
| C3 | 2 | 20％ | |
| C4 | 1 | 10％ | |
| C5 | 1 | 10％ | |
| C6 | 1 | 10％ |
When a user matches an investment organization for an enterprise and a financing project thereof, the business description keywords of the user are obtained through the enterprise database and transmitted to the recommendation system, the recommendation algorithm calculates and matches the recommendation result through the business keywords of the user and the business keywords in the investment organization database, and the recommendation result is ranked from large to small according to the business keyword proportion and is displayed to the user after paging processing.
For example: the business keywords of the enterprise are described as C1, C3, C4 and C6, and recommendation results are obtained and ranked by finding the mechanism with the highest ratio of the keywords in the above table:
the ratio of C1+ C3+ C4+ C6 of the mechanism A is 20% + 30% + 20% + 0% + 70%;
the ratio of C1+ C3+ C4+ C6 of the mechanism B is 12.5% + 25% + 12.5% + 62.5%;
the ratio of C1+ C3+ C4+ C6 of the mechanism C is 20% + 20% + 10% + 60%.
Agency a (70%), agency b (62.5%), agency c (60%) will therefore be recommended in sequence.
And finally, in order to further ensure the accuracy of the recommendation result, combining the recommendation results, and performing final weighting to obtain the recommendation result: for example, the weight of feature-based matching is set to 60%, the weight of collaborative matching recommendation is set to 20%, and the weight of recommendation based on association is set to 20%, then the final recommendation result can be obtained by calculation of the weights. For example:
the matching degree obtained based on the recommendation of the characteristics is as follows: mechanism B (75%), mechanism A (30%), mechanism C (25%);
the matching degree based on the collaborative recommendation of the investment institution is as follows: mechanism A (60%), mechanism B (40%), mechanism C (20%);
the matching degree based on the correlation recommendation of the speculative mechanism is as follows: mechanism B (70%), mechanism A (62.5%), mechanism C (60%);
the weighted matching values are respectively:
a first mechanism: 60% + 30% + 20% + 60% + 20% + 62.5% ═ 42.5%;
a mechanism B: 60% + 75% + 20% + 40% + 20% + 70% ═ 67%;
a third mechanism: 60% + 25% + 20% + 60% + 31%;
the final recommended ordered results are therefore: organization b (67%), organization a (42.5%), organization c (31%). The recommendations of the investment institutions may be made in this order.
In some embodiments of the present invention, the combined weighted proportion value may be continuously adjusted during the algorithm tuning process to obtain a recommendation result that better meets the actual requirements; preprocessing is needed before each set of recommended original data is calculated, so that result deviation caused by limit values or insufficient samples is avoided; on the basis, the weight of a supplementary time dimension can be further considered for each characteristic value, relevance and service description, so that recent data can obtain higher weight than past data, and a recommendation result which is more consistent with the current situation can be obtained.
In this way, recommendation algorithms based on cooperation and relevance are introduced, and recommendation is performed based on mutual investment relevance among investment institutions and business cooperation among invested entrepreneurship enterprises respectively. Because the investment field is different from the application field of other recommendation algorithms, the recommendation results of other fields are generally applied to a single-body single scene, investment institutions invest in enterprises, and because different investment stages, or different investment rounds, investment institutions among different rounds and institutions invested together with the rounds have obvious relevance; and moreover, investment mechanisms generally focus on specific vertical industries for investment, in order to guarantee maximization of investment income, synergistic effects among the invested enterprises can be pursued as much as possible, the investment mechanisms are matched by adopting a recommendation algorithm based on relevance and cooperation, a combined recommendation scheme is adopted, results are combined and sequenced in a weighting mode, and the accuracy of recommendation results is guaranteed, so that the matching degree is more accurate, and convenience is brought to investment of both parties.
Referring to fig. 3 based on the same design concept, an embodiment of the present invention further provides an investment institution recommendation apparatus, including:
the characteristic recommendation module is used for respectively describing the characteristics of the investment institutions and the items to be invested based on preset labels and matching the corresponding investment institutions based on the characteristic description of the items to be invested;
adding feature weight values of the items to be invested based on different operation behaviors of the items to be invested by the investment institutions, and determining first recommended investment institution results sorted according to weight ratios based on the feature weight values;
the collaborative recommendation module is used for acquiring historical investment institutions associated with the items to be invested and determining results of second recommended investment institutions based on the ranking of the association degrees among the historical investment institutions;
the correlated recommending module is used for acquiring the description keywords of the items to be invested and determining a third investment institution recommending result based on the keyword proportion of the description keywords in the investment services of the investment institutions; and
and the comprehensive recommendation module is used for comprehensively sequencing the investment institutions respectively contained based on the weight occupied by the first recommended investment institution result, the second recommended investment institution result and the third recommended investment institution result to obtain a final recommended investment institution result.
The specific implementation manner of the investment institution recommendation device can refer to the specific implementation manner of the investment institution recommendation method, and the invention is not repeated herein.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present invention may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
What has been described above includes examples of one or more embodiments. It is, of course, not possible to describe every conceivable combination of components or methodologies for purposes of describing the aforementioned embodiments, but one of ordinary skill in the art may recognize that many further combinations and permutations of various embodiments are possible. Accordingly, the embodiments described herein are intended to embrace all such alterations, modifications and variations that fall within the scope of the appended claims. Furthermore, to the extent that the term "includes" is used in either the detailed description or the claims, such term is intended to be inclusive in a manner similar to the term "comprising" as "comprising" is interpreted when employed as a transitional word in a claim. Furthermore, any use of the term "or" in the specification of the claims is intended to mean a "non-exclusive or".
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (10)
1. An investment institution recommendation method, comprising:
respectively describing the characteristics of the investment institutions and the items to be invested based on preset labels, and matching the corresponding investment institutions based on the characteristic description of the items to be invested;
adding feature weight values of the items to be invested based on different operation behaviors of the items to be invested by the investment institutions, and determining first recommended investment institution results sorted according to weight ratios based on the feature weight values;
acquiring historical investment institutions associated with the items to be invested, and determining a second recommended investment institution result based on the sequence of the association degree among the historical investment institutions;
acquiring description keywords of the item to be invested, and determining a third investment institution recommending result based on the keyword proportion of the description keywords in the investment business of the investment institution;
and comprehensively ranking the investment institutions contained in the investment institutions respectively based on the weight of the first recommended investment institution result, the second recommended investment institution result and the third recommended investment institution result to obtain a final recommended investment institution result.
2. The investment institution recommendation method according to claim 1, wherein the preset tag comprises at least: industry field, regional preference, round stage, billable amount, currency, institution category, major investment style, post-investment cooperation opportunities, and decision cycle.
3. The investment institution recommendation method according to claim 2, wherein the preset tag further comprises: the grade of the industry field, the specific province and city of the region preference, the stage and turn of the turn stage and the specific amount of the billable amount.
4. The investment institution recommendation method according to claim 1, wherein said different investment institution-based operational behavior on the item to be invested comprises:
viewing the item to be invested, viewing the corresponding business plan book and leaving the investment intention.
5. The investment institution recommendation method according to claim 2, wherein the describing the characteristics of the investment institution and the item to be invested respectively based on the preset label comprises:
and collecting information submitted by the investment institutions participating in the cooperation through the forms to extract corresponding characteristics.
6. The investment institution recommendation method according to claim 2, wherein the describing the characteristics of the investment institution and the item to be invested respectively based on the preset label further comprises:
the features of the investment institutions active in the market are obtained by disclosing network data.
7. The investment institution recommendation method according to claim 2, wherein the describing the characteristics of the investment institution and the item to be invested respectively based on the preset label further comprises:
and acquiring characteristics contained in the behavior data of the investment institution on the platform by constructing a project docking platform.
8. The investment institution recommendation method according to claim 7, wherein the docking platform is a wechat applet, and the wechat applet is connected with information of the investment institution and the item to be invested.
9. The investment institution recommendation method according to claim 8, wherein the describing the characteristics of the investment institution and the item to be invested respectively based on the preset label further comprises:
and comprehensively tracking the viewing, screening, searching and following of the speculative mechanism based on the WeChat small program, and increasing a characteristic weight value corresponding to the item to be invested based on different operation behaviors of the investment mechanism.
10. An investment institution recommendation apparatus, comprising:
the characteristic recommendation module is used for respectively describing the characteristics of the investment institutions and the items to be invested based on preset labels and matching the corresponding investment institutions based on the characteristic description of the items to be invested;
adding feature weight values of the items to be invested based on different operation behaviors of the items to be invested by the investment institutions, and determining first recommended investment institution results sorted according to weight ratios based on the feature weight values;
the collaborative recommendation module is used for acquiring historical investment institutions associated with the items to be invested and determining results of second recommended investment institutions based on the sequence of the association degrees among the historical investment institutions;
the associated recommendation module is used for acquiring the description keywords of the item to be invested and determining a third investment institution recommendation result based on the keyword proportion of the description keywords in the investment business of the investment institution; and
and the comprehensive recommendation module is used for comprehensively sequencing the investment institutions respectively contained based on the weight of the first recommended investment institution result, the second recommended investment institution result and the third recommended investment institution result to obtain a final recommended investment institution result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011467198.6A CN112488842A (en) | 2020-12-14 | 2020-12-14 | Investment institution recommendation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011467198.6A CN112488842A (en) | 2020-12-14 | 2020-12-14 | Investment institution recommendation method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112488842A true CN112488842A (en) | 2021-03-12 |
Family
ID=74916858
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011467198.6A Pending CN112488842A (en) | 2020-12-14 | 2020-12-14 | Investment institution recommendation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112488842A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140012780A1 (en) * | 2012-06-29 | 2014-01-09 | BlazeFund, Inc. | Systems and Methods for Equity Crowd Funding |
| CN103714084A (en) * | 2012-10-08 | 2014-04-09 | 腾讯科技（深圳）有限公司 | Method and device for recommending information |
| CN106445971A (en) * | 2015-08-11 | 2017-02-22 | 北京奇虎科技有限公司 | Application recommendation method and system |
| CN108255957A (en) * | 2017-12-21 | 2018-07-06 | 杭州传送门网络科技有限公司 | One kind recommends matching process based on Venture Capital field precision dataization |
| CN109918626A (en) * | 2017-12-13 | 2019-06-21 | 厦门头家信息科技有限公司 | A kind of foundation investment and financing service system |
| CN110264364A (en) * | 2019-04-30 | 2019-09-20 | 电子科技大学 | A kind of recommended method of investor |
| CN110930259A (en) * | 2019-11-15 | 2020-03-27 | 安徽海汇金融投资集团有限公司 | Creditor right recommendation method and system based on mixed strategy |
| CN111738822A (en) * | 2020-06-16 | 2020-10-02 | 中国银行股份有限公司 | Auditor recommendation method and device |
-
2020
- 2020-12-14 CN CN202011467198.6A patent/CN112488842A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140012780A1 (en) * | 2012-06-29 | 2014-01-09 | BlazeFund, Inc. | Systems and Methods for Equity Crowd Funding |
| CN103714084A (en) * | 2012-10-08 | 2014-04-09 | 腾讯科技（深圳）有限公司 | Method and device for recommending information |
| CN106445971A (en) * | 2015-08-11 | 2017-02-22 | 北京奇虎科技有限公司 | Application recommendation method and system |
| CN109918626A (en) * | 2017-12-13 | 2019-06-21 | 厦门头家信息科技有限公司 | A kind of foundation investment and financing service system |
| CN108255957A (en) * | 2017-12-21 | 2018-07-06 | 杭州传送门网络科技有限公司 | One kind recommends matching process based on Venture Capital field precision dataization |
| CN110264364A (en) * | 2019-04-30 | 2019-09-20 | 电子科技大学 | A kind of recommended method of investor |
| CN110930259A (en) * | 2019-11-15 | 2020-03-27 | 安徽海汇金融投资集团有限公司 | Creditor right recommendation method and system based on mixed strategy |
| CN111738822A (en) * | 2020-06-16 | 2020-10-02 | 中国银行股份有限公司 | Auditor recommendation method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Sarwar et al. | Analysis of recommendation algorithms for e-commerce | |
| US8930247B1 (en) | System and methods for content-based financial decision making support | |
| CN103927615B (en) | Entity is associated with classification | |
| CN117196312A (en) | Method and system for adjusting trust score of second entity for requesting entity | |
| US20070150398A1 (en) | Investor sentiment barometer | |
| WO2011085497A1 (en) | Systems and methods for conducting more reliable financial transactions, credit decisions, and security assessments | |
| WO2014153222A1 (en) | Computerized system and mehtod for determining an action's importance and impact on a transaction | |
| Lauw et al. | Quality and leniency in online collaborative rating systems | |
| US20230116362A1 (en) | Scoring trustworthiness, competence, and/or compatibility of any entity for activities including recruiting or hiring decisions, composing a team, insurance underwriting, credit decisions, or shortening or improving sales cycles | |
| CN112232950A (en) | Loan risk assessment method and device, equipment and computer-readable storage medium | |
| US20070150397A1 (en) | Search engine for stock investment strategies | |
| US20070150396A1 (en) | Stock value chains | |
| US20090083169A1 (en) | Financial opportunity information obtainment and evaluation | |
| US20220164374A1 (en) | Method of scoring and valuing data for exchange | |
| US20220058658A1 (en) | Method of scoring and valuing data for exchange | |
| CN112488842A (en) | Investment institution recommendation method and device | |
| Perlich et al. | High-quantile modeling for customer wallet estimation and other applications | |
| Bett | Effect of business intelligence techniques on organizational performance: a survey of selected commercial banks in south rift counties in Kenya | |
| Pincovsky et al. | Machine Learning applied to credit analysis: a Systematic Literature Review | |
| Vhalery et al. | The Analysis of Factors Influencing Financial Technology Usage in Higher Education | |
| Fulga | Integrated bi-criteria decision support system for portfolio selection | |
| Vasiljeva et al. | The implications of customer behaviour for banking service management: evidence from Latvia | |
| Şenyürek et al. | Effects of binary similarity measures on top-n recommendations | |
| Andreevna | The Investment Analysis of IT Companies: A Case Study of Yandex | |
| EP4138021A1 (en) | Method of scoring and valuing data for exchange |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210312 |