CN107577797B - Fund element information classification method and device - Google Patents
Fund element information classification method and device Download PDFInfo
- Publication number
- CN107577797B CN107577797B CN201710852446.0A CN201710852446A CN107577797B CN 107577797 B CN107577797 B CN 107577797B CN 201710852446 A CN201710852446 A CN 201710852446A CN 107577797 B CN107577797 B CN 107577797B
- Authority
- CN
- China
- Prior art keywords
- element information
- matching
- category
- investment strategy
- classifying
- 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
Images
Abstract
The embodiment of the application discloses a fund element information classification method and device, the method comprises the steps of obtaining the element information of a fund, extracting the feature words of the element information, matching the feature words of the element information with the keywords respectively corresponding to each investment strategy category to obtain a matching result, and classifying the element information into the matched investment strategy category if the matching result is successful. The method avoids the problem of low efficiency and accuracy caused by manually classifying the element information of the fund by a fund manager or an investment advisor, and realizes the classification of the element information of the fund quickly and accurately.
Description
Technical Field
The application relates to the field of computers, in particular to a fund element information classification method and device.
Background
Fund is an abbreviation for securities investment Fund. Funds may be classified into stock funds, bond funds, money market funds, futures funds, etc. depending on the investment target.
The element information refers to the necessary textual description of the fund manager to issue the fund itself, including but not limited to the fund name, investment direction, investment strategy, etc. The investment strategy refers to a rule system and an action plan scheme used by a fund manager or an investment advisor of the fund when investing in the fund assets. Investment strategies, although complex, can be categorized into several categories by their nature. For example, a hedge fund investment strategy classification system (HFR system for short) is published internationally, and the system comprises 9 main investment strategy categories, such as stock hedge strategy, event-driven strategy, macro strategy, compound strategy and the like. By categorizing the fund element information into these categories, it is possible to facilitate the processing or research of these funds in units of categories.
In the prior art, a fund manager or an investment advisor classifies element information of a fund in a manual mode, so that the efficiency is low, and the classification accuracy is low depending on the classification experience of the fund manager or the investment advisor. Therefore, how to rapidly and accurately classify the element information of the fund is a problem to be solved at present.
Disclosure of Invention
In order to solve the problems in the prior art, embodiments of the present application provide a method and an apparatus for classifying fund element information, so as to quickly and accurately classify the fund element information.
In one aspect, an embodiment of the present application provides a fund element information classification method, including:
acquiring element information of a fund, and extracting characteristic words of the element information, wherein the element information of the fund is a text description for classifying the fund by an investment strategy;
matching the feature words of the element information with the keywords respectively corresponding to each investment strategy category to obtain a matching result;
and if the matching result is successful, classifying the element information into the matched investment strategy category.
Optionally, the element information includes a name of the fund;
the matching of the feature words of the element information and the keywords respectively corresponding to each investment strategy category to obtain a matching result comprises the following steps: and matching the feature words in the name of the fund with the keywords respectively corresponding to each investment strategy category according to a first preset rule to obtain a first matching result.
Optionally, the investment strategy categories include a first preset investment strategy category;
the matching of the feature words of the element information and the keywords respectively corresponding to each investment strategy category to obtain a matching result comprises the following steps: according to a second preset rule, matching the feature words of the element information with the keywords respectively corresponding to the first preset investment strategy category to obtain a second matching result;
if the matching result is successful, classifying the element information into a matched investment strategy category comprises: and if the second matching result is successful matching and only successfully matching with one of the first preset investment strategy categories, classifying the element information into the matched first preset investment strategy category.
Optionally, the first preset investment strategy category comprises at least one of: a stock policy category, an event driven policy category, a managed futures policy category, a arbitrage policy category, a bond policy category, a portfolio policy category, and other policy categories.
Optionally, the investment strategy categories include a second preset investment strategy category;
the matching the feature words of the element information with the keywords respectively corresponding to each investment strategy category to obtain a matching result further comprises: and if the second matching result is successful in matching and is successfully matched with at least two first preset investment strategy categories, matching the element information with keywords respectively corresponding to the second preset investment strategy categories according to a third preset rule to obtain a third matching result.
If the matching result is successful, classifying the element information into a matched investment strategy category further comprises: and if the third matching result is successful matching, classifying the element information into the matched second preset investment strategy category.
Optionally, the second pre-set investment strategy category includes: bond policy category.
Optionally, the third preset rule includes: and if the feature words with the preset number in the element information are bonds, the third matching result is that the element information is successfully matched with the bond strategy category.
Optionally, the investment strategy categories include a third preset investment strategy category;
the matching of the feature words of the element information and the keywords respectively corresponding to each investment strategy category to obtain a matching result comprises the following steps: if the third matching result is unsuccessful, matching the feature words of the element information with the keywords respectively corresponding to the third preset investment strategy category according to a fourth preset rule to obtain a fourth matching result;
if the matching result is successful, classifying the element information into a matched investment strategy category comprises: and if the fourth matching result is successful matching, classifying the element information into the matched third preset investment strategy category.
Optionally, the third pre-set investment strategy category includes: a macro policy category; and the keywords corresponding to the macro strategy category comprise investment institution identifications.
Optionally, the investment strategy categories include a fourth preset investment strategy category;
the matching of the feature words of the element information and the keywords respectively corresponding to each investment strategy category to obtain a matching result comprises the following steps: if the fourth matching result is unsuccessful, matching the feature words of the element information with the keywords respectively corresponding to the fourth preset investment strategy category according to a fifth preset rule to obtain a fifth matching result;
if the matching result is successful, classifying the element information into a matched investment strategy category comprises: and if the fifth matching result is successful matching, classifying the information element information into the matched fourth preset investment strategy category.
Optionally, the fourth pre-set investment strategy category includes: a composite policy category.
On the other hand, the embodiment of the present application further provides a device for classifying fund element information, including: the device comprises an element information acquisition unit, a matching unit and an element information classification unit.
The element information acquisition unit is configured to: acquiring element information of a fund, and extracting characteristic words of the element information, wherein the element information of the fund is a text description for classifying the fund by an investment strategy;
the matching unit is configured to: matching the feature words of the element information with the keywords respectively corresponding to each investment strategy category to obtain a matching result;
the element information classifying unit is configured to: and if the matching result is successful, classifying the element information into the matched investment strategy category.
Optionally, the matching unit includes: a first matching subunit to: and matching the feature words in the name of the fund with the keywords respectively corresponding to each investment strategy category according to a first preset rule to obtain a first matching result.
Optionally, the element information classifying unit includes: a first factor information classifying subunit configured to: and if the first matching result is successful matching, classifying the element information into a matched investment strategy category.
Optionally, the matching unit further includes: a second matching subunit to: according to a second preset rule, matching the feature words of the element information with the keywords respectively corresponding to the first preset investment strategy category to obtain a second matching result; the first pre-set investment strategy category includes at least one of: a stock policy category, an event driven policy category, a managed futures policy category, a arbitrage policy category, a bond policy category, a portfolio policy category, and other policy categories.
Optionally, the element information classifying unit further includes: a second element information classifying subunit configured to: and if the second matching result is successful matching and only successfully matching with one of the first preset investment strategy categories, classifying the element information into the matched first preset investment strategy category.
Optionally, the matching unit further includes: a third matching subunit to: if the second matching result is successful and matches with at least two first preset investment strategy categories, matching the element information with the second preset investment strategy category according to a third preset rule to obtain a third matching result; the second pre-established investment strategy category comprises: bond policy category.
Optionally, the element information classifying unit further includes: a third element information classifying subunit configured to: and if the third matching result is successful matching, classifying the element information into a second preset investment strategy category.
Optionally, the matching unit further includes: a fourth matching subunit to: if the third matching result is unsuccessful, matching the feature words of the element information with the keywords respectively corresponding to the third preset investment strategy category according to a fourth preset rule to obtain a fourth matching result; the third pre-established investment strategy category comprises: a macro policy category; and the keywords corresponding to the macro strategy category comprise investment institution identifications.
Optionally, the element information classifying unit further includes: a fourth element information classifying subunit configured to: and if the fourth matching result is successful matching, classifying the element information into the matched third preset investment strategy category.
Optionally, the matching unit further includes: a fifth matching subunit to: if the fourth matching result is unsuccessful, matching the feature words of the element information with the keywords respectively corresponding to the fourth preset investment strategy category according to a fifth preset rule to obtain a fifth matching result; the fourth pre-established investment strategy category comprises: a composite policy category.
Optionally, the element information classifying unit further includes: a fifth element information classifying subunit configured to: and if the fifth matching result is successful matching, classifying the element information into the matched fourth preset investment strategy category.
In the method for classifying the fund element information, the element information of the fund is acquired, the feature words of the element information are extracted, the feature words of the element information are matched with the keywords respectively corresponding to each investment strategy category to obtain a matching result, and if the matching result is successful, the element information is classified into the matched investment strategy category. The method avoids the problem of low efficiency and accuracy caused by manually classifying the element information of the fund by a fund manager or an investment advisor, and realizes the classification of the element information of the fund quickly and accurately.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be 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 described in the present application, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flowchart of a fund element information classification method according to an embodiment of the present application;
FIG. 2 is a flowchart of another fund element information classification method provided in the embodiments of the present application;
fig. 3 is a block diagram illustrating a structure of a fund element information classifying device according to an embodiment of the present application;
fig. 4 is a block diagram of a fund element information classifying device according to an embodiment of the present application.
Detailed Description
In order to make the technical solutions of the present application better understood, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Referring to fig. 1, the figure is a flowchart of a fund element information classification method provided in an embodiment of the present application.
The fund element information classification method provided by the embodiment comprises the following steps:
s101: acquiring element information of the fund, and extracting characteristic words of the element information, wherein the element information of the fund is a text description used for classifying the fund by an investment strategy.
The fund is short for a security investment fund, and in the embodiment of the application, the fund can be a private fund or other fund types. The element information of the fund is necessary text description of the fund manager to the fund self-issuing, and can comprise fund names, investment directions, investment strategies, investment institutions and the like.
In this embodiment of the present application, the element information may be embodied in the form of an element specification, and a format of the element specification may be word or text, and the embodiment is not particularly limited. The feature words for extracting the element information may be extracted from the element specification, and for example, words in the element specification may be segmented, and a noun or a noun phrase may be extracted as the feature words of the element information by determining a part of speech.
The investment strategy refers to a rule system and an action plan scheme used by a fund manager or an investment advisor of the fund when investing in the fund assets. In practice, the investment results generated by different investment strategies have great difference, the evaluation methods of the investment results are different, and the investment strategies are complex, so that the investment results can be classified into a plurality of categories according to the essence of the investment results, and the funds can be conveniently processed or researched by taking the categories as units. Meanwhile, the investment strategy classification of the fund is an important basis for making fund investment decision, performance evaluation and even related businesses of many fund industries.
All possible fund investment strategy classification results and classification theories thereof are referred to as an investment strategy classification system according to a joint name, for example, an investment strategy classification system (HFR system for short) of hedge funds is internationally published, and the system comprises 9 main investment strategy categories, such as a stock strategy category, an event-driven strategy category, a management futures strategy category, a bond strategy category, a combined fund strategy category, a composite strategy category, a macro strategy category, a arbitrage strategy category and other strategy categories.
S102: and matching the feature words of the element information with the keywords respectively corresponding to each investment strategy category to obtain a matching result.
The keywords respectively corresponding to each investment strategy category may be preset, and the keywords may include a first keyword and a second keyword. The first keyword is a preset keyword capable of reflecting the investment strategy category, and the keyword is generally a proper noun and is often present in the element information. The second keyword may be a word associated with the first keyword, for example, may be a similar word corresponding to the first keyword, such a keyword is generally not frequently present in the element information, and mainly takes into consideration the situation that the word used by the composer of the element information is not standard and is not accurate.
For example, a first keyword of a stock strategy category may be "secondary market", "equity type products", etc., a first keyword for managing a futures strategy category may be "stock refers futures", "financial futures", etc., a first keyword of other strategy categories may be "stock rights company", "limited company", etc., and for example, "benefit type products" may be a synonym for "equity type products", may be a second keyword for a stock strategy category, and "economic futures" may be a synonym for "equity type products", and may be a second keyword for managing a futures strategy category.
During matching, the feature words of the element information can be matched with the first keywords of each investment strategy category, and when the feature words are unsuccessfully matched with the first keywords, the feature words of the element information are matched with the second keywords.
The matching of the feature words of the element information with the keywords respectively corresponding to each investment strategy category may be comparing the feature words of the element information with the keywords respectively corresponding to each investment strategy category. The matching result may be that one or more feature words of the fund element information are the same as one or some keywords corresponding to one of the investment strategy categories, the fund element information is successfully matched with the investment strategy category, otherwise, the matching is not successful.
S103: and if the matching result is successful, classifying the element information into the matched investment strategy category.
The specific implementation of step S103 may refer to the classification process in example two, for example, and is not described herein again.
In the fund element information classification method provided by the embodiment of the application, the element information of the fund is acquired, the feature words of the element information are extracted, the feature words of the element information are matched with the keywords respectively corresponding to each investment strategy category, and if the matching is successful, the element information is classified into the matched investment strategy category. The method avoids the problem of low efficiency and accuracy caused by manually classifying the element information of the fund by a fund manager or an investment advisor, and realizes the classification of the element information of the fund quickly and accurately.
Referring to fig. 2, the figure is a flowchart of another fund element information classification method provided in the embodiment of the present application.
The fund element information classification method provided by the embodiment comprises the following steps:
s201: acquiring element information of the fund, and extracting characteristic words of the element information, wherein the element information of the fund is a text description used for classifying the fund by an investment strategy.
The implementation process of step S201 is the same as step S101, and is not described herein again.
S202: and matching the feature words in the name of the fund with the first keywords corresponding to each investment strategy category respectively according to a first preset rule to obtain a first matching result, executing the step S203 if the first matching result is successful matching, and executing the step S204 if the first matching result is unsuccessful matching.
In this embodiment, the factor information includes a name of the fund.
The first preset rule may be a preset matching rule for matching the feature words in the fund name with the keywords corresponding to each investment strategy category, and under the rule, the feature words in the fund name can be successfully matched with the keywords corresponding to at most one investment strategy category in each investment strategy category.
For example, the preset matching rule of the arbitrage policy category is that the feature words contain "arbitrage" and do not contain the feature words of "FOF", "TOT", "TOF" and "MOM", and if the feature words in the name of the first fund satisfy the preset matching rule of the arbitrage policy category, the matching result of the matching with the arbitrage policy category is that the matching is successful. If the name of the first fund contains characteristic words such as FOF, TOT, TOF or MOM, namely the first keyword FOF, TOT, TOF and MOM in the combined fund policy category are matched, the matching result with the combined fund policy category is successful.
In other embodiments of the present application, step S202 may also be executed before step S212 and after other steps, and the execution time of step S202 does not affect the implementation of the embodiments of the present application.
S203: and classifying the element information into the matched investment strategy category, and executing the step S214.
S204: and matching the feature words of the element information with the first keywords respectively corresponding to the first preset investment strategy category according to a second preset rule to obtain a second matching result. If the second matching result is a successful match and a unique match, step S205 is executed, if the second matching result is a successful match and a non-unique match, step S206 is executed, and if the second matching result is an unsuccessful match, step S212 is executed.
The second preset rule is to compare whether the feature words of the element information are the same as the first keywords respectively corresponding to the first preset investment strategy categories. The unique matching means that the feature words of the element information are successfully matched with only the keyword corresponding to one investment strategy category in the first preset investment strategy category; the non-unique matching means that the feature words of the element information are successfully matched with the keywords corresponding to at least two investment strategy categories in the first preset investment strategy category.
The factor information may further include an investment direction, an investment strategy, and the like. The first pre-set investment strategy category comprises at least one of the following investment strategy categories: a stock policy category, an event driven policy category, a managed futures policy category, a arbitrage policy category, a bond policy category, a portfolio policy category, and other policy categories, among others.
For example, if one of the feature words of the element information of the second fund is "financial futures" and thus matches with the first keyword "secondary market" in the stock policy category, if none of the feature words in the element information of the second fund matches with the first keyword of the first preset investment policy category other than the stock policy category in the first preset investment policy category, the second matching result of the feature words of the element information of the second fund matching with each investment policy category is a successful and unique matching. If two of the feature words of the element information of the second fund are "financial futures" and "secondary market", match with the first keyword "secondary market" in the stock policy category, and match with the first keyword "financial futures" in the management futures policy category, the second matching result of the feature words of the element information of the second fund matching with each investment policy category is a non-unique match.
Based on the event-driven policy category being included in the stock policy category, the second preset rule may further include: and if the feature words of the elements are successfully matched with the first key words in the stock strategy category and the event-driven strategy category at the same time, the feature words of the elements are considered to be successfully matched with the event-driven strategy category.
S205: and classifying the element information into the matched first preset investment strategy category, and executing the step S214.
S206: and matching the element information with the first keywords respectively corresponding to the second preset investment strategy category according to a third preset rule to obtain a third matching result. If the third matching result is a successful matching, step S207 is executed, and if the third matching result is an unsuccessful matching, step S208 is executed.
The second predetermined investment strategy category may be a bond strategy category or the like. The second preset rule may be to determine whether a first preset number of feature words in the element information are the same as keywords corresponding to the second preset investment strategy category, respectively.
The sequence of the plurality of feature words in the element information may be determined by the occurrence sequence of the feature words appearing in the element description to which the feature words belong, or may be determined by the frequency of the feature words appearing in the element description to which the feature words belong. If the first characteristic word is "bond", it indicates that in the element specification, "bond" appears first or appears most frequently, and therefore, according to the second preset rule, the result of matching the element information with the bond policy category is that the matching is successful, and in other embodiments of the present application, the first preset number may be another number.
For example, the success of the feature words in the element information is preset to be determined by the appearance sequence of the feature words in the element specification to which the feature words belong, and a preset number of feature words are set as first feature words, the first feature word in the element information of the third fund is set as a bond, and the first feature word is the same as a first keyword "bond" in the bond policy category, so that the result of matching with the bond policy category is successful.
S207: and classifying the element information into a second preset investment strategy category, and executing the step S214.
S208: and matching the feature words of the element information with the first keywords respectively corresponding to the third preset investment strategy category according to a fourth preset rule to obtain a fourth matching result. If the fourth matching result is a successful matching, step S209 is performed, and if the fourth matching result is an unsuccessful matching, step S210 is performed.
The third pre-established investment strategy category comprises: macro policy category, etc., the factor information may include investment institutions, and the fourth preset rule may be to compare the investment institutions in the factor information with keywords of the third preset investment policy category.
Funds using the macro-strategy category are typically investment targets for at least two of stocks, bonds, bulk products, futures.
The first keyword corresponding to the macro policy category may be an investment institution identification. For example, the name or code number of the investment institution, if the feature words in the element information include the investment institution identification corresponding to the macro policy category, the matching result of the feature words of the element information and the macro policy category is successful.
S209: and classifying the element information into a third preset investment strategy category, and executing the step S214.
S210: and matching the feature words of the element information with the first keywords respectively corresponding to the fourth preset investment strategy category according to a fifth preset rule to obtain a fifth matching result. If the fifth matching result is a successful matching, step S211 is performed, and if the fifth matching result is an unsuccessful matching, step S214 is performed.
The fourth pre-established investment strategy category may comprise a composite investment strategy category or the like. Funds that adopt the composite policy category typically use a mix of at least two primary policies of stocks, event-driven, bonds, managed futures, arbitrage policies, or a mix of at least two of the above-mentioned primary policies. The first keyword of the composite investment strategy category can be a stock, an event driver, a bond, a management futures strategy, a arbitrage strategy and the like, and can also be a composite strategy or a multi-strategy and the like.
The fifth preset rule may be that matching between the feature words in the element information and the composite policy or the multiple policies is successful, or matching between the feature words and multiple first keywords such as stocks, event drivers, bonds, management futures, arbitrage policies, and the like is successful, and a fifth matching result is matching success.
S211: and classifying the element information into a fourth preset investment strategy category, and executing the step S214.
S212: and matching the characteristic words in the fund names with the second keywords respectively corresponding to the investment strategy categories to obtain a sixth matching result. If the fifth matching result is a successful matching, step S213 is executed, and if the fifth matching result is an unsuccessful matching, step S214 is executed.
The second keyword corresponding to each investment policy category may be preset, may be a word associated with the first keyword, and may be a similar word corresponding to the first keyword, for example. And the fifth matching result can be that the characteristic words of the fund names are the same as the second key words corresponding to one of the investment strategy categories, the matching is successful, otherwise, the matching is unsuccessful.
S213: and classifying the element information into a matched investment strategy category.
S214: and ending the flow.
The above steps are correspondingly set forth in the embodiments of the present application for easy understanding, and should not be limited as the steps of the fund element information classification method of the present application, and may be different in other embodiments of the present application.
In the method for classifying the fund element information, the fund element information is acquired, the feature words of the element information are extracted, the feature words of the element information are matched with the keywords respectively corresponding to each investment strategy category, if the matching is successful, the element information is classified into the matched investment strategy category, and a proper classifying method is designed according to the keywords and the characteristics of each investment strategy category, so that the fund element information can be accurately classified into the matched investment strategy category. The method avoids the problem of low efficiency and accuracy caused by manually classifying the element information of the fund by a fund manager or an investment advisor, and realizes the classification of the element information of the fund quickly and accurately.
Based on the fund element information classification method provided by the above embodiment, the embodiment of the application also provides a fund element information classification device, and the working principle of the fund element information classification device is explained in detail by combining the attached drawings.
Referring to fig. 3, this figure is a block diagram of a structure of a fund element information classifying device according to an embodiment of the present application.
The fund element information classifying device provided in the present embodiment includes an element information acquiring unit 1010, a matching unit 1020, and an element information classifying unit 1030, in which:
the element information acquiring unit 1011 is configured to acquire element information of a fund and extract a feature word of the element information, where the element information of the fund is a text description used for classifying the fund by an investment strategy.
And a matching unit 1020, configured to match the feature words of the element information with the keywords respectively corresponding to each investment strategy category, so as to obtain a matching result.
And the element information classifying unit 1030 is configured to classify the element information into a matched investment strategy category if the matching result is that matching is successful.
In the classification device for the fund element information provided by the embodiment of the application, the feature words of the element information are matched with the keywords respectively corresponding to each investment strategy category, and if the matching is successful, the element information is classified into the matched investment strategy category. The method avoids the problem of low efficiency and accuracy caused by manually classifying the element information of the fund by a fund manager or an investment advisor, and realizes the classification of the element information of the fund quickly and accurately.
Referring to fig. 4, this figure is a block diagram of a structure of a fund element information classifying device according to a fourth embodiment of the present application.
In the fund element information classifying device provided in this embodiment, the matching unit 1020 may include: a first matching sub-unit 1021, a second matching sub-unit 1022, a third matching sub-unit 1023, a fourth matching sub-unit 1024 and a fifth matching sub-unit 1025. The element information classifying unit 1030 may include: a first element information classifying sub-unit 1031, a second element information classifying sub-unit 1032, a third element information classifying sub-unit 1033, a fourth element information classifying sub-unit 1034, and a fifth element information classifying sub-unit 1035. Wherein:
and the first matching subunit 1021 is configured to match, according to a first preset rule, the feature words in the name of the fund with the keywords corresponding to the investment policy categories, respectively, to obtain a first matching result.
A first element information classifying subunit 1031, configured to classify the element information into a matched investment strategy category if the first matching result is a successful matching.
A second matching subunit 1022, configured to match, according to a second preset rule, the feature words of the element information with the keywords respectively corresponding to the first preset investment policy category, so as to obtain a second matching result; the first pre-set investment strategy category includes at least one of: a stock policy category, an event driven policy category, a managed futures policy category, a arbitrage policy category, a bond policy category, a portfolio policy category, and other policy categories, among others.
A second element information classifying subunit 1032 is configured to, if the second matching result is that matching is successful and matching with only one of the first predetermined investment strategy categories is successful, classify the element information into the matched first predetermined investment strategy category.
A third matching subunit 1023, configured to, if the second matching result is a successful matching and the second matching result is a successful matching with at least two first preset investment policy categories, match the element information with the second preset investment policy category according to a third preset rule to obtain a third matching result; the second pre-established investment strategy category comprises: bond policy categories, etc.
A third element information classifying subunit 1033, configured to classify the element information into a second preset investment strategy category if the third matching result is a successful matching.
A fourth matching subunit 1024, configured to, if the third matching result is that matching is unsuccessful, match the feature words of the element information with the keywords corresponding to the third preset investment policy category according to a fourth preset rule, so as to obtain a fourth matching result; the third pre-established investment strategy category comprises: macro policy categories, etc.
A fourth element information classifying subunit 1034, configured to, if the fourth matching result is that matching is successful, classify the element information into the matched third preset investment policy category.
A fifth matching subunit 1025 to: if the fourth matching result is unsuccessful, matching the feature words of the element information with the keywords respectively corresponding to the fourth preset investment strategy category according to a fifth preset rule to obtain a fifth matching result; the fourth pre-established investment strategy category comprises: composite policy categories, etc.
A fifth element information classifying subunit 1035, configured to: and if the fifth matching result is successful matching, classifying the element information into the matched fourth preset investment strategy category.
In the device for classifying fund element information, the element information is acquired, the feature words of the element information are extracted, the feature words of the element information are matched with the keywords respectively corresponding to each investment strategy category, and if the matching is successful, the element information is classified into the matched investment strategy category. The method avoids the problem of low efficiency and accuracy caused by manually classifying the element information of the fund by a fund manager or an investment advisor, and realizes the classification of the element information of the fund quickly and accurately.
When introducing elements of various embodiments of the present application, the articles "a," "an," "the," and "said" are intended to mean that there are one or more of the elements. The terms "comprising," "including," and "having" are intended to be inclusive and mean that there may be additional elements other than the listed elements.
It should be noted that, as one of ordinary skill in the art would understand, all or part of the processes of the above method embodiments may be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, and when executed, the computer program may include the processes of the above method embodiments. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the apparatus embodiment, since it is substantially similar to the method embodiment, it is relatively simple to describe, and reference may be made to some descriptions of the method embodiment for relevant points. The above-described apparatus embodiments are merely illustrative, and the units and modules described as separate components may or may not be physically separate. In addition, some or all of the units and modules may be selected according to actual needs to achieve the purpose of the solution of the embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
The foregoing is directed to embodiments of the present application and it is noted that numerous modifications and adaptations may be made by those skilled in the art without departing from the principles of the present application and are intended to be within the scope of the present application.
Claims (17)
1. A fund element information classification method is characterized by comprising the following steps:
acquiring element information of a fund, and extracting characteristic words of the element information, wherein the element information of the fund is a text description for classifying the fund by an investment strategy; wherein the element information further includes a name of the fund;
matching the feature words of the element information with the keywords respectively corresponding to each investment strategy category to obtain a matching result; matching the feature words in the name of the fund with the keywords respectively corresponding to each investment strategy category according to a first preset rule to obtain a first matching result;
if the matching result is successful, classifying the element information into a matched investment strategy category;
wherein each investment strategy category comprises a first preset investment strategy category;
the matching of the feature words of the element information and the keywords respectively corresponding to each investment strategy category to obtain a matching result comprises the following steps:
according to a second preset rule, matching the feature words of the element information with the keywords respectively corresponding to the first preset investment strategy category to obtain a second matching result;
if the matching result is successful, classifying the element information into a matched investment strategy category comprises:
and if the second matching result is successful matching and only successfully matching with one of the first preset investment strategy categories, classifying the element information into the matched first preset investment strategy category.
2. The method according to claim 1, wherein the first pre-set investment strategy category comprises at least one of:
a stock policy category, an event driven policy category, a managed futures policy category, a arbitrage policy category, a portfolio policy category, a bond policy category, and other policy categories.
3. The method according to claim 1 or 2, wherein said respective investment strategy categories comprise a second pre-set investment strategy category;
the matching the feature words of the element information with the keywords respectively corresponding to each investment strategy category to obtain a matching result further comprises:
if the second matching result is successful in matching and is successful in matching with at least two first preset investment strategy categories, matching the element information with keywords respectively corresponding to the second preset investment strategy categories according to a third preset rule to obtain a third matching result;
if the matching result is successful, classifying the element information into a matched investment strategy category further comprises:
and if the third matching result is successful matching, classifying the element information into the matched second preset investment strategy category.
4. The method according to claim 3, wherein the second pre-established investment strategy category comprises: bond policy category.
5. The method according to claim 4, wherein the third preset rule comprises:
and if the feature words with the preset number in the element information are bonds, the third matching result is that the element information is successfully matched with the bond strategy category.
6. The method according to claim 5, wherein said respective investment strategy categories include a third pre-established investment strategy category;
the matching of the feature words of the element information and the keywords respectively corresponding to each investment strategy category to obtain a matching result comprises the following steps:
if the third matching result is unsuccessful, matching the feature words of the element information with the keywords respectively corresponding to the third preset investment strategy category according to a fourth preset rule to obtain a fourth matching result;
if the matching result is successful, classifying the element information into a matched investment strategy category comprises:
and if the fourth matching result is successful matching, classifying the element information into the matched third preset investment strategy category.
7. The method according to claim 6, wherein the third pre-established investment strategy category comprises: a macro policy category;
and the keywords corresponding to the macro strategy category comprise investment institution identifications.
8. The method according to claim 7, wherein said respective investment strategy categories include a fourth pre-established investment strategy category;
the matching of the feature words of the element information and the keywords respectively corresponding to each investment strategy category to obtain a matching result comprises the following steps:
if the fourth matching result is unsuccessful, matching the feature words of the element information with the keywords respectively corresponding to the fourth preset investment strategy category according to a fifth preset rule to obtain a fifth matching result;
if the matching result is successful, classifying the element information into a matched investment strategy category comprises:
and if the fifth matching result is successful matching, classifying the element information into the matched fourth preset investment strategy category.
9. The method according to claim 8, wherein the fourth pre-established investment strategy category comprises: a composite policy category.
10. A fund element information classification device is characterized by comprising an element information acquisition unit, a matching unit and an element information classification unit, wherein:
the element information acquisition unit is configured to: acquiring element information of a fund, and extracting characteristic words of the element information, wherein the element information of the fund is a text description for classifying the fund by an investment strategy;
the matching unit is configured to: matching the feature words of the element information with the keywords respectively corresponding to each investment strategy category to obtain a matching result;
wherein the matching unit comprises a first matching subunit configured to: matching the feature words in the name of the fund with the keywords respectively corresponding to each investment strategy category according to a first preset rule to obtain a first matching result;
the element information classifying unit is configured to: if the matching result is successful, classifying the element information into a matched investment strategy category;
wherein the element information classifying unit includes:
a first factor information classifying subunit configured to: if the first matching result is successful, classifying the element information into a matched investment strategy category;
the matching unit further includes:
a second matching subunit to: according to a second preset rule, matching the feature words of the element information with the keywords respectively corresponding to the first preset investment strategy category to obtain a second matching result; the first pre-set investment strategy category includes at least one of: a stock policy category, an event driven policy category, a managed futures policy category, a arbitrage policy category, a bond policy category, a portfolio policy category, and other policy categories.
11. The apparatus according to claim 10, wherein the element information classifying unit further comprises:
a second element information classifying subunit configured to: and if the second matching result is successful matching and only successfully matching with one of the first preset investment strategy categories, classifying the element information into the matched first preset investment strategy category.
12. The apparatus of claim 10, wherein the matching unit further comprises:
a third matching subunit to: if the second matching result is successful and matches with at least two first preset investment strategy categories, matching the element information with the second preset investment strategy category according to a third preset rule to obtain a third matching result; the second pre-established investment strategy category comprises: bond policy category.
13. The apparatus according to claim 12, wherein the element information classifying unit further comprises:
a third element information classifying subunit configured to: and if the third matching result is successful matching, classifying the element information into a second preset investment strategy category.
14. The apparatus of claim 12, wherein the matching unit further comprises:
a fourth matching subunit to: if the third matching result is unsuccessful, matching the feature words of the element information with the keywords respectively corresponding to the third preset investment strategy category according to a fourth preset rule to obtain a fourth matching result; the third pre-established investment strategy category comprises: a macro policy category; and the keywords corresponding to the macro strategy category comprise investment institution identifications.
15. The apparatus according to claim 14, wherein the element information classifying unit further comprises:
a fourth element information classifying subunit configured to: and if the fourth matching result is successful matching, classifying the element information into the matched third preset investment strategy category.
16. The apparatus of claim 14, wherein the matching unit further comprises:
a fifth matching subunit to: if the fourth matching result is unsuccessful, matching the feature words of the element information with the keywords respectively corresponding to the fourth preset investment strategy category according to a fifth preset rule to obtain a fifth matching result; the fourth pre-established investment strategy category comprises: a composite policy category.
17. The apparatus according to claim 16, wherein the element information classifying unit further comprises:
a fifth element information classifying subunit configured to: and if the fifth matching result is successful matching, classifying the element information into the matched fourth preset investment strategy category.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710852446.0A CN107577797B (en) | 2017-09-19 | 2017-09-19 | Fund element information classification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710852446.0A CN107577797B (en) | 2017-09-19 | 2017-09-19 | Fund element information classification method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107577797A CN107577797A (en) | 2018-01-12 |
| CN107577797B true CN107577797B (en) | 2020-12-08 |
Family
ID=61036383
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710852446.0A Active CN107577797B (en) | 2017-09-19 | 2017-09-19 | Fund element information classification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107577797B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1388451A (en) * | 2001-05-28 | 2003-01-01 | 精业股份有限公司 | Financial data base expanding system and method |
| CN103226554A (en) * | 2012-12-14 | 2013-07-31 | 西藏同信证券有限责任公司 | Automatic stock matching and classifying method and system based on news data |
| CN105069336A (en) * | 2015-09-14 | 2015-11-18 | 中山易云云计算有限公司 | Distributed security management method based on big data weight dynamic intelligent analysis |
| CN106251226A (en) * | 2016-08-16 | 2016-12-21 | 深圳市众投邦股份有限公司 | Fund management method and device |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7177859B2 (en) * | 2002-06-26 | 2007-02-13 | Microsoft Corporation | Programming model for subscription services |
| US8412609B2 (en) * | 2010-09-24 | 2013-04-02 | Quantitative Management Associates Llc | Regime-based asset allocation via adaptive risk premium |
| CN102693511A (en) * | 2012-06-11 | 2012-09-26 | 深圳市中金阿尔法投资研究有限公司 | Hedge fund index and rating systems based on strategy classification |
| US20140279696A1 (en) * | 2013-03-15 | 2014-09-18 | Atlas Portfolio, LLC | Asset data management system and method |
| US10210351B2 (en) * | 2014-07-21 | 2019-02-19 | Servicenow, Inc. | Fingerprint-based configuration typing and classification |
| CN105069141A (en) * | 2015-08-19 | 2015-11-18 | 北京工商大学 | Construction method and construction system for stock standard news library |
| CN105989184A (en) * | 2015-08-25 | 2016-10-05 | 中国银联股份有限公司 | Classification method and apparatus |
-
2017
- 2017-09-19 CN CN201710852446.0A patent/CN107577797B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1388451A (en) * | 2001-05-28 | 2003-01-01 | 精业股份有限公司 | Financial data base expanding system and method |
| CN103226554A (en) * | 2012-12-14 | 2013-07-31 | 西藏同信证券有限责任公司 | Automatic stock matching and classifying method and system based on news data |
| CN105069336A (en) * | 2015-09-14 | 2015-11-18 | 中山易云云计算有限公司 | Distributed security management method based on big data weight dynamic intelligent analysis |
| CN106251226A (en) * | 2016-08-16 | 2016-12-21 | 深圳市众投邦股份有限公司 | Fund management method and device |
Non-Patent Citations (1)
| Title |
|---|
| 改进贝叶斯分类的智能短信分类方法;杨柳等;《计算机科学》;20141015;第31-35页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107577797A (en) | 2018-01-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110163478B (en) | Risk examination method and device for contract clauses | |
| US8725494B2 (en) | Signal processing approach to sentiment analysis for entities in documents | |
| US10579651B1 (en) | Method, system, and program for evaluating intellectual property right | |
| US11769008B2 (en) | Predictive analysis systems and methods using machine learning | |
| US11062413B1 (en) | Automated secondary linking for fraud detection systems | |
| CN110083623B (en) | Business rule generation method and device | |
| CN110162780B (en) | User intention recognition method and device | |
| CN107807962B (en) | A method of similarity mode being carried out to legal decision document using LDA topic model | |
| CN114265967B (en) | Sensitive data security level marking method and device | |
| CN106203808A (en) | Enterprise Credit Risk Evaluation method and apparatus | |
| Valero et al. | Future banking scenarios. Evolution of digitalisation in Spanish banking | |
| CN108885631B (en) | Method and system for contract management in a data marketplace | |
| Gupta et al. | Data mining-based financial statement fraud detection: Systematic literature review and meta-analysis to estimate data sample mapping of fraudulent companies against non-fraudulent companies | |
| CN112750029A (en) | Credit risk prediction method, device, electronic equipment and storage medium | |
| CN113159922A (en) | Data flow direction identification method, device, equipment and medium | |
| Bohoslavsky et al. | Sovereign debt crises: what have we learned? | |
| Vuong et al. | Relationship between innovations, capital expenditures and post-M&A performance: evidence from Vietnam, 2005-2012 | |
| Haryono et al. | Aspect-based sentiment analysis of financial headlines and microblogs using semantic similarity and bidirectional long short-term memory | |
| CN107577797B (en) | Fund element information classification method and device | |
| CN107172311B (en) | Service evaluation method and terminal equipment | |
| CN114049215A (en) | Abnormal transaction identification method, device and application | |
| Cheng | Interpretation of Material Adverse Change Clauses in an Adverse Economy | |
| CN112488557A (en) | Automatic calculation method, device and terminal based on grading standard objective scores | |
| Ghous et al. | Exchange stock price prediction using time series data: A survey | |
| Lehmann et al. | Economic recovery after COVID-19 requires a clear vision for a healthy banking sector |
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 |