CN113159972A - Combination determination method, combination determination device, electronic equipment and computer readable storage medium - Google Patents
Combination determination method, combination determination device, electronic equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN113159972A CN113159972A CN202110552237.0A CN202110552237A CN113159972A CN 113159972 A CN113159972 A CN 113159972A CN 202110552237 A CN202110552237 A CN 202110552237A CN 113159972 A CN113159972 A CN 113159972A
- Authority
- CN
- China
- Prior art keywords
- target product
- product
- target
- factor
- characteristic
- 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
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
Abstract
The application provides a combination determination method, a combination determination device, electronic equipment and a computer readable storage medium; the method comprises the following steps: the method comprises the steps that a main node device receives a product combination request, determines a target product and characteristic factors based on user preference, and sends information and characteristic factors of the target product to a plurality of slave node devices, so that the slave node devices determine the correlation degree between the corresponding characteristic factors and each target product, wherein each slave node device corresponds to one characteristic factor; receiving a plurality of relevancy returned by the slave node equipment; determining the initial weight of each target product based on the correlation degree between each characteristic factor and each target product and the weight corresponding to each characteristic factor; and sequencing the target products based on the initial weight of each target product, and responding to the product combination request based on the product combination formed by the sequenced target products. By the method and the device, the accuracy of investment can be improved.
Description
Technical Field
The present disclosure relates to internet technologies, and in particular, to a combination determination method and apparatus, an electronic device, and a computer-readable storage medium.
Background
With the ever-increasing investment targets in the market, people tend to choose a plurality of different types of constituent investment portfolios of investment targets to invest. In the related art, the investment portfolio can be selected only depending on manual experience and professional knowledge, which is too high for common investors, and meanwhile, a large amount of manpower cost needs to be invested, the investment accuracy is not high, and a large investment risk is possibly brought.
Disclosure of Invention
The embodiment of the application provides a combination determination method, a combination determination device, electronic equipment and a computer-readable storage medium, which can improve the accuracy of investment.
The technical scheme of the embodiment of the application is realized as follows:
the embodiment of the application provides a combination determination method, which comprises the following steps:
the method comprises the steps that a main node device receives a product combination request, determines a target product and characteristic factors based on user preference, and sends information of the target product and the characteristic factors to a plurality of slave node devices, so that the slave node devices determine the correlation degree between the corresponding characteristic factors and each target product, wherein each slave node device corresponds to one characteristic factor;
receiving the relevance returned by the plurality of slave node devices;
determining a starting weight of each target product based on the correlation degree between each characteristic factor and each target product and the weight corresponding to each characteristic factor;
and sequencing a plurality of target products based on the initial weight of each target product, and responding to the product combination request based on the product combination formed by the sequenced target products.
An embodiment of the present application provides a combination determination device, including:
the determining module is used for receiving a product combination request, determining a target product and characteristic factors based on user preferences, and sending information of the target product and the characteristic factors to a plurality of slave node devices so that the slave node devices determine the correlation degree between the corresponding characteristic factors and each target product, wherein each slave node device corresponds to one characteristic factor; and determining a starting weight of each target product based on the correlation degree between each characteristic factor and each target product and the weight corresponding to each characteristic factor;
a receiving module, configured to receive the relevancy returned by the plurality of slave node devices;
and the sequencing module is used for sequencing the target products based on the initial weight of each target product and responding to the product combination request based on the product combination formed by the sequenced target products.
In the foregoing solution, the determining module is further configured to:
determining a preference of a user based on a purchase record of the user or a user preference survey result;
determining at least one target product matching the user's preferences and at least one feature factor matching the user's preferences by querying a mapping table.
In the foregoing solution, when the characteristic factor is used to evaluate the market profitability of the target product, the determining module is further configured to:
sending the information of the target product and the characteristic factor to slave node equipment corresponding to the characteristic factor so as to enable the slave node equipment to work
And the slave node equipment corresponding to the characteristic factors is divided based on the distribution of the characteristic factors to obtain a plurality of characteristic factor intervals, the interval probability corresponding to the characteristic factor interval to which the characteristic factor of each target product belongs is determined, and the interval probability is used as the correlation degree between the corresponding target product and the characteristic factors.
In the above scheme, when the feature factor is used to evaluate the public opinion risk of the target product, the determining module is further configured to:
sending the information of the target product and the characteristic factors to slave node equipment corresponding to the characteristic factors so that the slave node equipment acquires media content and identifies the media content to obtain target media content related to the target product;
determining the number of preset keywords included in the target media content;
and adjusting the public opinion reference value based on the number of the preset keywords to obtain the correlation degree between the target product and the characteristic factor.
In the foregoing solution, the determining module is further configured to:
acquiring historical performance data of the target product;
determining a candidate public opinion benchmark value based on the historical performance data;
and performing a back test on the candidate public opinion reference value, and when the candidate public opinion reference value passes the test, taking the candidate public opinion reference value as the public opinion reference value.
In the foregoing solution, the determining module is further configured to:
and carrying out weighted summation on the correlation degree between each target product and each characteristic factor based on the weight corresponding to each characteristic factor to obtain the initial weight of each target product.
In the foregoing solution, the combination determining apparatus further includes an adjusting module, configured to:
determining a benefit of at least one target product associated with each of the feature factors in the product portfolio;
determining an overall profit for the corresponding feature factor based on the profit for the at least one target product;
when the overall profit of the characteristic factor is higher than a factor profit reference value, increasing the weight of the at least one target product associated with the characteristic factor;
and when the overall income of the characteristic factors is lower than a factor income minimum threshold, reducing the weight of the at least one target product associated with the characteristic factors, or removing the characteristic factors to obtain a new product combination.
In the foregoing solution, the adjusting module is further configured to:
determining a benefit for each of the target products in the product portfolio;
when the income of the target product is higher than a target product income reference value, increasing the weight of the target product;
and when the income of the target product is lower than the lowest threshold value of the income of the target product, adjusting the weight of the target product, or removing the target product from the product combination to obtain a new product combination.
In the foregoing solution, the adjusting module is further configured to:
reduce the weight of the target product, or
And restoring the weight of the target product to the initial weight.
An embodiment of the present application provides an electronic device, including:
a memory for storing executable instructions;
and the processor is used for realizing the combination determination method provided by the embodiment of the application when executing the executable instructions stored in the memory.
The embodiment of the present application provides a computer-readable storage medium, which stores executable instructions for causing a processor to implement the combination determination method provided by the embodiment of the present application when executed.
The present application provides a computer program product or a computer program, where the computer program product or the computer program includes computer instructions stored in a computer-readable storage medium, and a processor of an electronic device reads the computer instructions from the computer-readable storage medium, and executes the computer instructions, so that the electronic device executes the combination determination method provided in the present application.
The embodiment of the application has the following beneficial effects:
the characteristic factors and the target products are determined based on the user preference, the initial weight of each target product is determined based on the correlation degree between the target products and the characteristic factors, so that a product combination formed by each target product can be efficiently and quickly obtained, meanwhile, the proportion of each target product in the product combination can be determined, manual screening of the target products and the characteristic factors is not needed, the product combination is more intelligent, and the target products are closer to the user preference and the user requirements.
Drawings
Fig. 1 is a schematic architecture diagram of an investment system 10 provided by an embodiment of the present application;
fig. 2 is a schematic flowchart of a combination determination method provided in an embodiment of the present application;
FIG. 3 is a schematic illustration of portfolio determination provided by an embodiment of the present application;
FIG. 4 is a schematic diagram of a tag mapping provided by an embodiment of the present application;
FIG. 5 is a schematic illustration of the ranking of investment targets provided by an embodiment of the present application;
FIG. 6 is a schematic illustration of determining a ranking of investment targets provided by an embodiment of the present application;
FIG. 7 is a schematic diagram of determining portfolios provided by an embodiment of the present application;
FIG. 8 is a schematic diagram of a tempering chamber provided by an embodiment of the present application;
fig. 9 is a schematic structural diagram of a server 200 according to an embodiment of the present application.
Detailed Description
In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be described in further detail with reference to the attached drawings, the described embodiments should not be considered as limiting the present application, and all other embodiments obtained by a person of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.
In the following description, reference is made to "some embodiments" which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of the present application only and is not intended to be limiting of the application.
Before further detailed description of the embodiments of the present application, terms and expressions referred to in the embodiments of the present application will be described, and the terms and expressions referred to in the embodiments of the present application will be used for the following explanation.
1) The investment targets are as follows: refers to the subject matter available for investment purchase throughout the financial market. The types of investment targets include funds, stocks, options, gold, etc. When the type of the investment target is fund, the investment target can be onsite fund, offsite fund, plate fund, index fund and the like; when the type of the investment target is stock, the investment target can be any one stock; when the type of the investment target is an option, the investment target may be a short-term option or a long-term option.
2) Investment factors: the investment factors are factors which can be evaluated and can measure the investment targets and are generated after being analyzed through algorithm services, and the factors comprise basic surface factors, price factors, net asset profitability and the like.
3) Market interference Ratio (PER, Price Earnings Ratio): also known as the ben-yi ratio or the market price profitability ratio. Market profitability, which is the ratio of the price of an investment target divided by its profit, is often used to assess whether the price level of the investment target is reasonable.
4) And (3) bin adjustment: the warehouse adjustment is to carry out timely adjustment and replacement on stock holding and warehouse positions when the big plate changes to a certain degree so as to control risks and convert profits. The binning operation generally has three directions: the first is to sell one part of the profit and adjust the position of the bin; secondly, selling a part of the lost stocks, and performing loss stopping operation on the bin positions to prevent larger loss; and thirdly, selling the current held stock and converting the current held stock into a new stock.
In the process of determining an investment product combination, the related technology often manually screens the characteristic factors and selects a target product for investment based on the characteristic factors, which requires a certain investment experience and professional knowledge, so that not only the threshold of a common investor is too high, but also a large amount of labor cost is required, the investment accuracy is poor, and a large investment risk may be brought.
In view of the foregoing problems, embodiments of the present application provide a combination determination method, apparatus, electronic device, and computer-readable storage medium, which can improve accuracy of investment.
The combination determination method provided by the embodiment of the present application may be implemented by various electronic devices, for example, may be implemented by a server (hereinafter, a master node device) alone, or may be implemented by a server and a terminal in cooperation. For example, the server alone performs the combination determination method described below, or the terminal and the server cooperate to perform the combination determination method described below. For example, a user preference questionnaire is presented in a user terminal, answers to the questionnaire filled or selected by a user are obtained in response to a questionnaire submitting operation of the user, a user preference questionnaire result is obtained, a product combination request carrying the user preference questionnaire result is sent to a server, after the server receives the product combination request, determining associated target products and characteristic factors according to the user preference survey result, and determining the weight of each characteristic factor, and the correlation degree between each target product and each characteristic factor, determining the weight of each target product based on the correlation degree between each target product and each characteristic factor and the weight corresponding to each characteristic factor, and finally, sorting the target products in a descending order based on the weight of each target product, and sending the product combination formed by the sorted target products to a terminal of a user so as to present the suggested product combination in the terminal.
In the embodiment of the application, the server may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a network service, cloud communication, a middleware service, a domain name service, a security service, a CDN, a big data and artificial intelligence platform, and the like; the terminal may be, but is not limited to, a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart television, a smart vehicle-mounted terminal, and the like. The terminal and the server may be directly or indirectly connected through wired or wireless communication, which is not limited in this embodiment of the application.
Taking a server as an example, for example, the server cluster may be deployed in a cloud, and an artificial intelligence cloud Service (AI aas, AI as a Service) is opened to a user, the AIaaS platform splits several types of common AI services, and provides an independent or packaged Service in the cloud, this Service mode is similar to an AI theme mall, and all users may access one or more artificial intelligence services provided by the AIaaS platform by using an application programming interface.
For example, one of the artificial intelligence cloud services may be a product combination service, that is, a cloud server encapsulates the product combination program provided by the embodiment of the present application. The method comprises the steps that a terminal of a user responds to a questionnaire submitting operation, a product combination request carrying user preference survey results is sent to a server at the cloud end, the server at the cloud end calls a packaged product combination program, associated characteristic factors and target products are determined according to questionnaire answers, the weights of the target products are determined according to the characteristic factors, the target products are sorted in a descending order according to the weights, and product combinations formed by the sorted target products are sent to the terminal of the user so that suggested product combinations can be presented in the terminal.
The following describes an example in which a server and a terminal cooperatively implement the combination determination method provided in the embodiments of the present application. Referring to fig. 1, fig. 1 is a schematic diagram of an architecture of an investment system 10 provided by an embodiment of the present application. The terminal 400 is connected to the server 200 through a network 300, and the network 300 may be a wide area network or a local area network, or a combination of both.
In some embodiments, the terminal 400 of the user sends a product combination request carrying a user preference survey result to the server 200 in response to the questionnaire submission operation, the server 200 determines the associated feature factors and target products according to the user preference survey result, determines the weight of each target product according to the feature factors, performs descending order sorting on the target products according to the weight, and sends a product combination formed by the sorted target products to the terminal 400 of the user so as to present a suggested product combination in the terminal 400.
In the following, a combination determination method provided by an embodiment of the present application will be described with reference to the accompanying drawings, where an execution subject of the combination determination method may be a master node device, and specifically, the master node device may be implemented by running the above various computer programs; of course, as will be understood from the following description, it is obvious that the combination determination method provided in the embodiments of the present application may also be implemented by the terminal and the master node device in cooperation.
Referring to fig. 2, fig. 2 is a schematic flowchart of a combination determination method provided in an embodiment of the present application, and will be described with reference to the steps shown in fig. 2.
In step 101, the master node device receives a product combination request, determines a target product and a feature factor based on user preferences, and transmits information of the target product and the feature factor to the plurality of slave node devices, so that the plurality of slave node devices determine a correlation between the corresponding feature factor and each target product.
In some embodiments, the server cluster includes a master node device and a plurality of slave node devices, each slave node device being connected to the master node device and each slave node device being independent of each other. The master node device is used for determining the product combination based on the product combination request, and the slave node device is used for determining the correlation degree of the target product and the characteristic factor. The product combination request is for requesting recommendation of a product combination of at least one product. In some possible examples, the correlation between the target product and the feature factor may also be determined by the master node device, and the product combination may also be determined.
In some embodiments, the terminal sends a product combination request to the master node device in the server cluster in response to a user's associated operation (e.g., login operation, browse operation, questionnaire submission operation) when at least one of the following occurs: when a user logs into a related application (such as a financial application or a payment application) or applet, when a user browses investably purchasable products in a related application, when a user fills out a user preference questionnaire in a related application.
In some embodiments, the user preferences include the type of product the user prefers to invest, affordable risk capabilities, duration of investment, and the like. The target product is a virtual, tradable product that may be an investment target, a cryptocurrency (e.g., bitcoin), or the like. The characteristic factor is a factor for characterizing the characteristics (such as value, volatility, risk, trend, etc.) of the target product itself, for example, when the target product is an investment target, the corresponding characteristic factor may be an investment factor, such as a base surface factor or a price factor. The information of the target product includes information such as the type and name of the target product.
In some embodiments, determining the target product and the feature factor based on the user preference may be accomplished as follows. Determining the preference of the user based on the purchase record of the user or the survey result of the preference of the user; at least one target product matching the user's preferences and at least one feature factor matching the user's preferences are determined by querying the mapping table. The mapping table stores user preferences and corresponding target products, and the user preferences and corresponding characteristic factors. It should be noted that the user preferences and the target products may be in a one-to-one or one-to-many relationship, and the user preferences and the feature factors may also be in a one-to-one or one-to-many relationship.
In some possible examples, when the product combination request received by the master node device includes user preference questionnaires including questionnaire answers that the user fills in or selects in the user preference questionnaire, the user's preferences may be determined based on the user preference questionnaires (i.e., questionnaire answers). For example, for the problem: what kind of target you tend to invest in? A. The growth is stable; B. the fluctuation is large; C. the period fluctuates. If the answer of the questionnaire shows that the user selects A, the user prefers conservative investment, and the method is not suitable for products with large investment income and large risk. Then, by taking the conservative investment as a user preference query mapping table, the corresponding target product and the characteristic factor can be obtained.
In some possible examples, the master node device may obtain a record of purchases made by the user in the financial application in the near term (e.g., the last three months or the last year) and analyze the products in the record of purchases to obtain the user's preferences. For example, the user has bought stock 1 and stock 2 in the financing application program in the last three months, and the volatility of stock 1 and stock 2 is large, so that the user preference inauguration investment can be determined, and the corresponding target product and characteristic factor can be obtained by using the inauguration investment as the user preference query mapping table.
In other possible examples, when the product combination request received by the master node device includes user preference questionnaires, the user preference questionnaires include questionnaire answers that the user fills in or selects in the user preference questionnaire. When the user preference questionnaire is in a form of blank filling, semantic analysis can be performed on blank filling contents of the user in the user preference survey result, so that a target product and characteristic factors are determined. When the user preference questionnaire is in the form of selection questions, each option of each selection question is associated with at least one tag, and the tags comprise market class tags (such as A stock, American stock and harbor stock), plate class tags (such as main board, startup board and scientific edition), industry class tags (such as finance industry, manufacturing industry and insurance industry), index class tags (such as market profitability, market value, net market rate and fluctuation rate) or custom tags (such as pork and short video). The target product and the feature factor may be determined according to the label associated with the answer selected by the user in each choice question of the user preference questionnaire. For example, counting the frequency of occurrence of each associated tag, and if the tag is a tag related to a product, when the frequency of occurrence of the tag exceeds a frequency threshold, taking the product related to the tag as a target product; if the label is a label related to the factor, when the frequency of the label exceeds the frequency threshold value, the factor related to the label is taken as the characteristic factor. As an example, in the tag associated with the answer selected in each choice question of the user preference questionnaire, the tag "stock a" appears 3 times, exceeding the frequency threshold (1 time), and thus "stock a" is taken as the target product.
In some embodiments, each slave node device corresponds to a characteristic factor. The degree of correlation characterizes the degree of correlation between the characteristic factor and the target product. For example, for the target product "A shares," the correlation of the characteristic factor "cost factor" with "A shares" may be 0.5, and the correlation of the characteristic factor "net asset profitability" with "A shares" may be 0.6, indicating that the "net asset profitability" is more correlated with "A shares" than the "cost factor" with "A shares".
In some embodiments, after the master node device sends the determined at least one target product and the at least one characteristic factor to the plurality of slave node devices, each slave node device determines whether a characteristic factor corresponding to the slave node device exists in the at least one characteristic factor, and if the corresponding characteristic factor does not exist, the slave node device is idle and does not perform processing. And if the corresponding characteristic factors exist, determining the correlation degree between the corresponding characteristic factors and each target product through the slave node equipment.
In some possible examples, when the feature factor is used to evaluate the market profitability of the target product, the slave node device corresponding to the feature factor divides a plurality of feature factor intervals based on the distribution of the feature factor, determines an interval probability corresponding to the feature factor interval to which the feature factor of each target product belongs, and takes the interval probability as the correlation degree between the corresponding target product and the feature factor.
Since the market profitability of each investment target is different, the market profitability of each investment target can be counted over a period of time (e.g., within 3 months), so as to obtain the distribution of the market profitability, and a plurality of market profitability intervals (i.e., characteristic factor intervals) can be obtained by dividing based on the distribution of the market profitability. For example, the market profitability may be divided evenly, and the number of the market profitability that falls into each market profitability interval may be counted as the interval probability corresponding to the market profitability interval. When the correlation degree between the target product and the market profitability is determined, the market profitability interval to which the market profitability of the target product belongs is determined, and then the interval probability corresponding to the market profitability interval is used as the correlation degree between the target product and the market profitability.
In some possible examples, when the characteristic factor is used for evaluating the public opinion risk of the target product, the slave node device corresponding to the characteristic factor acquires media content, and performs identification processing on the media content to obtain target media content associated with the target product, wherein the type of the target media content includes at least one of the following: video, text, picture. The target media content associated with the target product, i.e., the media content whose content includes information such as the name of the target product. Determining the number of preset keywords included in the target media content; and adjusting the public opinion reference value based on the number of the preset keywords to obtain the correlation between the target product and the characteristic factor. The preset keywords comprise positive keywords, negative keywords and neutral keywords. Every time the positive keywords appear, the public opinion reference value is increased by a preset value; every time a negative keyword appears, the public opinion benchmark value is reduced by the preset value. Therefore, the public opinion reference value can be adjusted based on the number of the preset keywords, and the correlation degree between the target product and the characteristic factor is obtained.
In some possible examples, the consensus reference value may be determined as follows. Acquiring historical performance data of a target product; determining a candidate public opinion reference value based on historical performance data; and performing back-testing on the candidate public opinion reference value, and taking the candidate public opinion reference value as the public opinion reference value when the verification is passed. The historical expression data comprises the fluctuation condition, the income condition, the number of purchasers, the media comment condition and the like of the target product.
In step 102, the master node device receives the correlation degrees returned from the plurality of slave node devices.
In step 103, a starting weight of each target product is determined based on the correlation between each feature factor and each target product and the weight corresponding to each feature factor.
In some embodiments, the correlation between each target product and each feature factor is weighted and summed based on the weight corresponding to each feature factor, so as to obtain the initial weight of each target product. Wherein, the weights corresponding to different characteristic factors are fixed values. When the sum of the initial weights of the target products is not equal to 1, normalization processing needs to be performed on the initial weights, so that the sum of the initial weights of the target products is 1.
For example, the weight corresponding to the characteristic factor 1 is 0.3, the weight corresponding to the characteristic factor 2 is 0.3, and the weight corresponding to the characteristic factor 3 is 0.2. For the target product 1, if the correlation between the target product 1 and the characteristic factor 1 is 0.5, the correlation between the target product 1 and the characteristic factor 2 is 0.3, and the correlation between the target product 1 and the characteristic factor 3 is 0.4, the initial weight of the target product 1 is: 0.3 × 0.5+0.3 × 0.3+0.2 × 0.4 is 0.32.
In this way, the initial weights of the individual target products that make up the product combination can be quickly determined, and the share of the individual target products can be determined. When the profit of the target product is lost, the weight of the target product can be restored to the initial weight.
In step 104, the target products are ranked based on the initial weight of each target product, and the product combination request is responded based on the product combination formed by the ranked target products.
In some embodiments, the target products are sorted in descending order or ascending order based on the initial weight of each target product, and the product combination formed by the sorted target products is returned to the terminal to respond to the product combination request of the terminal. And after receiving the confirmed purchasing operation of the terminal, purchasing the target products according to the shares corresponding to the initial weights of the target products. Therefore, the investment risk can be reduced, the risk resistance of the product combination is improved, and the product income is improved in a mode of purchasing the product combination by investment.
In some embodiments, after determining the product portfolio, the return of the target product associated with the investment factor in the product portfolio is continuously tracked and binned (i.e., adjusted) according to its return. The target product with the correlation degree greater than the threshold value of the correlation degree with the investment factor can be used as the target product associated with the investment factor. The adjusted time interval may be once a day, or once every three days, once a week, etc. At certain intervals, the main node equipment determines the income of at least one target product associated with each characteristic factor in the product combination; determining an overall profit for the corresponding feature factor based on the profit for the at least one target product; when the overall profit of the characteristic factor is higher than the factor profit reference value, increasing the weight of at least one target product associated with the characteristic factor; and when the overall income of the characteristic factors is lower than the factor income minimum threshold, reducing the weight of at least one target product associated with the characteristic factors, or removing the characteristic factors to obtain a new product combination.
For example, the correlation threshold is set to 0.7, the correlation between the characteristic factor 4 and the target product 1 is 0.75, and the correlation between the characteristic factor 4 and the target product 2 is 0.8, then the characteristic factor 4 is associated with the target product 1 and the target product 2, and the income condition of the target product 1 and the target product 2 is taken as the overall income of the characteristic factor 4. And when the overall profit is higher than the factor profit reference value, increasing the weight of the target product 1 or the target product 2 or the target product 1 and the target product 2 in the product combination. And when the overall profit is lower than the factor profit minimum threshold, reducing the weight of the target product 1 or the target product 2 or the target product 1 and the target product 2 in the product combination, or removing the target product 1 or the target product 2 or the target product 1 and the target product 2 to obtain a new product combination. Therefore, the performance of the characteristic factors can be evaluated according to the profits of the target products related to the characteristic factors, the product combination is adjusted according to the performance of the characteristic factors, and the profits of users are increased.
In some embodiments, after determining the product portfolio, the profitability of the investment target in the product portfolio is continuously tracked and the product portfolio is adjusted according to its profitability. The adjusted time interval may be once a day, or once every three days, once a week, etc. At certain intervals, the main node equipment determines the income of each target product in the product combination; when the income of the target product is higher than the income reference value of the target product, increasing the weight of the target product; and when the income of the target product is lower than the lowest income threshold value of the target product, reducing the weight of the target product, or restoring the weight of the target product to the initial weight, or removing the target product from the product combination to obtain a new product combination.
The target product income reference value corresponding to each target product can be the same or different; the lowest threshold value of the target product income corresponding to each target product can be the same or different. And taking the income interval between the target product income minimum threshold value of each target product and the target product income reference value as an income normal floating interval. And when the income of the target product is in the income normal floating interval, confirming that the income of the target product is normal. And when the income of the target product is higher than the income reference value of the target product, confirming that the target product belongs to the profit state, and increasing the weight of the target product in the product combination in a mode of increasing and holding the target product. When the income of the target product is lower than the lowest income threshold value of the target product, the target product is confirmed to be in a loss state, the weight of the target product in the product combination can be reduced in a mode of maintaining the target product, and the share of the target product (such as reducing the stock number of stocks) can also be adjusted, so that the weight of the target product is restored to the initial weight occupied in the product combination when the product combination is created. When the target product loss exceeds the stop loss value, the target product can also be removed from the product combination to avoid further loss. Thus, the weights of the target products in the product combination can be adjusted in time according to the income expression of the target products, loss is avoided, and income is increased.
In some embodiments, after determining the adjustment policy for the product combination by the method described above, the product combination invested by the user may be automatically adjusted, or the adjustment policy and the adjustment reason (such as loss) may be sent to the terminal of the user, and the adjustment may be performed on the product combination after receiving the confirmation operation of the adjustment policy. Therefore, the user can intuitively feel the profit and loss change of the product combination of the investment, the corresponding adjustment strategy is given, the user does not need to determine how to adjust according to the investment experience, the adjustment strategy does not need to be determined by a third party, the equipment resource is saved, and the adjustment efficiency is improved.
It can be seen that the characteristic factors and the target products are determined based on the user preference in the embodiment of the application; determining the correlation degree between each target product and each characteristic factor; determining the weight of each target product based on the correlation degree between each target product and each characteristic factor and the weight corresponding to each characteristic factor; the target products are sorted based on the weight of each target product, the combination formed by the sorted target products is used as the product combination corresponding to the user, manual screening of the target products and characteristic factors is not needed, the method is more intelligent, the proper product combination can be determined efficiently and quickly, and the product combination is closer to the user preference and the user requirement.
Next, an exemplary application of the embodiment of the present application in a practical application scenario will be described.
According to the embodiment of the application, the investment portfolio is recommended to the user based on the investment target, the investment factors and the user preference, and meanwhile long-term performance tracking can be conducted on the investment factors and the investment portfolio, so that a proper warehouse adjusting scheme is recommended to the user for the user to select and adjust according to the latest combined income and factor income.
In some embodiments, as shown in FIG. 3, FIG. 3 is a schematic illustration of portfolio determination provided by embodiments of the present application. User preferences can be determined in a Web page through a risk questionnaire and the like, and then investment targets and investment factors are determined. Questions in the risk questionnaire are used to determine user preferences for industry, market, risk, revenue, etc. investment characteristics, etc. And the answers to each question are associated with different investment factors and investment goals. For example, for the multiple choice question 1, do you tend to invest in the logo of which markets below? The selection can be made from three options: A. a strand is formed; B. beautifying the thigh; C. and (4) harbor strand. Wherein, option a may be associated with investment factor 1 and investment target 1, option B may be associated with investment factor 2 and investment target 2, and option C may be associated with investment factor 3 and investment target 3. It can be seen that the multiple choice question 1 is for determining the investment target preferred by the user, and when the user selects only a, the corresponding investment factor 1 and the investment target 1 are determined accordingly. As another example, for the multiple choice question 2, what kind of target below you tend to invest? The selection can be made from three options: A. the growth is stable; B. the fluctuation is large; C. the period fluctuates. It can be seen that the multiple choice question 2 is for determining the type of user preference, where each option is also associated with a corresponding investment factor and investment target. When the answer selected by the user for each question in the questionnaire is received, if the market preferred by the user is China stock A, the industry is the consuming industry, and the risk is acceptable loss and strives for higher profit, the corresponding investment target and the investment factor can be determined according to the characteristics (labels).
Referring to fig. 4, fig. 4 is a schematic diagram of a label mapping provided in an embodiment of the present application. Each investment factor is associated with a plurality of tags in a pool of investment factors, and each investment target is associated with a plurality of tags in the pool of investment targets. Referring to table 1, table 1 is a schematic table of an incremental tag pool provided in an embodiment of the present application, and tags in the tag pool represent a feature to be updated (modified or added) in real time or periodically.
| Market label | A, Mei and hong Kong |
| Plate type label | Main board, entrepreneurship board and scientific plate |
| Industry type label | Finance, manufacturing and insurance industries |
| Index label | Market profitability, market value, market net rate, and fluctuation rate |
| Custom label | Pork short video |
TABLE 1 schematic of incremental tag pools
After the investment factors are determined, the weights corresponding to the investment factors can be determined. For example, 4 investment factors, namely a factor A, a factor B, a factor C and a factor D, are screened out according to the user preference. The weight corresponding to each factor can be determined according to data such as historical income of each factor, and the weight corresponding to each factor is a fixed value in the process of determining the investment portfolio. Assume that the weight for factor a is 1, the weight for factor B is 2, the weight for factor C is 3, and the weight for factor D is 4.
Then, as shown in fig. 5 and 6, the degree of correlation of each investment target with each investment factor can be determined. Taking the investment factor as a market profitability factor (for estimating the market profitability of the investment target) as an example, the correlation between the investment target and the market profitability factor can be determined according to the distribution state of the market profitability corresponding to the investment target in the normal distribution. If the market profit rate corresponding to the investment target is 50 and the reference value is 10, the relative value is 5, and the probability that 5 falls in the normal distribution corresponding interval is determined to be 80%, then the correlation between the investment target and the market profit rate factor is 0.8. Taking the investment factor as a public opinion factor (for evaluating public opinion risk) as an example, an event subject (investment target) in news can be identified based on a natural language processing algorithm, and then a reference value is calculated based on keywords (positive field and negative field) in the news of the related event subject to obtain the degree of correlation. For example, the reference value is 10, if the positive field appears, 0.1 is added to the reference value, if the negative field appears, 0.2 is subtracted from the reference value, and the final value (e.g., 10.1) is used as the correlation between the investment target and the public opinion factor.
After the weight corresponding to each investment factor and the correlation degree of each investment target and each investment factor are obtained, the corresponding weight of each investment target can be determined. Referring to table 2, table 2 is a table of the relationship between the investment targets and the investment factors provided in the examples of the present application. In the relational table, the data in each cell is the correlation between the corresponding investment targets and the investment factors. Taking the target a as an example, the corresponding weight is 0.5 × 1+0.1 × 2+0.7 × 3+1.5 × 4 — 8.8. The weights corresponding to target b, target c, target d, target e and target f can be calculated in turn. Then, the corresponding weights of the investment targets can be normalized to obtain normalized weights. As shown in fig. 7, the investment targets are sorted in a descending order according to the normalized weights, the investment portfolio formed by the sorted investment targets is sent to the client of the user, and after receiving the determination operation of the user on the investment portfolio, the investment portfolio is determined to be the investment portfolio selected by the user.
TABLE 2 relationship of investment target to investment factor
As shown in fig. 8, after determining the investment portfolio and making investment, the market information of all investment targets is synchronized through batch tasks every day, the income of each investment portfolio and each investment factor is calculated according to the market information, and the corresponding shunting information is pushed to the user according to the income condition. For example, if the performance of a certain investment factor is lower than a reference value, it may be recommended to propose the investment factor; if the performance of a certain investment factor is higher than a reference value, the weight of the investment factor can be increased; if the weight sequence of the investment targets changes, the investment targets are recommended to be adjusted; other investment factors and the like can also be added. The user can select whether to transfer the investment portfolio or not, and can authorize the system to automatically transfer the investment portfolio, if the automatic transfer is authorized, the investment portfolio position or the pool of the investment target and the pool of the investment factor will be automatically adjusted when the loss deviation of the investment portfolio exceeds the threshold value (such as 7%).
It can be seen that, in the embodiment of the application, based on the investment preference of the user, the corresponding investment targets and the corresponding investment factors are screened, the investment combination related to the user preference is obtained by combining and calculating the investment targets and the investment factors, manual screening of the investment targets and the investment factors is not needed, the method is more intelligent, the proper investment combination can be determined efficiently and quickly, and the investment combination is closer to the user preference and the user requirement. Meanwhile, long-term performance tracking can be carried out on the investment factors and the investment portfolio, and a proper warehouse adjusting scheme is recommended to the user for the user to select and adjust according to the latest portfolio income and factor income. The early warning is timely given to the user through the warehouse adjustment suggestion, possible investment risks are avoided, the stability and the safety of investment are improved, and the investment income is guaranteed.
An exemplary structure of the server is explained below. Referring to fig. 9, fig. 9 is a schematic structural diagram of a server 200 according to an embodiment of the present application, where the server 200 shown in fig. 9 includes: at least one processor 410, memory 440, at least one network interface 420. The various components in server 200 are coupled together by a bus system 430. It is understood that the bus system 430 is used to enable connected communication between these components. The bus system 430 includes a power bus, a control bus, and a status signal bus in addition to the data bus. For clarity of illustration, however, the various buses are labeled as bus system 430 in fig. 9.
The Processor 410 may be an integrated circuit chip having Signal processing capabilities, such as a general purpose Processor, a Digital Signal Processor (DSP), or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like, wherein the general purpose Processor may be a microprocessor or any conventional Processor, or the like.
The memory 440 may be removable, non-removable, or a combination thereof. Exemplary hardware devices include solid state memory, hard disk drives, optical disk drives, and the like. Memory 440 optionally includes one or more storage devices physically located remote from processor 410.
Memory 440 includes volatile memory or nonvolatile memory, and can include both volatile and nonvolatile memory. The nonvolatile Memory may be a Read Only Memory (ROM), and the volatile Memory may be a Random Access Memory (RAM). The memory 440 described in embodiments herein is intended to comprise any suitable type of memory.
In some embodiments, memory 440 is capable of storing data to support various operations, examples of which include programs, modules, and data structures, or subsets or supersets thereof, as exemplified below.
Operating system 441, which includes system programs such as a framework layer, a core library layer, a driver layer, etc. for handling various basic system services and performing hardware-related tasks, is used for implementing various basic services and for handling hardware-based tasks.
A network communication module 442 for communicating to other electronic devices via one or more (wired or wireless) network interfaces 420, the example network interface 430 including: bluetooth, wireless compatibility authentication (WiFi), and Universal Serial Bus (USB), among others.
In some embodiments, the combination determination apparatus provided by the embodiments of the present application may be implemented in software, and fig. 9 illustrates the combination determination apparatus 443 stored in the memory 440, which may be software in the form of programs, plug-ins, and the like, and includes a determination module 4431, a receiving module 4432, a sorting module 4433, and an adjusting module 4434. The functions of the respective modules will be explained below.
A determining module 4431, configured to receive a product combination request, determine a target product and a feature factor based on user preferences, and send information and the feature factor of the target product to a plurality of slave node devices, so that the plurality of slave node devices determine a correlation between the corresponding feature factor and each target product, where each slave node device corresponds to one feature factor; the initial weight of each target product is determined based on the correlation degree between each characteristic factor and each target product and the weight corresponding to each characteristic factor; a receiving module 4432, configured to receive a plurality of correlation degrees returned from the node device; the sorting module 4433 is configured to sort the plurality of target products based on the initial weight of each target product, and respond to the product combination request based on the product combination composed of the sorted target products.
In some embodiments, the determining module 4431 is further configured to determine the user's preferences based on the user's purchase record or the user preference survey results; at least one target product matching the user's preferences and at least one feature factor matching the user's preferences are determined by querying the mapping table.
In some embodiments, when the feature factor is used to evaluate the market profitability of the target product, the determining module 4431 is further configured to send the information of the target product and the feature factor to the slave node device corresponding to the feature factor, so that the slave node device corresponding to the feature factor is divided based on the distribution of the feature factor to obtain a plurality of feature factor intervals, and determine an interval probability corresponding to the feature factor interval to which the feature factor of each target product belongs, and use the interval probability as the correlation between the corresponding target product and the feature factor.
In some embodiments, when the feature factor is used to evaluate the public opinion risk of the target product, the determining module 4431 is further configured to send the information of the target product and the feature factor to the slave node device corresponding to the feature factor, so that the slave node device obtains the media content and performs identification processing on the media content to obtain the target media content associated with the target product; determining the number of preset keywords included in the target media content; and adjusting the public opinion reference value based on the number of the preset keywords to obtain the correlation between the target product and the characteristic factor.
In some embodiments, the determining module 4431 is further configured to obtain historical performance data of the target product; determining a candidate public opinion reference value based on historical performance data; and performing back-testing on the candidate public opinion reference value, and taking the candidate public opinion reference value as the public opinion reference value when the verification is passed.
In some embodiments, the determining module 4431 is further configured to perform weighted summation on the correlation between each target product and each feature factor based on the weight corresponding to each feature factor, so as to obtain a starting weight of each target product.
In some embodiments, the combination determining apparatus further comprises an adjustment module 4434 for determining a benefit of at least one target product associated with each of the feature factors in the product combination; determining an overall profit for the corresponding feature factor based on the profit for the at least one target product; when the overall profit of the characteristic factor is higher than the factor profit reference value, increasing the weight of at least one target product associated with the characteristic factor; and when the overall income of the characteristic factors is lower than the factor income minimum threshold, reducing the weight of at least one target product associated with the characteristic factors, or removing the characteristic factors to obtain a new product combination.
In some embodiments, the adjustment module 4434 is further configured to determine a revenue for each target product in the product portfolio; when the income of the target product is higher than the income reference value of the target product, increasing the weight of the target product; and when the income of the target product is lower than the lowest threshold value of the income of the target product, adjusting the weight of the target product, or removing the target product from the product combination to obtain a new product combination.
In some embodiments, the adjustment module 4434 is further configured to reduce the weight of the target product or restore the weight of the target product to the initial weight.
Embodiments of the present application provide a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the electronic device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the electronic device executes the combination determination method described in the embodiment of the present application.
Embodiments of the present application provide a computer-readable storage medium having stored therein executable instructions that, when executed by a processor, cause the processor to perform a combination determination method provided by embodiments of the present application, for example, the combination determination method as shown in fig. 2.
In some embodiments, the computer-readable storage medium may be memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash, magnetic surface memory, optical disk, or CD-ROM; or may be various devices including one or any combination of the above memories.
In some embodiments, executable instructions may be written in any form of programming language (including compiled or interpreted languages), in the form of programs, software modules, scripts or code, and may be deployed in any form, including as a stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment.
By way of example, executable instructions may correspond, but do not necessarily have to correspond, to files in a file system, and may be stored in a portion of a file that holds other programs or data, such as in one or more scripts in a hypertext Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files that store one or more modules, sub-programs, or portions of code).
By way of example, executable instructions may be deployed to be executed on one computing device or on multiple computing devices at one site or distributed across multiple sites and interconnected by a communication network.
In summary, it can be seen that, in the embodiment of the present application, based on the investment preference of the user, the corresponding investment targets and the corresponding investment factors are screened, and the investment portfolio related to the user preference is obtained by combining and calculating the investment targets and the investment factors, so that the investment targets and the investment factors do not need to be screened manually, which is more intelligent, and a suitable investment portfolio can be determined efficiently and quickly, and can be closer to the user preference and the user requirement. Meanwhile, long-term performance tracking can be carried out on the investment factors and the investment portfolio, and a proper warehouse adjusting scheme is recommended to the user for the user to select and adjust according to the latest portfolio income and factor income. The early warning is timely given to the user through the warehouse adjustment suggestion, possible investment risks are avoided, the stability and the safety of investment are improved, and the investment income is guaranteed.
The above description is only an example of the present application, and is not intended to limit the scope of the present application. Any modification, equivalent replacement, and improvement made within the spirit and scope of the present application are included in the protection scope of the present application.
Claims (12)
1. A method of combination determination, the method comprising:
the method comprises the steps that a main node device receives a product combination request, determines a target product and characteristic factors based on user preference, and sends information of the target product and the characteristic factors to a plurality of slave node devices, so that the slave node devices determine the correlation degree between the corresponding characteristic factors and each target product, wherein each slave node device corresponds to one characteristic factor;
receiving the relevance returned by the plurality of slave node devices;
determining a starting weight of each target product based on the correlation degree between each characteristic factor and each target product and the weight corresponding to each characteristic factor;
and sequencing a plurality of target products based on the initial weight of each target product, and responding to the product combination request based on the product combination formed by the sequenced target products.
2. The method of claim 1, wherein determining the target product and the feature factor based on the user preference comprises:
determining a preference of a user based on a purchase record of the user or a user preference survey result;
determining at least one target product matching the user's preferences and at least one feature factor matching the user's preferences by querying a mapping table.
3. The method according to claim 1, wherein when the characteristic factors are used for evaluating a market profitability of the target product, the sending the information of the target product and the characteristic factors to a plurality of slave node devices to enable the plurality of slave node devices to determine a correlation between the corresponding characteristic factors and each target product comprises:
sending the information of the target product and the characteristic factor to slave node equipment corresponding to the characteristic factor so as to enable the slave node equipment to work
And the slave node equipment corresponding to the characteristic factors is divided based on the distribution of the characteristic factors to obtain a plurality of characteristic factor intervals, the interval probability corresponding to the characteristic factor interval to which the characteristic factor of each target product belongs is determined, and the interval probability is used as the correlation degree between the corresponding target product and the characteristic factors.
4. The method of claim 1, wherein when the characteristic factors are used for evaluating the public opinion risk of a target product, the sending the information of the target product and the characteristic factors to a plurality of slave node devices to enable the plurality of slave node devices to determine the correlation between the corresponding characteristic factors and each target product comprises:
sending the information of the target product and the characteristic factors to slave node equipment corresponding to the characteristic factors so that the slave node equipment acquires media content and identifies the media content to obtain target media content related to the target product;
determining the number of preset keywords included in the target media content;
and adjusting the public opinion reference value based on the number of the preset keywords to obtain the correlation degree between the target product and the characteristic factor.
5. The method of claim 4, wherein prior to said transmitting the information of the target products and the characteristic factors to a plurality of slave node devices to cause the plurality of slave node devices to determine a degree of correlation between the corresponding characteristic factors and each of the target products, the method further comprises:
acquiring historical performance data of the target product;
determining a candidate public opinion benchmark value based on the historical performance data;
and performing a back test on the candidate public opinion reference value, and when the candidate public opinion reference value passes the test, taking the candidate public opinion reference value as the public opinion reference value.
6. The method of claim 1, wherein determining the starting weight of each target product based on the correlation between each characteristic factor and each target product and the weight corresponding to each characteristic factor comprises:
and carrying out weighted summation on the correlation degree between each target product and each characteristic factor based on the weight corresponding to each characteristic factor to obtain the initial weight of each target product.
7. The method of claim 1, wherein after the product portfolio response to the product portfolio request based on the ranked target products, the method further comprises:
determining a benefit of at least one target product associated with each of the feature factors in the product portfolio;
determining an overall profit for the corresponding feature factor based on the profit for the at least one target product;
when the overall profit of the characteristic factor is higher than a factor profit reference value, increasing the weight of the at least one target product associated with the characteristic factor;
and when the overall income of the characteristic factors is lower than a factor income minimum threshold, reducing the weight of the at least one target product associated with the characteristic factors, or removing the characteristic factors to obtain a new product combination.
8. The method of claim 1, wherein after the product portfolio response to the product portfolio request based on the ranked target products, the method further comprises:
determining a benefit for each of the target products in the product portfolio;
when the income of the target product is higher than a target product income reference value, increasing the weight of the target product;
and when the income of the target product is lower than the lowest threshold value of the income of the target product, adjusting the weight of the target product, or removing the target product from the product combination to obtain a new product combination.
9. The method of claim 8, wherein the adjusting the weight of the target product comprises:
reduce the weight of the target product, or
And restoring the weight of the target product to the initial weight.
10. A combination determination apparatus, comprising:
the determining module is used for receiving a product combination request, determining a target product and characteristic factors based on user preferences, and sending information of the target product and the characteristic factors to a plurality of slave node devices so that the slave node devices determine the correlation degree between the corresponding characteristic factors and each target product, wherein each slave node device corresponds to one characteristic factor; and determining a starting weight of each target product based on the correlation degree between each characteristic factor and each target product and the weight corresponding to each characteristic factor;
a receiving module, configured to receive the relevancy returned by the plurality of slave node devices;
and the sequencing module is used for sequencing the target products based on the initial weight of each target product and responding to the product combination request based on the product combination formed by the sequenced target products.
11. An electronic device, comprising:
a memory for storing executable instructions;
a processor for implementing the combination determination method of any one of claims 1 to 9 when executing executable instructions stored in the memory.
12. A computer-readable storage medium having stored thereon executable instructions for causing a processor to execute the combination determination method according to any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110552237.0A CN113159972A (en) | 2021-05-20 | 2021-05-20 | Combination determination method, combination determination device, electronic equipment and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110552237.0A CN113159972A (en) | 2021-05-20 | 2021-05-20 | Combination determination method, combination determination device, electronic equipment and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113159972A true CN113159972A (en) | 2021-07-23 |
Family
ID=76876780
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110552237.0A Pending CN113159972A (en) | 2021-05-20 | 2021-05-20 | Combination determination method, combination determination device, electronic equipment and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113159972A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11606446B1 (en) | 2021-09-13 | 2023-03-14 | International Business Machines Corporation | Microapplication composition |
| WO2023035849A1 (en) * | 2021-09-08 | 2023-03-16 | 富途网络科技(深圳)有限公司 | Investment portfolio management method and apparatus, storage medium, and terminal device |
| CN116739789A (en) * | 2023-08-16 | 2023-09-12 | 中信证券股份有限公司 | Virtual article return information sending method and device, electronic equipment and medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150317736A1 (en) * | 2012-04-27 | 2015-11-05 | Disi Lian | Methods and tools for guranteeing portfolio expected return while minimizing risks |
| CN107436866A (en) * | 2016-05-25 | 2017-12-05 | 阿里巴巴集团控股有限公司 | The recommendation method and device of finance product |
| CN109886788A (en) * | 2019-02-26 | 2019-06-14 | 湖南大学 | A kind of pleasantly surprised degree recommended method based on Weak link |
| CN110443715A (en) * | 2019-06-27 | 2019-11-12 | 平安科技（深圳）有限公司 | Fund Products Show method, apparatus, equipment and computer readable storage medium |
| CN110473040A (en) * | 2018-05-10 | 2019-11-19 | 北京三快在线科技有限公司 | A kind of Products Show method and device, electronic equipment |
| CN111581516A (en) * | 2020-05-11 | 2020-08-25 | 中国银行股份有限公司 | Investment product recommendation method and related device |
-
2021
- 2021-05-20 CN CN202110552237.0A patent/CN113159972A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150317736A1 (en) * | 2012-04-27 | 2015-11-05 | Disi Lian | Methods and tools for guranteeing portfolio expected return while minimizing risks |
| CN107436866A (en) * | 2016-05-25 | 2017-12-05 | 阿里巴巴集团控股有限公司 | The recommendation method and device of finance product |
| CN110473040A (en) * | 2018-05-10 | 2019-11-19 | 北京三快在线科技有限公司 | A kind of Products Show method and device, electronic equipment |
| CN109886788A (en) * | 2019-02-26 | 2019-06-14 | 湖南大学 | A kind of pleasantly surprised degree recommended method based on Weak link |
| CN110443715A (en) * | 2019-06-27 | 2019-11-12 | 平安科技（深圳）有限公司 | Fund Products Show method, apparatus, equipment and computer readable storage medium |
| CN111581516A (en) * | 2020-05-11 | 2020-08-25 | 中国银行股份有限公司 | Investment product recommendation method and related device |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023035849A1 (en) * | 2021-09-08 | 2023-03-16 | 富途网络科技(深圳)有限公司 | Investment portfolio management method and apparatus, storage medium, and terminal device |
| US11606446B1 (en) | 2021-09-13 | 2023-03-14 | International Business Machines Corporation | Microapplication composition |
| WO2023036180A1 (en) * | 2021-09-13 | 2023-03-16 | International Business Machines Corporation | Microapplication composition |
| CN116739789A (en) * | 2023-08-16 | 2023-09-12 | 中信证券股份有限公司 | Virtual article return information sending method and device, electronic equipment and medium |
| CN116739789B (en) * | 2023-08-16 | 2023-12-19 | 中信证券股份有限公司 | Virtual article return information sending method and device, electronic equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8930247B1 (en) | System and methods for content-based financial decision making support | |
| CN113159972A (en) | Combination determination method, combination determination device, electronic equipment and computer readable storage medium | |
| Bothos et al. | Using social media to predict future events with agent-based markets | |
| US20220012809A1 (en) | Data structures for transfer and processing of financial data | |
| CN107798607A (en) | Asset Allocation strategy acquisition methods, device, computer equipment and storage medium | |
| US11276120B2 (en) | Dashboard interface, platform, and environment for matching subscribers with subscription providers and presenting enhanced subscription provider performance metrics | |
| Xu | Linear and nonlinear causality between corn cash and futures prices | |
| US20080040250A1 (en) | System and Method for Analysing Risk Associated with an Investment Portfolio | |
| US8386396B2 (en) | Systems and methods for bidirectional matching | |
| CN101578618A (en) | Diamond valuation method, apparatus and computer readable medium product | |
| US20140258175A1 (en) | Generating Personalized Investment Recommendations | |
| US20190228015A1 (en) | Broker chat bot | |
| US20180144403A1 (en) | Select group crowdsource enabled system, method and analytical structure to perform securities valuations and valuation adjustments and generate derivatives thereform | |
| US11803927B2 (en) | Analysis of intellectual-property data in relation to products and services | |
| US20190073413A1 (en) | System and Method for Producing a Media Sentiment Based Index and Portfolio of Securities | |
| WO2007085055A1 (en) | A mass customisable interactive, multi-faceted system for data collection, processing, analysis, transmission, and trading in securities | |
| US20090319439A1 (en) | Determination of customized investing advice | |
| KR20120032606A (en) | Stock investment system enabling participattion of stock investment clients and method thereof | |
| Camilleri et al. | The determinants of securities trading activity: evidence from four European equity markets | |
| US20180225767A1 (en) | Investment management proposal system | |
| CN112862618A (en) | Bin adjustment prompting method and device, electronic equipment and storage medium | |
| US20210256611A1 (en) | Apparatus and method for generating and validating customized investment portfolios | |
| US20200294144A1 (en) | Method for initiating and hosting an auction for a security | |
| CN114943582A (en) | Information recommendation method and system and recommendation server | |
| JP2021168184A (en) | Source code trading system using AI |
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 |