User portrait-based matching strategy generation method and related device

Abstract

The application provides a user portrait-based matching strategy generation method and related device, and relates to the field of computers. First, a name list including a plurality of job personnel is acquired, and then job record data of each job personnel in a previous job cycle is acquired; then, a user portrait of each job personnel is determined based on the job record data; and a job object matching strategy is determined for each job personnel, the job object matching strategy corresponding to a job behavior type of the job personnel. Since the user portrait represents a job behavior type matched with the corresponding job personnel, the job behavior type reflects a preferred behavior feature, so that the recommended content using the job object matching strategy can be matched with the preferred behavior feature of the job personnel, and user experience is ensured.

Description

Technical Field

[0001] This invention relates to the field of computers, and more specifically, to a method and apparatus for generating matching strategies based on user profiles. Background Technology

[0002] Recommending products or services to users is a common practice. Currently, one recommendation method is for marketers to use a broad-based approach, or to make targeted recommendations based on user preferences derived from past behavior.

[0003] Another recommendation method is for the platform to make automated recommendations to users. In this case, how to accurately identify users with different behavioral preferences and then make personalized recommendations for users' tasks is a problem that needs to be considered. Summary of the Invention

[0004] The purpose of this invention is to provide a matching strategy generation method and related apparatus based on user profiles, so as to improve the problems existing in the prior art.

[0005] The embodiments of the present invention can be implemented as follows:

[0006] In a first aspect, the present invention provides a matching strategy generation method based on user profiles, comprising:

[0007] Obtain the user list; the user list includes several operational personnel;

[0008] Obtain the work record data of each worker in the previous work cycle;

[0009] A user profile is determined for each worker based on the job record data; the user profile represents the type of job behavior that matches the corresponding worker.

[0010] A task object matching strategy is determined for each worker; the task object matching strategy corresponds to the type of task behavior of the worker.

[0011] In an optional implementation, the job behavior type includes at least one of fundamental job operators, event-driven job operators, and technical job operators;

[0012] The term "fundamental analyst" refers to the analyst who selects target tasks based on a comprehensive analysis of each task; "event-driven analyst" refers to the analyst who selects target tasks based on the analysis of trending data within each task; and "technical analyst" refers to the analyst who selects target tasks based on the analysis of chart data of each task.

[0013] The step of determining the user profile of each worker based on the job record data includes:

[0014] Based on the job record data, identify the job personnel in the user list who belong to the fundamental job operator;

[0015] Based on the job record data, identify the job personnel in the user list who belong to the event-driven surface operator;

[0016] Remove the operators who belong to the fundamental surface operators and / or the event-driven surface operators from the user list to obtain the filtered user list;

[0017] Based on the job record data, it is determined that the filtered user list belongs to the technical staff of the operator.

[0018] In an optional implementation, the job record data includes at least one job record, which includes the job date and the job object;

[0019] The step of determining the personnel belonging to the fundamental operations operator in the user list based on the operation record data includes:

[0020] For each worker in the user list, obtain multiple feature factors of the work object in each work record corresponding to the worker at the time of its work date;

[0021] Based on the feature factors corresponding to each work date in the previous work cycle, calculate the feature mean value corresponding to each feature factor;

[0022] If at least one characteristic has a mean greater than a first set threshold, then the operator is determined to be a fundamental operator.

[0023] In an optional implementation, the job record data includes at least one job record, which includes the job date and the job object;

[0024] The step of determining the operators belonging to the event-driven surface operator in the user list based on the job record data includes:

[0025] For each worker's work record, obtain the quantity and price change characteristics of the work object in the work record for the next three days before the work date, the change characteristics of its own field, and other change characteristics of its field;

[0026] If the price and volume change characteristics, the change characteristics of the field itself, and other change characteristics of the field satisfy the own price and volume change conditions, the price and volume change conditions of the field, and the price and volume change conditions of other fields respectively, then the operation object of the operation record is determined to be an event-driven object.

[0027] If the proportion of job records in the job record data of the operator that belong to the event-driven object exceeds a preset proportion, then the operator is determined to be an event-driven surface operator.

[0028] In an optional implementation, the job record data includes at least one job record;

[0029] The step of determining, based on the job record data, that the filtered user list belongs to the technical staff includes:

[0030] For each worker in the filtered user list, the worker's work frequency is determined based on the number of work records and the number of work days in the previous work cycle.

[0031] If the work frequency is greater than the second set threshold, then the worker is determined to be a technical worker.

[0032] Secondly, the present invention provides a matching strategy generation apparatus based on user profiles, comprising:

[0033] The acquisition module is used for:

[0034] Obtain the user list; the user list includes several operational personnel;

[0035] Obtain the work record data of each worker in the previous work cycle;

[0036] Processing module, used for:

[0037] A user profile is determined for each worker based on the job record data; the user profile represents the type of job behavior that matches the corresponding worker.

[0038] A task object matching strategy is determined for each worker; the task object matching strategy corresponds to the type of task behavior of the worker.

[0039] In an optional implementation, the job behavior type includes at least one of fundamental job operators, event-driven job operators, and technical job operators;

[0040] The term "fundamental analyst" refers to the analyst who selects target tasks based on a comprehensive analysis of each task; "event-driven analyst" refers to the analyst who selects target tasks based on the analysis of trending data within each task; and "technical analyst" refers to the analyst who selects target tasks based on the analysis of chart data of each task.

[0041] When the processing module is used to determine the user profile of each worker based on the job record data, it is specifically used for:

[0042] Based on the job record data, identify the job personnel in the user list who belong to the fundamental job operator;

[0043] Based on the job record data, identify the job personnel in the user list who belong to the event-driven surface operator;

[0044] Remove the operators who belong to the fundamental surface operators and / or the event-driven surface operators from the user list to obtain the filtered user list;

[0045] Based on the job record data, it is determined that the filtered user list belongs to the technical staff of the operator.

[0046] In an optional implementation, the job record data includes at least one job record, which includes the job date and the job object;

[0047] The processing module, when determining the personnel belonging to the fundamental operations worker in the user list based on the job record data, is specifically used for:

[0048] For each worker in the user list, obtain multiple feature factors of the work object in each work record corresponding to the worker at the time of its work date;

[0049] Based on the feature factors corresponding to each work date in the previous work cycle, calculate the feature mean value corresponding to each feature factor;

[0050] If at least one characteristic has a mean greater than a first set threshold, then the operator is determined to be a fundamental operator.

[0051] Thirdly, the present invention provides an electronic device, comprising: a memory and a processor, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor executes the machine-readable instructions to implement the user profile-based matching strategy generation method as described in any of the foregoing embodiments.

[0052] Fourthly, the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the matching strategy generation method based on user profile as described in any of the foregoing embodiments.

[0053] Compared with existing technologies, this invention provides a method and related apparatus for generating matching strategies based on user profiles. First, a user list including several operators is obtained. Then, the operation record data of each operator in the previous operation cycle is obtained. Next, a user profile for each operator is determined based on the operation record data. Finally, an operation object matching strategy is determined for each operator, which corresponds to the operator's operation behavior type. This method can determine user profiles based on operators' operation record data. Since the user profile represents the operation behavior type that matches the corresponding operator, and the operation behavior type reflects preferred behavior characteristics, it ensures that the recommended content using the operation object matching strategy matches the operator's preferred behavior characteristics, thus guaranteeing a better user experience. Attached Figure Description

[0054] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0055] Figure 1 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.

[0056] Figure 2 This is one of the flowcharts illustrating a matching strategy generation method based on user profiles provided in an embodiment of the present invention.

[0057] Figure 3 This is a second flowchart illustrating a matching strategy generation method based on user profiles, provided in an embodiment of the present invention.

[0058] Figure 4 This is a schematic diagram of a matching strategy generation device based on user profiles, provided in an embodiment of the present invention. Detailed Implementation

[0059] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0060] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0061] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0062] It should be noted that, where there is no conflict, the features in the embodiments of the present invention can be combined with each other.

[0063] As described in the background section, recommending products or services to users is a common practice. Currently, one recommendation method is for marketers to use a broad-based approach, or to make targeted recommendations based on user preferences derived from past behavior.

[0064] Another recommendation method is for the platform to make automated recommendations to users. In this case, how to accurately identify users with different behavioral preferences and then make personalized recommendations for users' tasks is a problem that needs to be considered.

[0065] Taking the recommendation of products such as stocks and funds as an example, marketers usually use a broad approach to recommend products to users on the platform. However, this often results in products recommended to users that do not match their preferred behavioral characteristics, leading to a poor user experience.

[0066] Similarly, when recommending products or videos to users, if the same content is recommended to every user, the recommended content may not match the user's preferred behavior characteristics, resulting in a poor user experience.

[0067] Based on the discovery of the aforementioned technical problems, the inventors, through creative labor, proposed the following technical solutions to solve or improve these problems. It should be noted that the deficiencies in the solutions of the prior art are all results derived by the inventors after practical experience and careful research. Therefore, the discovery process of the aforementioned problems and the solutions proposed in the embodiments of this application below should be considered contributions made by the inventors to this application during the inventive process, and should not be construed as technical content known to those skilled in the art.

[0068] In view of this, embodiments of the present invention provide a matching strategy generation method based on user profiles, which can determine user profiles based on the work record data of operators. Since the user profile represents the type of work behavior that matches the corresponding operator, and the type of work behavior reflects the preferred behavior characteristics, this ensures that the recommended content using the work object matching strategy can match the preferred behavior characteristics of the operator, thus guaranteeing the user experience. The following detailed description is provided through embodiments and in conjunction with the accompanying drawings.

[0069] Please see Figure 1 , Figure 1 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. The electronic device 100 includes a processor 110, a memory 120, and a bus 130, with the processor 110 connected to the memory 120 via the bus 130.

[0070] The memory 120 can be used to store software programs and modules, such as the program instructions / modules corresponding to the user profile-based matching strategy generation apparatus 200 provided in the embodiments of the present invention. The processor 110 executes various functional applications and data processing by running the software programs and modules stored in the memory 120, such as the user profile-based matching strategy generation method provided in the embodiments of the present invention.

[0071] The memory 120 may be, but is not limited to, random access memory (RAM), read-only memory (ROM), flash memory, programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), etc.

[0072] The processor 110 can be an integrated circuit chip with signal processing capabilities. The processor 110 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0073] Optionally, the electronic device 100 may be, but is not limited to, a personal computer, a smartphone, a server, etc.

[0074] Understandable. Figure 1 The structure shown is for illustrative purposes only; the electronic device 100 may also include components that are more advanced than those shown. Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown. Figure 1 The components shown can be implemented using hardware, software, or a combination thereof.

[0075] Please refer to Figure 2 , Figure 2 This is a flowchart illustrating a user profile-based matching strategy generation method provided in an embodiment of the present invention. The execution subject of this method can be the aforementioned electronic device, and the method includes the following steps S100 to S400:

[0076] S100, Get the user list.

[0077] S200: Obtain the work record data of each operator in the previous work cycle.

[0078] In this embodiment, the user list includes several operators. The work cycle can be set according to the actual situation, for example, the work cycle can be set to one week, one month, one quarter, half a year, or one year.

[0079] S300: Determine the user profile of each operator based on work record data.

[0080] In this embodiment, the user profile can represent the type of work behavior that matches the corresponding operator, and the type of work behavior can reflect the operator's preferred behavior characteristics when performing the work.

[0081] S400. Determine the task object matching strategy for each operator. The task object matching strategy corresponds to the operator's task behavior type.

[0082] The matching strategy generation method based on user profiles provided in this invention can determine user profiles based on the work record data of the workers. Since the user profile represents the type of work behavior that matches the corresponding worker, and the type of work behavior reflects the preferred behavior characteristics, it can ensure that the recommended content using the work object matching strategy can match the preferred behavior characteristics of the workers, thus ensuring the user experience.

[0083] In one optional example, taking product recommendation as an example, the user list can first be obtained from the customer management system. Then, the online behavioral characteristic data (i.e., work record data) of each user (i.e., the operator) in the user list can be obtained from the customer management system. This online behavioral characteristic data can include the collection rate, like rate, forwarding rate, and order rate of all products viewed by the user in the previous time period (e.g., one week). Then, based on the online behavioral characteristic data, a user profile for each user is determined. Taking user A as an example, this process can include the following steps:

[0084] 1. For each product that user A browsed in the past week, find the product's tag features, which may include scenario type, sub-scenario tags, price range, positive review rate, etc.

[0085] 2. Calculate the value characteristic value of the product. This value characteristic value can be obtained by multiplying the collection rate, like rate, forwarding rate, and order rate and then normalizing them.

[0086] 3. Collect all products that user A viewed in the previous week with a value feature value greater than the threshold of 0.5 and form a product set; based on this product set, determine user A's preferred scenario type, sub-scenario tags, price range, positive review rate, etc., to obtain a user profile.

[0087] Thus, based on user A's user profile, a product recommendation strategy (i.e., job matching strategy) that matches user's preferred behavior characteristics can be determined.

[0088] It should be noted that the above example is merely one illustration and is not intended to be limiting.

[0089] In another alternative example, the job behavior type may include at least one of fundamental job, event-driven job, and technical job.

[0090] Among them, fundamental analysis operators select target targets based on a comprehensive analysis of each target; event-driven analysis operators select target targets based on the analysis of popular data in each target; and technical analysis operators select target targets based on the analysis of chart data of each target.

[0091] Correspondingly, please refer to Figure 3 The sub-steps of step S300 above may include S310 to S340.

[0092] S310. Based on the job record data, identify the job personnel in the user list who belong to the fundamental job operators.

[0093] In this embodiment, the job record data may include at least one job record, which may include the job date and the job object. In an optional example, sub-steps of S310 may include S311 to S313:

[0094] S311. For each operator in the user list, obtain multiple feature factors of the operation object on the operation date in each operation record corresponding to the operator.

[0095] It is understandable that for any characteristic factor of a certain work date, that characteristic factor can reflect a certain characteristic development of the work object on that work date, and all characteristic factors can jointly characterize the overall development of the work object on that work date.

[0096] S312. Based on the feature factors corresponding to each work date in the previous work cycle, calculate the feature mean value corresponding to each feature factor.

[0097] In this embodiment, for any one of the multiple feature factors, the feature mean corresponding to that feature factor can be calculated based on the sum of the feature factors corresponding to all job dates.

[0098] S313. If at least one feature has a mean value greater than the first set threshold, then the operator is determined to be a fundamental operator.

[0099] In an optional example, if there are 10 feature factors (feature factors K1 to K10), based on worker A's work record data, the mean values ​​of each of the 10 feature factors (feature means K1 to K10) can be calculated. If at least one feature mean (e.g., feature mean K5) is greater than a first set threshold, it indicates that the worker pays more attention to feature factor K5 corresponding to feature mean K5 when selecting work objects. Therefore, worker A can be determined to be a fundamental analyst. This way, all fundamental analysts in the user list can be identified.

[0100] Taking the stock and fund investment industry as an example, the aforementioned fundamental analysts, event-driven analysts, and technical analysts can be respectively identified as fundamental traders, event-driven traders, and technical traders. The type of operational behavior reflects the preferred behavioral characteristics of analysts when investing in stocks and / or funds.

[0101] In this example, the operators in the user list are investors who purchase funds or stocks. Correspondingly, the operation record data can be the investor's transaction record data, which may include stock transaction flow and / or fund transaction flow.

[0102] The job record data includes job records, which can refer to transaction records included in transaction record data. The job date and job object included in the job record can respectively correspond to the transaction date and the individual stock traded in the transaction record.

[0103] Optionally, the feature factor is the individual stock feature factor of the traded stock. The individual stock feature factor can include 8 individual stock factor feature values ​​and 4 industry feature values ​​of the individual stock, for a total of 12.

[0104] Individual stock factor characteristics may include: market risk premium, size factor, value factor, profitability factor, liquidity factor, rolling dividend yield factor, PEG, and revenue growth rate factor; individual stock industry characteristics may include: industry win rate, industry odds, industry crowding, and industry trend.

[0105] It's understandable that we can connect to a marketing big data platform to obtain the 12 stock characteristic factors for each traded stock in each transaction record for each operator on the corresponding transaction date. The definition or calculation method of the 12 stock characteristic factors is as follows:

[0106] 1. Market risk premium: The daily return of a traded stock minus the risk-free rate;

[0107] 2. Size factor: The logarithm of the daily market capitalization of all A-shares (including the STAR Market);

[0108] 3. Value Factor: The smaller of the price-to-book ratio (PB) and price-to-earnings ratio (PE) of a traded stock, i.e., min(price-to-book ratio PB, price-to-earnings ratio PE).

[0109] 4. Profitability Factors: The diluted ROE (Return On Equity) of the traded stock after deducting non-recurring gains and losses;

[0110] 5. Liquidity Factor: Average daily turnover rate (%) of individual stocks traded per month;

[0111] 6. Rolling Dividend Yield Factor: The daily rolling dividend yield factor of the traded stock;

[0112] 7. PEG ratio: refers to the ratio of a stock's price-to-earnings ratio to its earnings growth rate.

[0113] 8. Revenue Growth Rate: The revenue growth rate factor for individual stocks being traded;

[0114] 9. Winning probability by industry: The weighted average of the year-end valuation difference of the industry to which the traded stock belongs, the absolute value of the FY1 forecast growth rate, the marginal change of the FY1 forecast growth rate, and the factor of the marginal change of policy.

[0115] 10. Industry Odds: The weighting of factors such as industry crowding, valuation, and fund holdings in the industry to which the traded stock belongs;

[0116] 11. Industry Crowding: Weighting factors such as the overall industry sector, individual stock characteristics, and capital flow of the traded stock.

[0117] 12. Industry Trend: The information ratio of the industry to which the traded stock belongs over the past 12 months relative to the industry equal-weight index.

[0118] Assuming the work cycle is one month, taking the size factor and value factor among the above 12 stock characteristic factors as examples, the table below (1) shows the transaction time and stocks of each transaction record in the transaction record data of investor A within one month, as well as the size factor and value factor of each stock obtained.

[0119] Table (1)

[0120] 2010-01-04 0000001 0.64 0.32 2010-01-07 0000002 0.56 0.26 2010-01-08 0000003 0.89 0.45 2010-01-10 0000004 0.96 0.60 2010-01-13 0000005 0.24 0.23 2010-01-15 0000006 0.78 0.14 2010-01-18 0000007 0.69 0.09

[0121] In the table, the transaction time is for illustrative purposes only, and the stock codes are listed below each traded stock. Based on the table content, the characteristic mean corresponding to the size factor can be calculated:

[0122] (0.64+0.56+0.89+0.96+0.24+0.78+0.69) / 7=0.68

[0123] Calculate the mean of the features corresponding to the value factors:

[0124] (0.32+0.26+0.45+0.60+0.23+0.14+0.09) / 7=0.29

[0125] The first threshold can be set to 0.5. If there is a feature mean of 0.68 > 0.5, it means that investor A pays more attention to various factors of the fundamental characteristics of individual stocks when choosing investment targets. Therefore, investor A can be judged to be a fundamental trader.

[0126] It should be noted that the above examples only illustrate the method for calculating the characteristic mean of the size factor and value factor. The method for determining the characteristic mean of the other 10 individual stock characteristic factors is similar and will not be elaborated here. Furthermore, the above examples are merely illustrations, and the specific application shall prevail, without limitation.

[0127] S320. Based on the job record data, identify the operators in the user list who belong to the event-driven surface operators.

[0128] In an optional example, the sub-steps of S320 may include S321 to S323:

[0129] S321. For each work record of each worker, obtain the quantity and price change characteristics of the work object in the work record for the next three days before the work date, the change characteristics of its own field, and other change characteristics of its field.

[0130] Based on the above examples, for any work record (i.e., transaction record) of worker A (i.e., investor A), the volume and price change characteristics, the characteristic value of the sector itself, and other characteristic values ​​of the sector for the work object in the work record over the three days following the work date are respectively: the volume and price change characteristics, the characteristic value of the concept sector itself, and other characteristic values ​​of the concept sector for the individual stock traded in the transaction record over the three days following the transaction date. The meanings of these three characteristic values ​​are as follows:

[0131] 1. Individual stock volume and price change characteristics: The sum of the price changes of the traded stock over the next three days.

[0132] 2. Change characteristics of the concept sector to which the stock belongs: The increase of the concept sector to which the stock belongs in the next three days.

[0133] 3. Other changing characteristics of the concept sector: The ratio of the number of stocks that are rising to the number of stocks that are falling in the same concept sector as the traded stock.

[0134] It should be noted that "the next three days" is a relative concept, referring to the three days leading up to the transaction date.

[0135] S322. If the characteristics of price and volume changes, the characteristics of changes in the field itself, and the characteristics of other changes in the field satisfy the conditions for price and volume changes of the field itself, the conditions for price and volume changes of the field itself, and the conditions for price and volume changes of other changes in the field, then the operation object of the operation record is determined to be an event-driven object.

[0136] In this embodiment, an event-driven object can represent a job object that belongs to the current hot topic concept.

[0137] Following the examples above, the condition for a stock's own price fluctuation can be that its volume and price change characteristic value is greater than or equal to 21%; the condition for the price fluctuation of its sector can be that the characteristic value of the sector itself is greater than or equal to 5%; and the condition for other price fluctuations in its sector can be that other characteristic values ​​of the sector are greater than 1.

[0138] Event-driven objects can represent event-driven stock pools, which can include multiple stocks corresponding to various current hot concepts.

[0139] If the stock (stock code 0001052) traded in a transaction record of investor A satisfies the following characteristics: the stock's price and volume change characteristics, the characteristic value of its own concept sector, and other characteristic values ​​of its own concept sector, the condition of its own price and volume change, the condition of its own sector price and volume change, and the condition of other price and volume change in its own sector, then it means that the stock (stock code 0001052) belongs to the event-driven stock pool.

[0140] S323. If the proportion of work records in the work record data of the operator that are event-driven objects exceeds the preset proportion, then the operator is determined to be an event-driven surface operator.

[0141] In this embodiment, the preset percentage can be set according to the actual application situation. For example, the preset percentage can be set to 0.5.

[0142] Continuing the example above, assuming a preset percentage of 0.5, investor A's trading records include 10 trading records, each involving a different stock. If half of these 10 stocks belong to the event-driven stock pool, it indicates that investor A pays close attention to current hot concepts when selecting stocks for investment, thus classifying investor A as an event-driven trader.

[0143] S330. Remove the operators who are fundamental and / or event-driven operators from the user list to obtain the filtered user list.

[0144] S340. Based on the work record data, determine the personnel who belong to the technical side of the user list after screening.

[0145] In an optional example, the sub-steps of step S340 may include S341 to S342:

[0146] S341. For each operator in the filtered user list, determine the operator's work frequency based on the number of operator's work records and the number of work days in the previous work cycle.

[0147] S342. If the work frequency is greater than the second set threshold, the worker is determined to be a technical worker.

[0148] In this embodiment, the number of workdays in the previous work cycle can be the number of working days in the work cycle, and the second set threshold is based on the actual setting. The work frequency can be the ratio of the number of work records to the number of workdays.

[0149] For example, when the work cycle is one month, the number of work days can be 21; when the work cycle is one week, the number of work days can be 5; the second threshold can be 0.5. It should be understood that this example is merely illustrative and is not intended to be limiting.

[0150] Following the example above, the frequency of operations of the workers is the same as the trading frequency of the investors.

[0151] In the optional example, for investor B, if his trading record data includes 15 trading records, that is, the number of trading records is 15, and assuming the operation cycle is one month, that is, the number of operation days is 21, the second set threshold can be 0.5, the trading frequency of investor B = 15 / 21≈0.714. Since 0.714>0.5, then investor B can be determined to be a technical trader.

[0152] Through the aforementioned steps S300 and their sub-steps, the user profile of each investor in the user list can be determined. It can be understood that the investor's user profile and its target matching strategy can be stored in the marketing big data platform's database, providing data support for subsequent personalized recommendations.

[0153] In an optional implementation, the sub-steps of step S400 above may include:

[0154] For each operator in the user list, the corresponding job matching strategy is determined based on the operator's user profile.

[0155] Continuing with the previous example, for investor C in the user list, the user profile could exist as follows:

[0156] Scenario 1: The user profile indicates that Investor C is a fundamental trader. In this case, the target audience matching strategy for Investor C would be to recommend a fundamental strategy fund portfolio service to Investor C.

[0157] Scenario 2: The user profile indicates that Investor C is an event-driven trader. In this case, the target audience matching strategy for Investor C would be to recommend an event-driven strategy fund portfolio service to Investor C.

[0158] Scenario 3: The user profile indicates that Investor C is both a fundamental trader and an event-driven trader. In this case, the matching strategy for Investor C would be to recommend both fundamental strategy fund portfolio services and event-driven strategy fund portfolio services to Investor C.

[0159] Scenario 3: The user profile indicates that Investor C is a technical trader. In this case, the target audience matching strategy for Investor C would be to recommend a technical strategy fund portfolio service to Investor C.

[0160] It is understandable that, in the user profile, if an investor does not belong to any of the categories of fundamental trader, event-driven trader, or technical trader, then the system's default recommendation strategy will be applied to that investor.

[0161] It should be noted that the execution order of each step in the above method embodiments is not limited to that shown in the attached figures, and the execution order of each step shall be subject to the actual application situation.

[0162] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0163] This solution can determine a user profile for each investor based on their transaction history data, and then determine a personalized investment strategy for each investor based on that user profile. This enables personalized recommendations of investment products and services such as funds and stocks to investors based on their individual user profiles.

[0164] In order to perform the corresponding steps in the above method embodiments and various possible implementations, an implementation method of a matching strategy generation device based on user profiles is given below.

[0165] Please see Figure 4 , Figure 4 A schematic diagram of a user profile-based matching strategy generation device 200 provided in an embodiment of the present invention is shown. The user profile-based matching strategy generation device 200 includes an acquisition module 210 and a processing module 220.

[0166] Module 210 is used to: obtain a user list; the user list includes several operators; and obtain the operation record data of each operator in the previous operation cycle.

[0167] The processing module 220 is used to: determine the user profile of each operator based on the job record data; the user profile represents the job behavior type that matches the corresponding operator; determine the job object matching strategy for each operator; and the job object matching strategy corresponds to the job behavior type of the operator.

[0168] In optional implementations, the job behavior type includes at least one of fundamental job operators, event-driven job operators, and technical job operators; fundamental job operators represent job operators who select target job objects based on a comprehensive analysis of each job object; event-driven job operators represent job operators who select target job objects based on the analysis of popular data in each job object; and technical job operators represent job operators who select target job objects based on the analysis of chart data of each job object.

[0169] When processing module 220 determines the user profile of each operator based on job record data, it can specifically be used to: determine the operators in the user list who belong to the fundamental operations category based on job record data; determine the operators in the user list who belong to the event-driven operations category based on job record data; remove the operators in the user list who belong to the fundamental operations category and / or the event-driven operations category to obtain a filtered user list; and determine the operators in the filtered user list who belong to the technical operations category based on job record data.

[0170] In an optional implementation, the job record data includes at least one job record, which includes the job date and the job object; the processing module 220, when determining the personnel belonging to the basic operations team in the user list based on the job record data, can specifically be used for:

[0171] For each worker in the user list, obtain multiple feature factors of the work object in each work record corresponding to the worker at the time of its work date; calculate the feature mean corresponding to each feature factor based on the feature factors corresponding to each work date in the previous work cycle; if there is at least one feature mean greater than the first set threshold, then determine that the worker belongs to the fundamentals worker.

[0172] In an optional implementation, the job record data includes at least one job record, which includes the job date and the job object; the processing module 220, when determining the operators belonging to the event-driven surface operator in the user list based on the job record data, can specifically be used for:

[0173] For each worker's work record, obtain the quantity and price change characteristics, the characteristic value of its own domain, and other characteristic values ​​of its domain for the three days leading up to the work date. If the quantity and price change characteristics, the characteristic value of its own domain, and the characteristic value of other characteristics of its domain satisfy its own rise and fall conditions, the rise and fall conditions of its domain, and the rise and fall conditions of other domains, respectively, then the work object in the work record is determined to be an event-driven object. If the proportion of work records in the worker's work record data that the work object belongs to the event-driven object exceeds the preset proportion, then the worker is determined to be an event-driven surface worker.

[0174] In an optional implementation, the job record data includes at least one job record; the processing module 220 is used to determine, based on the job record data, that the selected user list belongs to the technical staff, specifically: for each staff member in the selected user list, based on the number of the staff member's job records and the number of work days in the previous work cycle, determine the staff member's work frequency; if the work frequency is greater than a second set threshold, then determine that the staff member belongs to the technical staff.

[0175] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the user profile-based matching strategy generation device 200 described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0176] This invention also provides a computer-readable storage medium storing a computer program. When executed by a processor, this computer program implements the user profile-based matching strategy generation method disclosed in the above embodiments. The computer-readable storage medium can be, but is not limited to, various media capable of storing program code, such as a USB flash drive, external hard drive, ROM, RAM, PROM, EPROM, EEPROM, FLASH disk, or optical disk.

[0177] In summary, this invention provides a method and related apparatus for generating matching strategies based on user profiles. First, a user list including several operators is obtained. Then, the operation record data of each operator in the previous operation cycle is obtained. Next, a user profile for each operator is determined based on the operation record data. Finally, an operation object matching strategy is determined for each operator, and this strategy corresponds to the operator's operation behavior type. This method enables the determination of user profiles based on operator operation record data. Since the user profile represents the operation behavior type that matches the corresponding operator, and the operation behavior type reflects preferred behavior characteristics, it ensures that the recommended content using the operation object matching strategy matches the operator's preferred behavior characteristics, thus guaranteeing a better user experience.

[0178] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A matching strategy generation method based on user profiles, characterized in that, include: Obtain the user list; the user list includes several operational personnel; Obtain the work record data of each worker in the previous work cycle; A user profile is determined for each worker based on the job record data; the user profile represents the type of job behavior that matches the corresponding worker. A task object matching strategy is determined for each worker; the task object matching strategy corresponds to the type of task behavior of each worker. The job record data includes at least one job record, which includes the job date and the job object; the job behavior type includes at least one of fundamental analyst, event-driven analyst, and technical analyst; the fundamental analyst type indicates that the analyst selects the target job object based on a comprehensive analysis of each job object; the event-driven analyst type indicates that the analyst selects the target job object based on the analysis of popular data in each job object; the technical analyst type indicates that the analyst selects the target job object based on the analysis of chart data of each job object. The step of determining the user profile of each worker based on the job record data includes: For each worker in the user list, obtain multiple feature factors of the work object in each work record corresponding to the worker at the time of its work date; calculate the feature mean corresponding to each feature factor based on the feature factors corresponding to each work date in the previous work cycle; if there is at least one feature mean greater than a first set threshold, then determine that the worker belongs to the fundamentals worker. For each worker's work record, obtain the quantity and price change characteristics, the characteristic value of its own domain, and other characteristic values ​​of its domain for the three days following the work date. If the quantity and price change characteristics, the characteristic value of its own domain, and the other characteristic values ​​of its domain satisfy its own rise and fall conditions, the rise and fall conditions of its domain, and the other rise and fall conditions of its domain, respectively, then determine that the work object in the work record belongs to the event-driven type. If the proportion of work records in the worker's work record data where the work object belongs to the event-driven type exceeds a preset proportion, then determine that the worker belongs to the event-driven type worker. Remove the operators who belong to the fundamental surface operators and / or the event-driven surface operators from the user list to obtain the filtered user list; For each worker in the filtered user list, the worker's work frequency is determined based on the number of work records and the number of work days in the previous work cycle; if the work frequency is greater than a second set threshold, the worker is determined to be a technical worker.

2. A matching strategy generation device based on user profiles, characterized in that, include: The acquisition module is used for: Obtain the user list; the user list includes several operational personnel; Obtain the work record data of each worker in the previous work cycle; Processing module, used for: A user profile is determined for each worker based on the job record data; the user profile represents the type of job behavior that matches the corresponding worker. A task object matching strategy is determined for each worker; the task object matching strategy corresponds to the type of task behavior of each worker. The job record data includes at least one job record, which includes the job date and the job object; the job behavior type includes at least one of fundamental analyst, event-driven analyst, and technical analyst. The term "fundamental analyst" refers to the analyst who selects target tasks based on a comprehensive analysis of each task; "event-driven analyst" refers to the analyst who selects target tasks based on the analysis of trending data within each task; and "technical analyst" refers to the analyst who selects target tasks based on the analysis of chart data of each task. When the processing module is used to determine the user profile of each worker based on the job record data, it is specifically used for: For each worker in the user list, obtain multiple feature factors of the work object in each work record corresponding to the worker at the time of its work date; calculate the feature mean corresponding to each feature factor based on the feature factors corresponding to each work date in the previous work cycle; if there is at least one feature mean greater than a first set threshold, then determine that the worker belongs to the fundamentals worker. For each worker's work record, obtain the quantity and price change characteristics, the characteristic value of its own domain, and other characteristic values ​​of its domain for the three days following the work date. If the quantity and price change characteristics, the characteristic value of its own domain, and the other characteristic values ​​of its domain satisfy its own rise and fall conditions, the rise and fall conditions of its domain, and the other rise and fall conditions of its domain, respectively, then determine that the work object in the work record belongs to the event-driven type. If the proportion of work records in the worker's work record data where the work object belongs to the event-driven type exceeds a preset proportion, then determine that the worker belongs to the event-driven type worker. Remove the operators who belong to the fundamental surface operators and / or the event-driven surface operators from the user list to obtain the filtered user list; For each worker in the filtered user list, the worker's work frequency is determined based on the number of work records and the number of work days in the previous work cycle; if the work frequency is greater than a second set threshold, the worker is determined to be a technical worker.

3. An electronic device, characterized in that, include: The electronic device includes a memory and a processor, wherein the memory stores machine-readable instructions executable by the processor, and the processor executes the machine-readable instructions to implement the user profile-based matching strategy generation method as described in claim 1 when the electronic device is running.

4. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the matching strategy generation method based on user profiles as described in claim 1.

Images