Cache data processing method for intelligently analyzing operation habits of investment users

Abstract

The invention discloses a cache data processing method for intelligently analyzing operation habits of investment users, and relates to the technical field of cache data processing. The method comprises the following steps: acquiring basic information of a user; detecting whether the user basic information exists or not; if yes, reading matched user data according to the user basic information, and analyzing the user data to generate a user caching strategy; and if not, constructing a user fuzzy portrait through the user basic information, then performing similarity query through the user fuzzy portrait and historical user data to obtain user data with the highest similarity, and generating a user emergency caching strategy according to the user data with the highest similarity. According to the cache data processing method provided by the invention, the initial use experience of a new user can be effectively improved, and the cache data can be fully optimized by collecting and utilizing the user data, so that an intelligent investment service is provided for the user.

Description

Technical Field

[0001] The present invention relates to the technical field of cache data processing, and in particular to a cache data processing method for intelligently analyzing the operating habits of investment users. Background Art

[0002] In the investment field, understanding the user's operating habits is crucial to providing intelligent services and optimizing investment strategies. For example, collecting user data from the cloud or big data, or directly collecting user operation logs, but these prerequisites require data collection and mining of users. When new users register and use, it is difficult to quickly develop a cache strategy suitable for their operations. They can only slowly collect their data and optimize the cache data, which makes it impossible to quickly provide more accurate services. While increasing the cache space occupied by useless data, it is also easy to increase user churn. At the same time, if a large amount of stored user operation data is not effectively cached and effectively applied, it will also lead to a certain degree of data waste, which will not only reduce data reading efficiency, but also affect the user operation experience. Summary of the invention

[0003] The purpose of the present invention is to provide a cache data processing method, device, equipment and medium for intelligently analyzing the operating habits of investment users, so as to solve the problems raised in the above-mentioned background technology.

[0004] To achieve the above object, the present invention provides the following technical solution: a cache data processing method for intelligently analyzing the operation habits of investment users, comprising the following steps: Get basic user information; Detecting whether the basic user information already exists; If yes, read the matching user data according to the user basic information, and generate a user cache strategy by analyzing the user data; If not, construct a user fuzzy portrait through the user basic information, and then perform a similarity query between the user fuzzy portrait and the historical user data to obtain the user data with the highest similarity, and generate a user emergency cache strategy based on the user data with the highest similarity; execute the user emergency cache strategy; further obtain the user data of the new user, and generate a user cache strategy for the new user based on the user data of the new user, and optionally replace the user emergency cache strategy; Feedback is continuously obtained to continuously update the user cache strategy that has been executed.

[0005] Preferably, reading the matching user data according to the user basic information and generating a user cache strategy by analyzing the user data includes: Search the existing database to obtain user data matching the basic user information; Implant cache strategy generation model; Input the user data, and analyze the user data using the cache strategy generation model; The cache strategy generation model outputs a user cache strategy that matches the user data.

[0006] Preferably, the implantation cache strategy generation model includes: Build models through machine learning algorithms; Acquire historical user data and generate a data set, which includes a training set for model training, a validation set for model selection and parameter adjustment, and a test set for evaluating model capabilities; The model is trained, verified, adjusted and evaluated using the data set to confirm the model's cache strategy output capability; After confirmation, the output cache strategy generates a model and deploys it.

[0007] Preferably, the method of constructing a user fuzzy portrait through the user basic information, and then performing a similarity query between the user fuzzy portrait and historical user data to obtain the user data with the highest similarity, and generating a user emergency cache strategy according to the user data with the highest similarity, further includes: Traverse the database to obtain existing user data; Analyze the existing user data and build historical user portraits in sequence; Generate a historical user portrait set and store the historical user portraits.

[0008] Preferably, the step of constructing a user fuzzy portrait through the user basic information, then performing a similarity query between the user fuzzy portrait and historical user data to obtain the user data with the highest similarity, and generating a user emergency cache strategy based on the user data with the highest similarity includes: Analyze user basic information and build user fuzzy portrait; Performing a similarity query between the user fuzzy portrait and the historical user portrait in the historical user portrait set; Get similarity query results and select the historical user portrait with the highest similarity; Search the database according to the historical user portrait with the highest similarity to obtain corresponding historical user data; The historical user data is analyzed by using a deployed cache strategy generation model, and a user emergency cache strategy for emergency use by new users is generated.

[0009] Preferably, the acquiring of user data of the new user, generating a user cache strategy for the new user according to the user data of the new user, and optionally replacing the user emergency cache strategy includes: Continue to try to obtain extended data of new users through user preference testing, user usage feedback, user operation data and big data retrieval; Continuously updating the basic user information and user data of the new user according to the extended data; Analyze the updated user basic information and user data to obtain an updated user fuzzy portrait; Setting a first threshold and a second threshold for portrait upgrade, and detecting the total update degree of the user's fuzzy portrait; If the total update degree of the user fuzzy portrait does not exceed the first threshold, continue to obtain the extended data of the new user and wait for the next update of the user fuzzy portrait; If the total update degree of the user fuzzy portrait exceeds the first threshold, a similarity query is performed again with the historical user portrait in the historical user portrait set, and corresponding historical user data is obtained according to the similarity query result, and then the newly obtained historical user data is analyzed by the cache strategy generation model, and a new user emergency cache strategy is generated, and then user feedback is waited for, and the new user emergency cache strategy is optionally replaced; If the total update degree of the user fuzzy portrait exceeds the second threshold, the updated user basic information corresponding to the user fuzzy portrait is archived and stored, and the updated user basic information is analyzed by the cache strategy generation model, and a new user cache strategy is generated, and then user feedback is waited for, and the new user cache strategy is optionally replaced.

[0010] Preferably, the continuously obtaining feedback and continuously updating the executed user cache strategy includes: When the user cache strategy is executed, the user's operation data and user's usage feedback are continuously collected; The user data is updated according to the user's operation data and the user's usage feedback, and the user cache strategy is updated through the cache strategy generation model; Evaluate the updated user cache strategy and set optimization thresholds; If the updated user cache policy evaluation exceeds the optimization threshold, the executed user cache policy is optimized and updated; otherwise, the cache policy generation model is continued to wait for the next update of the user cache policy.

[0011] The present invention also provides a cache data processing device for intelligently analyzing the operating habits of investment users, comprising: Information acquisition module, which is used to obtain basic user information; An information search module, which is used to detect whether the basic user information already exists; A strategy generation module, which is used to read matching user data according to the user basic information and generate a user cache strategy by analyzing the user data; The strategy generation module is further used to construct a user fuzzy portrait through the user basic information, and then perform a similarity query between the user fuzzy portrait and historical user data to obtain the user data with the highest similarity, and generate a user emergency cache strategy based on the user data with the highest similarity; execute the user emergency cache strategy; further obtain user data of a new user, and generate a user cache strategy for the new user based on the user data of the new user, and optionally replace the user emergency cache strategy; A policy update module is used to continuously update the executed user cache policy.

[0012] The present invention further provides an electronic device, wherein the electronic device is a physical device, and the electronic device comprises: A processor and a memory, wherein the memory is communicatively connected to the processor; The memory is used to store at least one executable instruction executed by the processor, and the processor is used to execute the executable instruction to implement the cache data processing method for intelligently analyzing the operating habits of investment users as mentioned above.

[0013] The present invention also provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the cache data processing method for intelligently analyzing the operating habits of investment users as described above is implemented.

[0014] Compared with the prior art, the present invention has the following beneficial effects: After collecting basic user information and before obtaining user data, by generating a fuzzy portrait and comparing it with existing user information, the most similar user data is selected to generate a user emergency caching strategy for new users to use. This can quickly guess the user's operating preferences and generate strategies, thereby satisfying the user's operating preferences to a certain extent and reducing user churn. At the same time, through subsequent data collection, the executed strategies can be updated to make the caching strategy more in line with the user's operating preferences, reduce invalid caching operations, optimize the user's operating experience, and provide users with intelligent investment services. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1A main flow chart of a cache data processing method for intelligently analyzing investment user operation habits provided by an embodiment of the present invention; Figure 2 A flowchart of a method for generating a user cache strategy provided by an embodiment of the present invention; Figure 3 A flowchart of a method for generating a user emergency cache strategy provided by an embodiment of the present invention; Figure 4 A flowchart of another method for generating a user cache strategy provided by an embodiment of the present invention; Figure 5 A schematic diagram of the structure of a cache data processing device for intelligently analyzing the operating habits of investment users provided by an embodiment of the present invention; Figure 6 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0017] The execution subject of the method of this embodiment is a terminal, which can be a mobile phone, tablet computer, PDA, notebook or desktop computer, etc. Of course, it can also be other devices with similar functions, which is not limited in this embodiment.

[0018] See also Figures 1 to 4 The present invention provides a cache data processing method for intelligently analyzing the operating habits of investment users. The method is applied to cache data processing and optimization when a user uses an investment platform for the first time or multiple times, and includes: Step 100, obtaining basic user information.

[0019] The basic user information includes the information entered by the user when registering or logging in.

[0020] Specifically, when registering or logging in, the user needs to enter his or her account number, user name, name, age, gender, occupation and other basic information. After the user completes the registration or login operation, the next step of information search operation can be carried out by obtaining this information to determine whether the user is a new user or an old user.

[0021] Step 200 , detect whether the basic user information already exists, if so, execute step 210 , otherwise jump to step 220 .

[0022] Specifically, the basic information of registered users is usually stored in an encrypted form, which may be cloud storage or local storage. After the basic information of users reaches a certain standard or completeness, it is stored in a separate file in the database. And usually stored together with the basic information of registered users is the user data of registered users, including their transaction records, query records, access records and other related operation data, and some of the stored content can be updated based on the latest operation data of the users obtained.

[0023] Optionally, when detecting whether the basic user information exists, in order to improve the response speed, it is usually necessary to search only all or part of the basic user information without searching the user data.

[0024] It should be noted that usually the login operation is performed by old users, and the registration operation is performed by new users. However, it is not ruled out that the basic user information of registered users is quite scarce and is not stored in separate files. Since the designated database stores basic user information and related user data that can generate user caching strategies independently, their basic information is not in the database and they are treated as new customers. Similarly, newly registered users may not be completely new users. They may just have different user names or account numbers, and other basic information is stored. Therefore, by searching for their basic information in the database, they can be judged as old users, and this provides a data basis for the subsequent generation of user caching strategies.

[0025] Wherein, the 200 also includes: Step 210: Read matching user data according to the user basic information, and generate a user cache strategy by analyzing the user data.

[0026] Specifically, the user data includes transaction records, query records, access records and other related operation data. Therefore, when generating a user caching strategy, user data is the main reference item. Knowing the user's investment and operation preferences can more accurately generate and iteratively optimize the cache strategy plan based on their preferences.

[0027] Among them, Figure 2 As shown, the step 210 also includes: Step 211, searching an existing database to obtain user data matching the basic user information; Step 212, implanting a cache strategy generation model; Step 213, input the user data, and analyze the user data using the cache strategy generation model; Step 214: the cache strategy generation model outputs a user cache strategy that matches the user data.

[0028] It is understandable that when it is confirmed that the basic information of the user exists, it indicates that the user is an old user, and then the stored user data can be analyzed to generate a cache strategy model.

[0029] Wherein, the step 212 further includes: Step 2121, building a model through a machine learning algorithm; Step 2122, obtaining historical user data and generating a data set, wherein the data set includes a training set for model training, a validation set for model selection and parameter adjustment, and a test set for evaluating model capabilities; Step 2123, using the data set to train, verify, adjust and evaluate the model to confirm the cache strategy output capability of the model; Step 2124, after confirmation, the cache strategy generation model is output and deployed.

[0030] Among them, in step 2121, the machine learning algorithm can be a decision tree algorithm, a support vector machine (SVM) algorithm, a K nearest neighbor (KNN) algorithm, a clustering algorithm or a random forest algorithm. For example, the random forest algorithm can classify the user's operation data and mine the features corresponding to different operation habits; the random forest algorithm can improve the accuracy of classification and prediction through the combination of multiple decision trees, and is suitable for analyzing complex user operation habits; the support vector machine (SVM) algorithm can be used to classify user behavior, and has good processing capabilities for high-dimensional data; the K nearest neighbor (KNN) algorithm can classify user operation data according to the similarity with other user data to determine the user's operation habit type; clustering algorithms, such as K-Means clustering, can cluster users with similar operation habits into one category, so as to better understand the behavior patterns of user groups. Which machine learning algorithm is used depends on the actual application situation and is not specifically limited in this embodiment.

[0031] Step 220, construct a user fuzzy portrait through the user basic information, then perform a similarity query between the user fuzzy portrait and historical user data to obtain the user data with the highest similarity, and generate a user emergency cache strategy based on the user data with the highest similarity; execute the user emergency cache strategy; further obtain the user data of the new user, and generate a user cache strategy for the new user based on the user data of the new user, and optionally replace the user emergency cache strategy.

[0032] Understandably, the user fuzzy portrait constructed by judging based on basic information such as name, age, gender, and occupation is not accurate enough. Because there is less information, it is impossible to accurately judge the user's investment tendency, and thus it is impossible to accurately judge which operations the user tends to perform or which windows or software to use when performing operations. Therefore, it is impossible to directly generate a cache strategy. However, by analyzing the types of user fuzzy portraits, such as young and aggressive, middle-aged and stable, or elderly and conservative, and specific occupational preferences, it is possible to analyze whether it is similar to the basic user information already in the database, and further detect the old user with the highest similarity, and generate a user emergency cache strategy through the user data of the old user for emergency use by new users, thereby achieving the effect of quickly guessing the user's operation preference and generating a strategy.

[0033] It should be noted that after the user emergency caching strategy is executed, it is necessary to obtain the user data of the new user as soon as possible and generate a new user caching strategy for replacement, so as to more accurately respond to the operation preferences of the new user and reduce the user churn rate.

[0034] Specifically, before step 220 is implemented, the following steps are also included: Step S1, traverse the database to obtain existing user data; Step S2, analyzing the existing user data and sequentially constructing historical user portraits; Step S3, generating a historical user portrait set and storing the historical user portraits.

[0035] It can be understood that this database is used solely to store the basic user information database of users who have met the policy generation conditions or have generated user cache policies. It is also used to store user data, including access records, operation logs and other related operation data. Since most of these data have already generated user cache policies, the subsequent use process may increase the policy generation speed when the policy is generated again through these data. It is also possible to directly apply the generated user cache policy according to the actual situation and replace it with the user emergency cache policy used by the new user, such as when hardware resources are limited or the model is also performing other tasks at the same time.

[0036] like Figure 3 As shown, step 220 includes: Step 2201, analyzing the basic information of the user and constructing a fuzzy profile of the user; Step 2202, performing a similarity query between the user fuzzy portrait and the historical user portrait in the historical user portrait set; Step 2203, obtaining similarity query results, and selecting the historical user portrait with the highest similarity; Step 2204, searching the database according to the historical user portrait with the highest similarity to obtain corresponding historical user data; Step 2205, analyzing the historical user data through the deployed cache strategy generation model, and generating a user emergency cache strategy for emergency use by new users; Step 2206, execute the user emergency cache strategy.

[0037] like Figure 4 As shown, the step 220 also includes: Step 2207, continuously trying to obtain extended data of new users through user preference testing, user usage feedback, user operation data, and big data retrieval; Step 2208, continuously updating the basic user information and user data of the new user according to the extended data; Step 2209, analyzing the updated user basic information and user data to obtain an updated user fuzzy portrait; Step 2210, setting a first threshold and a second threshold for portrait upgrade, Step 2211, detecting the total update degree of the user's fuzzy portrait; If the total update degree of the user fuzzy portrait does not exceed the first threshold, return to step 2207, continue to obtain extended data, and wait for the next update of the user fuzzy portrait; If the total update degree of the user blurred portrait exceeds the first threshold and does not exceed the second threshold, executing step 2212; If the total update degree of the user fuzzy portrait exceeds the second threshold, executing step 2213; Step 2212, re-query the similarity with the historical user portrait in the historical user portrait set, and obtain the corresponding historical user data according to the similarity query result, and then analyze the newly obtained historical user data through the cache strategy generation model, and generate a new user emergency cache strategy, and then send and wait for user feedback, and optionally replace the new user emergency cache strategy; Step 2213, the updated user basic information corresponding to the user fuzzy portrait is archived and stored, and the updated user basic information is analyzed through the cache strategy generation model, and a new user cache strategy is generated, which is then sent and waited for user feedback, and the new user cache strategy is optionally replaced.

[0038] It can be understood that the first threshold and the second threshold are used to determine the update degree of the basic user information and user data of the new user. If the updated data is small and it is difficult to support the model to generate a more accurate user cache strategy for it, the user fuzzy profile of the new user can be updated and improved, and the updated user fuzzy profile can be used to determine whether there is a more similar historical user profile, and the stored user data can be used to regenerate a user emergency cache strategy that is more in line with the new user's operating habits for optional replacement; If there is a lot of updated data and the total update degree has reached the second threshold, it means that the data collected by the new user has met the minimum requirements of the model for generating a separate strategy for it. In this case, it can be archived and stored separately, and a user cache strategy that can be continuously updated can be generated.

[0039] Wherein, after step 2212, the method further includes: Get user feedback. If the user chooses to replace, execute step 22121. Otherwise, jump to step 22122. Step 22121, replacing the user emergency cache policy being executed with a new user emergency cache policy; Step 22122, store the new user emergency cache strategy, wait for the user to reselect, or wait for the total update degree of the user fuzzy portrait to exceed the second threshold.

[0040] After step 2213, the following steps are also included: Get user feedback. If the user chooses to replace, execute step 22131. Otherwise, jump to step 22132. Step 22131, replacing the currently executed user emergency cache policy with a new user cache policy; Step 22132, store the new user cache policy and wait for the user to reselect.

[0041] Understandably, the user can choose to replace the policy being executed, or choose not to replace it if he feels that the cache policy that has been executed has met his operational needs or is more suitable for his operational needs.

[0042] Step 300: continuously obtain feedback and continuously update the executed user cache strategy.

[0043] Specifically, step 300 includes: Step 310, when the user cache strategy is executed, continuously collect the user's operation data and the user's usage feedback; Step 320, updating the user data according to the user's operation data and the user's usage feedback, and updating the user cache strategy through the cache strategy generation model; Step 330, evaluating the updated user cache policy and setting an optimization threshold; Step 340: If the updated user cache policy evaluation exceeds the optimization threshold, the executed user cache policy is optimized and updated; otherwise, the cache policy generation model is continued to wait for the next update of the user cache policy.

[0044] Specifically, after the user cache strategy is executed, the cache device can be monitored, or user operation data and user usage feedback can be collected to decide whether to optimize and update the executed strategy. If the feedback is good and the user operation data has not changed significantly, the original strategy can be kept unchanged, otherwise it can be updated. At the same time, if indicators such as cache hit rate and system response time are abnormal, the strategy can also be optimized and updated. During specific use, the user cache strategy can be optimized regularly according to data collection or feedback. If the optimization threshold is exceeded, the executed user cache strategy is updated, otherwise wait for the next data collection.

[0045] In this embodiment, after collecting basic user information and before obtaining user data, a fuzzy portrait is generated and compared with existing user information, and the most similar user data is selected to generate a user emergency cache strategy for new users to use. This can quickly guess the user's operating preferences and generate a strategy, thereby satisfying the user's operating preferences to a certain extent and reducing user churn. At the same time, through subsequent data collection, the executed strategy can be updated to make the cache strategy more in line with the user's operating preferences, reduce invalid cache operations, optimize the user's operating experience, and provide users with intelligent investment services.

[0046] Based on the above embodiments, Figure 5 As shown, the present invention also provides a cache data processing device for intelligently analyzing the operating habits of investment users, which is used to support the cache data processing method for intelligently analyzing the operating habits of investment users in the above embodiment. The cache data processing device for intelligently analyzing the operating habits of investment users includes: Information acquisition module 11, which is used to obtain basic user information; An information search module 12, which is used to detect whether the basic user information already exists; A strategy generating module 13, which is used to read the matching user data according to the user basic information, and generate a user cache strategy by analyzing the user data; The strategy generation module 13 is further used to construct a user fuzzy portrait through the user basic information, and then perform a similarity query between the user fuzzy portrait and the historical user data to obtain the user data with the highest similarity, and generate a user emergency cache strategy based on the user data with the highest similarity; execute the user emergency cache strategy; further obtain the user data of the new user, and generate a user cache strategy for the new user based on the user data of the new user, and optionally replace the user emergency cache strategy; The policy updating module 14 is used for continuously updating the executed user cache policy.

[0047] In an optional embodiment, the strategy generation module 13 includes: A cache strategy generating unit, which reads matching user data according to the user basic information and generates a user cache strategy by analyzing the user data; An emergency strategy generation unit is used to construct a user fuzzy portrait through the user basic information, then perform a similarity query between the user fuzzy portrait and historical user data to obtain the user data with the highest similarity, and generate a user emergency cache strategy based on the user data with the highest similarity; execute the user emergency cache strategy; further obtain user data of a new user, and generate a user cache strategy for the new user based on the user data of the new user, and optionally replace the user emergency cache strategy.

[0048] In an optional embodiment, the cache strategy generation unit is specifically used to: Search the existing database to obtain user data matching the user basic information, implant a cache strategy generation model, input the user data, and analyze the user data through the cache strategy generation model, which outputs a user cache strategy matching the user data.

[0049] In an optional embodiment, the cache strategy generation unit is further used to: Establish a model through machine learning algorithm; obtain historical user data and generate a data set, which includes a training set for model training, a verification set for model selection and parameter adjustment, and a test set for evaluating model capabilities; use the data set to train, verify, adjust and evaluate the model to confirm the model's cache strategy output capability; after confirmation, output the cache strategy generation model and deploy it.

[0050] In an optional embodiment, the emergency strategy generation unit is specifically used to: Analyze the basic information of the user and construct a fuzzy user portrait; perform a similarity query between the fuzzy user portrait and the historical user portrait in the historical user portrait set; obtain the similarity query result and select the historical user portrait with the highest similarity; search the database according to the historical user portrait with the highest similarity to obtain the corresponding historical user data; analyze the historical user data through the deployed cache strategy generation model and generate a user emergency cache strategy for emergency use by new users; Furthermore, continuously trying to obtain extended data of new users through user preference testing, user usage feedback, user operation data and big data retrieval; continuously updating the user basic information and user data of new users according to the extended data; analyzing the updated user basic information and user data to obtain an updated user fuzzy portrait; setting a first threshold and a second threshold for portrait upgrade, and detecting the total update degree of the user fuzzy portrait; if the total update degree of the user fuzzy portrait does not exceed the first threshold, continuing to obtain the extended data of the new user and waiting for the next update of the user fuzzy portrait; if the total update degree of the user fuzzy portrait exceeds the first threshold, re-compare with the historical user portrait set The historical user portrait is subjected to similarity query, and the corresponding historical user data is obtained according to the similarity query result, and then the newly obtained historical user data is analyzed by the cache strategy generation model, and a new user emergency cache strategy is generated, and then user feedback is waited for, and the new user emergency cache strategy is optionally replaced; if the total update degree of the user fuzzy portrait exceeds the second threshold, the updated user basic information corresponding to the user fuzzy portrait is archived and stored, and at the same time, the updated user basic information is analyzed by the cache strategy generation model, and a new user cache strategy is generated, and then user feedback is waited for, and the new user cache strategy is optionally replaced.

[0051] In an optional embodiment, the strategy generation module 13 further includes: The historical user portrait generation unit is used to traverse the database, obtain existing user data, analyze the existing user data, and sequentially construct historical user portraits, generate a historical user portrait set, and store the historical user portraits.

[0052] In an optional embodiment, the policy updating module 14 is specifically used for: When the user cache strategy is executed, the user's operation data and the user's usage feedback are continuously collected; the user data is updated according to the user's operation data and the user's usage feedback, and the user cache strategy is updated through the cache strategy generation model; the updated user cache strategy is evaluated, and an optimization threshold is set; if the updated user cache strategy evaluation exceeds the optimization threshold, the executed user cache strategy is optimized and updated, otherwise, the cache strategy generation model is continued to wait for the next update of the user cache strategy.

[0053] In this embodiment, after collecting basic user information and before obtaining user data, a fuzzy portrait is generated and compared with existing user information, and the most similar user data is selected to generate a user emergency cache strategy for new users to use. This can quickly guess the user's operating preferences and generate a strategy, thereby satisfying the user's operating preferences to a certain extent and reducing user churn. At the same time, through subsequent data collection, the executed strategy can be updated to make the cache strategy more in line with the user's operating preferences, reduce invalid cache operations, optimize the user's operating experience, and provide users with intelligent investment services.

[0054] Furthermore, the cache data processing device for intelligently analyzing the operating habits of investment users can run the cache data processing method for intelligently analyzing the operating habits of investment users. The specific implementation can be found in the method embodiment, which will not be repeated here.

[0055] Based on the above embodiments, Figure 6 As shown, the present invention also provides a cache data processing method and device for intelligently analyzing the operating habits of investment users, and the cache data processing method and device for intelligently analyzing the operating habits of investment users includes: At least one processor 22, at least one memory 21, a communication interface 23 and a communication bus 24, wherein the processor 22 is communicatively connected with the memory 21; In this embodiment, the memory 21 may be implemented in any appropriate manner, for example, the memory 21 may be a read-only memory, a mechanical hard disk, a solid-state hard disk, or a USB flash drive, etc.; the memory 21 is used to store at least one executable instruction executed by the processor; In this embodiment, the processor 22 can be implemented in any appropriate manner. For example, the processor 22 can take the form of a microprocessor or a processor and a computer-readable medium storing computer-readable program code (such as software or firmware) that can be executed by the (micro)processor, a logic gate, a switch, an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), a programmable logic controller, and an embedded microcontroller, etc.; the processor is used to execute the executable instructions to implement the cache data processing method for intelligently analyzing the operating habits of investment users as described above.

[0056] Based on the above embodiments, the present invention also provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the cache data processing method for intelligently analyzing the operating habits of investment users as described above is implemented.

[0057] Those skilled in the art will appreciate that the modules and method steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0058] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices, equipment and modules can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0059] In the several embodiments provided in the present application, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or units can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or equipment, which can be electrical, mechanical or other forms.

[0060] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0061] In addition, each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0062] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage media include: U disk, mobile hard disk, read-only storage server, random access storage server, disk or optical disk, and other media that can store program instructions.

[0063] In addition, it should be noted that the combination of the various technical features in this case is not limited to the combination described in the claims of this case or the combination described in the specific embodiments. All technical features described in this case can be freely combined or combined in any way unless there is a contradiction between them.

[0064] It should be noted that the above examples are only specific embodiments of the present invention, and the present invention is obviously not limited to the above examples, and there are many similar variations. All variations directly derived or associated from the contents disclosed by the technicians in this field should fall within the protection scope of the present invention.

[0065] The above are only preferred embodiments of the present invention and are not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A cache data processing method for intelligently analyzing the operating habits of investment users, characterized in that: The following steps are involved: Get basic user information; Detecting whether the basic user information already exists; If yes, read the matching user data according to the user basic information, and generate a user cache strategy by analyzing the user data; If not, a user fuzzy profile is constructed through the user basic information, and then a similarity query is performed between the user fuzzy profile and the historical user data to obtain the user data with the highest similarity, and a user emergency cache strategy is generated according to the user data with the highest similarity; Executing the user emergency cache strategy; further acquiring user data of the new user, generating a user cache strategy for the new user based on the user data of the new user, and optionally replacing the user emergency cache strategy; Feedback is continuously obtained to continuously update the executed user cache strategy.

2. The cache data processing method for intelligently analyzing investment user operation habits according to claim 1 is characterized in that: The reading of matching user data according to the user basic information and generating a user cache strategy by analyzing the user data includes: Search the existing database to obtain user data matching the basic user information; Implant cache strategy generation model; Input the user data, and analyze the user data using the cache strategy generation model; The cache strategy generation model outputs a user cache strategy that matches the user data.

3. The cache data processing method for intelligently analyzing the operation habits of investment users according to claim 2 is characterized in that: The implantation cache strategy generation model includes: Build models through machine learning algorithms; Acquire historical user data and generate a data set, which includes a training set for model training, a validation set for model selection and parameter adjustment, and a test set for evaluating model capabilities; The model is trained, verified, adjusted and evaluated using the data set to confirm the model's cache strategy output capability; After confirmation, the output cache strategy generates a model and deploys it.

4. The cache data processing method for intelligently analyzing investment user operation habits according to claim 1 is characterized in that: The method further includes: constructing a user fuzzy portrait through the user basic information, performing a similarity query between the user fuzzy portrait and historical user data, obtaining user data with the highest similarity, and generating a user emergency cache strategy based on the user data with the highest similarity, and the method also includes: Traverse the database to obtain existing user data; Analyze the existing user data and build historical user portraits in sequence; Generate a historical user portrait set and store the historical user portraits.

5. The cache data processing method for intelligently analyzing the operation habits of investment users according to claim 4 is characterized in that: The method of constructing a user fuzzy portrait through the user basic information, performing a similarity query between the user fuzzy portrait and historical user data to obtain the user data with the highest similarity, and generating a user emergency cache strategy according to the user data with the highest similarity includes: Analyze user basic information and build user fuzzy portrait; Performing a similarity query between the user fuzzy portrait and the historical user portrait in the historical user portrait set; Get similarity query results and select the historical user portrait with the highest similarity; Search the database according to the historical user portrait with the highest similarity to obtain corresponding historical user data; The historical user data is analyzed by using a deployed cache strategy generation model, and a user emergency cache strategy for emergency use by new users is generated.

6. The cache data processing method for intelligently analyzing investment user operation habits according to claim 5 is characterized in that: The acquiring of user data of the new user, generating a user cache strategy for the new user according to the user data of the new user, and optionally replacing the user emergency cache strategy includes: Continue to try to obtain extended data of new users through user preference testing, user usage feedback, user operation data and big data retrieval; Continuously updating the basic user information and user data of the new user according to the extended data; Analyze the updated user basic information and user data to obtain an updated user fuzzy portrait; Setting a first threshold and a second threshold for portrait upgrade, and detecting the total update degree of the user's fuzzy portrait; If the total update degree of the user fuzzy portrait does not exceed the first threshold, continue to obtain the extended data of the new user and wait for the next update of the user fuzzy portrait; If the total update degree of the user fuzzy portrait exceeds the first threshold, a similarity query is performed again with the historical user portrait in the historical user portrait set, and corresponding historical user data is obtained according to the similarity query result, and then the newly obtained historical user data is analyzed by the cache strategy generation model, and a new user emergency cache strategy is generated, and then user feedback is waited for, and the new user emergency cache strategy is optionally replaced; If the total update degree of the user fuzzy portrait exceeds the second threshold, the updated user basic information corresponding to the user fuzzy portrait is archived and stored, and the updated user basic information is analyzed by the cache strategy generation model, and a new user cache strategy is generated, and then user feedback is waited for, and the new user cache strategy is optionally replaced.

7. The cache data processing method for intelligently analyzing investment user operation habits according to claim 1 is characterized in that: The continuously obtaining feedback and continuously updating the executed user cache strategy includes: When the user cache strategy is executed, the user's operation data and user's usage feedback are continuously collected; The user data is updated according to the user's operation data and the user's usage feedback, and the user cache strategy is updated through the cache strategy generation model; Evaluate the updated user cache strategy and set optimization thresholds; If the updated user cache policy evaluation exceeds the optimization threshold, the executed user cache policy is optimized and updated; otherwise, the cache policy generation model is continued to wait for the next update of the user cache policy.

8. A cache data processing device for intelligently analyzing the operating habits of investment users, characterized in that: include: Information acquisition module, which is used to obtain basic user information; An information search module, which is used to detect whether the basic user information already exists; A strategy generation module, which is used to read matching user data according to the user basic information and generate a user cache strategy by analyzing the user data; The strategy generation module is further used to construct a user fuzzy portrait through the user basic information, and then perform a similarity query between the user fuzzy portrait and historical user data to obtain the user data with the highest similarity, and generate a user emergency cache strategy based on the user data with the highest similarity; Executing the user emergency cache strategy; further acquiring user data of the new user, generating a user cache strategy for the new user based on the user data of the new user, and optionally replacing the user emergency cache strategy; A policy update module is used to continuously update the executed user cache policy.

9. An electronic device, characterized in that: The electronic device comprises: A processor and a memory, wherein the memory is communicatively connected to the processor; The memory is used to store at least one executable instruction executed by the processor, and the processor is used to execute the executable instruction to implement the cache data processing method for intelligently analyzing investment user operation habits as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the cache data processing method for intelligently analyzing the operating habits of investment users as described in any one of claims 1 to 7 is implemented.

Images