User information storage method, device, electronic device and computer medium

Abstract

The embodiments of the present disclosure disclose a method, device, electronic device and computer medium for storing user grade information. A specific implementation of the method includes: obtaining product information and at least one data source corresponding to the product information; binding the product information with the at least one data source with preset weights to obtain a bound data model set; generating a user rating information set based on the bound data model set; performing grade mapping on the user rating information set to obtain a mapped user rating grade information sequence; in response to determining that the feedback ratio corresponding to the extracted user feedback information representing normal feedback in the extracted user feedback information set is greater than a preset ratio threshold, storing the filtered user grade information sequence in a shared database. This implementation improves the security of user information and shortens the storage cycle of user information.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of computer technology, and in particular to a user information storage method, device, electronic device, and computer medium. Background Art

[0002] With the rapid development of the Internet, different users usually need to distinguish the levels of user information when using product information. User information storage is a technology used to store user level information, which can improve the security of user information and shorten the storage period of user information. In addition to user information storage, determining the user's subsequent operation behavior after the user level information is stored can also improve the security of user information. In addition, dynamically adjusting the data source can shorten the storage period of user information. At present, the method commonly used for user information storage is to analyze the consumption habits of a large number of users and manually record the user's level information to realize user information storage.

[0003] However, when the above method is adopted, the following technical problems often occur:

[0004] First, manually recording a large amount of user level information is labor-intensive and inefficient, and is prone to large errors, resulting in low credibility of user information storage, which in turn cannot guarantee that user information will not be leaked, resulting in low security of user information. As user level information is relatively complex, manual recording is slow, resulting in a longer storage period for user information.

[0005] Second, since it is impossible to determine whether the user's subsequent operating behavior is abnormal after the user level information is stored, the user information may be leaked, resulting in low security of the user information.

[0006] Third, since it is impossible to dynamically bind product information to the corresponding data source, the matching degree between product information and data source is not accurate enough. At the same time, since the data source cannot be adjusted in time during the binding process, the speed of generating the bound data model set is slow, thus prolonging the storage cycle of user information.

[0007] The above information disclosed in this Background section is only for enhancement of understanding of the background of the inventive concept and therefore it may contain information that does not form the prior art that is already known in this country to a person of ordinary skill in the art. Summary of the invention

[0008] The content of this disclosure is used to introduce concepts in a brief form, which will be described in detail in the detailed implementation section below. The content of this disclosure is not intended to identify the key features or essential features of the technical solution claimed for protection, nor is it intended to limit the scope of the technical solution claimed for protection.

[0009] Some embodiments of the present disclosure propose user information storage methods, devices, electronic devices, and computer media to solve one or more of the technical problems mentioned in the above background technology section.

[0010] In a first aspect, some embodiments of the present disclosure provide a method for storing user information, the method comprising: obtaining product information and at least one data source corresponding to the product information; binding the product information with the at least one data source by preset weights to obtain a bound data model set; generating a user rating information set according to the bound data model set; performing grade mapping on the user rating information set to obtain a mapped user rating grade information sequence; performing grade labeling on the user information corresponding to each mapped user rating grade information in the mapped user rating grade information sequence to obtain a labeled user grade information sequence; pushing the preset product information to each labeled user in the labeled user grade information sequence; The push result set is obtained by filtering the marked user level information sequence corresponding to the push result representing the push failure in the above push result set at a preset level to obtain a filtered user level information sequence; security reinforcement is performed on the above filtered user level information sequence to obtain a reinforced user level information sequence; user feedback information is extracted from at least one user device corresponding to the above reinforced user level information sequence to obtain an extracted user feedback information set; in response to determining that the feedback ratio corresponding to the extracted user feedback information representing normal feedback in the above extracted user feedback information set is greater than a preset ratio threshold, the above filtered user level information sequence is stored in a shared database.

[0011] In a second aspect, some embodiments of the present disclosure provide a user information storage device, the device comprising: an acquisition unit, configured to acquire product information and at least one data source corresponding to the above product information; a binding unit, configured to bind the above product information with the above at least one data source with a preset weight to obtain a bound data model set; a generation unit, configured to generate a user rating information set according to the above bound data model set; a mapping unit, configured to perform grade mapping on the above user rating information set to obtain a mapped user rating grade information sequence; a labeling unit, configured to perform grade labeling on user information corresponding to each mapped user rating grade information in the above mapped user rating grade information sequence to obtain a labeled user grade information sequence; a pushing unit, configured to push the preset product information to the above labeled user grade information set. The user devices corresponding to each annotated user level information in the sequence obtain a push result set; the screening unit is configured to perform preset level screening processing on the annotated user level information sequence corresponding to the push result representing push failure in the above push result set, and obtain a screened user level information sequence; the security reinforcement unit is configured to perform security reinforcement on the above screened user level information sequence, and obtain a reinforced user level information sequence; the extraction unit is configured to extract user feedback information from at least one user device corresponding to the above reinforced user level information sequence, and obtain an extracted user feedback information set; the storage unit is configured to store the above screened user level information sequence in a shared database in response to determining that the feedback ratio corresponding to the extracted user feedback information representing normal feedback in the above extracted user feedback information set is greater than a preset ratio threshold.

[0012] In a third aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation manner of the above-mentioned first aspect.

[0013] In a fourth aspect, some embodiments of the present disclosure provide a computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the method described in any implementation manner of the above-mentioned first aspect is implemented.

[0014] The above-mentioned embodiments of the present disclosure have the following beneficial effects: through the user information storage method of some embodiments of the present disclosure, the security of user information is improved and the storage period of user information is shortened. Specifically, the reasons for the low security of user information and the long storage period of user information are: manually recording a large amount of user level information has the problems of large workload and low efficiency, which is easy to produce large errors, resulting in low credibility of user information storage, and thus unable to ensure that user information is not leaked, resulting in low security of user information. Since user level information is relatively complex, the speed of manual recording is slow, resulting in a long storage period of user information. Based on this, the user information storage method of some embodiments of the present disclosure, first, obtains product information and at least one data source corresponding to the above product information. Thus, it can provide convenience for subsequent processing. The above product information is bound to the above at least one data source with a preset weight to obtain a bound data model set. Thus, the association relationship between the product information and the above at least one data source can be established. According to the above bound data model set, a user rating information set is generated. Thus, it can avoid manually recording a large amount of user level information, solving the problem of large workload and low efficiency. The above user rating information set is grade mapped to obtain a mapped user rating grade information sequence. Thus, the user's evaluation of the product can be understood more intuitively, the error can be reduced, and the credibility of the user information storage can be improved. The user information corresponding to each mapped user rating level information in the above-mentioned mapped user rating level information sequence is graded to obtain a marked user level information sequence. Thus, it is convenient to understand the user. The preset product information is pushed to the user device corresponding to each marked user level information in the above-mentioned marked user level information sequence to obtain a push result set. Thus, the user's satisfaction and experience can be improved, and the push error can also be reduced. The marked user level information sequence corresponding to the push result representing the push failure in the above-mentioned push result set is subjected to a preset level screening process to obtain a screened user level information sequence. Thus, the marked user level information corresponding to the push result of the push failure can be removed, and the marked user level information that can be pushed successfully is retained, which can improve the credibility of the user information storage and solve the problem that the user level information is relatively complex. The above-mentioned screened user level information sequence is securely reinforced to obtain a reinforced user level information sequence. Thus, the user information can be prevented from being leaked and the security of the user information can be improved. The user feedback information of at least one user device corresponding to the reinforced user level information sequence is extracted to obtain an extracted user feedback information set. Thus, the feedback information of the user device mobile phone user can be used to extract the reinforced user level information that meets the requirements.In response to determining that the feedback ratio corresponding to the extracted user feedback information representing normal feedback in the extracted user feedback information set is greater than a preset ratio threshold, the filtered user level information sequence is stored in a shared database. Thus, the user information can be stored without manual recording, thereby shortening the user information storage period. Therefore, the security of the user information is improved and the user information storage period is shortened. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.

[0016] Figure 1 is a flow chart of some embodiments of the user information storage method according to the present disclosure;

[0017] Figure 2 is a schematic diagram of the structure of some embodiments of the user information storage device according to the present disclosure;

[0018] Figure 3 It is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION

[0019] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0020] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present disclosure can be combined with each other.

[0021] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0022] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0023] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0024] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0025] Figure 1 This is a process 100 of some embodiments of the user information storage method of the present disclosure. The user information storage method comprises the following steps:

[0026] Step 101: Acquire product information and at least one data source corresponding to the product information.

[0027] In some embodiments, the execution subject of the user information storage method (eg, a computing device) may obtain the product information and at least one data source corresponding to the product information through a wired connection or a wireless connection.

[0028] Here, the product information may refer to financial products and the name information of financial products. The data source in the at least one data source may refer to the source of providing data. For example, the data source in the at least one data source may refer to a database. The data source in the at least one data source may also refer to a file.

[0029] It should be noted that the above-mentioned wireless connection methods may include but are not limited to 3G / 4G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other wireless connection methods currently known or to be developed in the future.

[0030] Step 102: Bind the product information with the at least one data source according to preset weights to obtain a bound data model set.

[0031] In some embodiments, the execution entity may bind the product information to the at least one data source with preset weights to obtain a bound data model set.

[0032] Here, the preset weight may refer to a preset weight containing a ratio condition. For example, the preset weight may refer to a preset "weight ratio of 60%, 40%, 30%". The bound data model in the bound data model set may refer to a data model of a data source and product information bound with preset weights. The bound data model set is used to determine the degree of association between at least one data source and product information.

[0033] As an example, the execution entity may combine the product information with the at least one data source according to a preset weight to obtain a combined data model set as a bound data model set.

[0034] Optionally, the execution subject may bind the product information with the at least one data source with a preset weight through the following steps to obtain a bound data model set:

[0035] The first step is to bind the product information to a data source whose weight is greater than or equal to the preset first weight value in response to determining that the weight corresponding to the data source in the at least one data source is greater than or equal to the preset first weight value to obtain a first data model after binding.

[0036] Here, the above-mentioned preset first weight value may refer to a value corresponding to a preset weight. For example, the above-mentioned preset first weight value may refer to 60%. The above-mentioned first data model after binding may refer to a data model after the product information is bound to a data source greater than or equal to the preset first weight value. The above-mentioned first data model after binding is used to determine the degree of association between the data source greater than or equal to the preset first weight value and the product information. Here, the above-mentioned binding may refer to a combination.

[0037] In the second step, in response to determining that the weight corresponding to a data source in the at least one data source is greater than or equal to a preset second weight value, the product information is bound to a data source greater than or equal to the preset second weight value to obtain a second data model after binding.

[0038] Here, the above-mentioned preset second weight value may refer to a value corresponding to a preset weight. For example, the above-mentioned preset second weight value may refer to 40%. The above-mentioned second data model after binding may refer to a data model after the product information is bound to a data source greater than or equal to the preset second weight value. The above-mentioned second data model after binding is used to determine the degree of association between the data source greater than or equal to the preset second weight value and the product information.

[0039] In the third step, in response to determining that the weight corresponding to a data source in the at least one data source is greater than or equal to a preset third weight value, the product information is bound to a data source greater than or equal to the preset third weight value to obtain a third data model after binding.

[0040] Here, the above-mentioned preset third weight value may refer to a value corresponding to a preset weight. For example, the above-mentioned preset third weight value may refer to 30%. The above-mentioned third data model after binding may refer to a data model after the product information is bound to a data source greater than or equal to the preset third weight value. The above-mentioned third data model after binding is used to determine the degree of association between the data source greater than or equal to the preset third weight value and the product information.

[0041] In the fourth step, the first data model after binding, the second data model after binding and the third data model after binding are determined as a bound data model set.

[0042] Optionally, the execution subject may bind the product information with the at least one data source with a preset weight through the following steps to obtain a bound data model set:

[0043] The first step is to set an initial weight value for the at least one data source to obtain an initial data source weight set.

[0044] Here, the above-mentioned initial weight value may refer to the initially set weight.

[0045] As an example, the execution entity may randomly set an initial weight value for the at least one data source to obtain an initial data source weight set.

[0046] The second step is to perform at least one user behavior information check on the above product information to obtain a behavior information check list.

[0047] Here, the above behavior information verification list may include: click rate verification information, browsing time verification information.

[0048] As an example, the execution subject may determine at least one user behavior information on the product information to obtain a user behavior information set, and then verify each user behavior information in the user behavior information set to obtain a behavior information verification list.

[0049] The third step is to perform indicator detection on each data source of the at least one data source to generate a data source indicator group and obtain a data source indicator group set.

[0050] Here, the above-mentioned indicator may refer to a data integrity indicator of a data source.

[0051] As an example, the execution subject may determine the indicator corresponding to each data source in the at least one data source to generate at least one indicator to obtain an indicator group set. Then, each indicator group in the indicator group set is tested to generate a tested indicator group, and the tested indicator group set is obtained as the data source indicator group set.

[0052] The fourth step is to input the above behavior information verification list and the above data source indicator group into a pre-trained weight prediction model to obtain at least one data source weight.

[0053] Here, the weight prediction model may refer to a multilayer perceptron (MLP) model. The input layer of the weight prediction model may be used to input a behavior inspection list and a data source indicator set. The output layer of the weight prediction model may be used to output at least one data source weight.

[0054] Step 5: For each data source weight in the at least one data source weight, perform the following processing steps:

[0055] In a first sub-step, a difference is determined between the above-mentioned data source weight and an initial data source weight corresponding to the above-mentioned data source weight in the above-mentioned initial data source weight set to obtain a weight difference.

[0056] Here, the above-mentioned weight difference may refer to the difference between the data source weight and the corresponding initial data source weight.

[0057] As an example, the execution entity may subtract the initial data source weight corresponding to the data source weight in the initial data source weight set from the data source weight to obtain a weight difference.

[0058] In the second sub-step, a preset period detection is performed on the above-mentioned weight difference to obtain a detection result.

[0059] Here, the preset period may refer to a pre-set period. For example, the preset period may refer to 30 seconds.

[0060] As an example, the execution entity may detect the weight difference at a preset period to obtain a detection result.

[0061] In a third sub-step, in response to determining that the detection result indicates a detection anomaly, dynamically adjusting a data source corresponding to the data source weight in the at least one data source according to the data source weight to obtain an adjusted data source.

[0062] As an example, the execution entity may locate the data source corresponding to the data source weight in at least one of the data sources to obtain the data source location. Then, a preset weight ratio is set for the data source corresponding to the data source location to obtain the data source after the weight is set. Finally, the data source after the weight is set is used as the adjusted data source. The preset weight ratio may refer to 50%.

[0063] In the sixth step, in response to determining that the weight corresponding to the adjusted data source in at least one adjusted data source is greater than or equal to the preset weight condition, the above-mentioned product information is bound to at least one adjusted data source greater than or equal to the preset weight condition to obtain a bound data model set.

[0064] Here, the preset weight condition may refer to the preset “weight ratio is 60%”. The binding may refer to combining.

[0065] The relevant contents in the first step to the sixth step above serve as an inventive point of the present disclosure, and solve the technical problem three mentioned in the background technology: "Since it is impossible to dynamically bind the product information to the corresponding data source, the matching degree between the product information and the data source is not accurate enough. At the same time, since the data source cannot be adjusted in time during the binding process, the speed of generating the bound data model set is slow, thereby extending the user information storage period". The factors that lead to a long user information storage period are often as follows: Since it is impossible to dynamically bind the product information to the corresponding data source, the matching degree between the product information and the data source is not accurate enough. At the same time, since the data source cannot be adjusted in time during the binding process, the speed of generating the bound data model set is slow, thereby extending the user information storage period. In order to achieve this effect, in the first step, an initial weight value is set for the above at least one data source to obtain an initial data source weight set. Thus, the initial weight value can be set to facilitate subsequent processing. In the second step, at least one user behavior information test is performed on the above product information to obtain a behavior information test list. Thus, the user's behavior of using product information can be determined, and the security of user information can be improved. In the third step, an indicator detection is performed on each of the at least one data source to generate a data source indicator group and obtain a data source indicator group set. Thus, the security of user information can be improved. In the fourth step, the behavior information inspection list and the data source indicator group set are input into a pre-trained weight prediction model to obtain at least one data source weight. Thus, the weight of the data source can be dynamically predicted. In the fifth step, for each of the at least one data source weight, the following processing steps are performed: a first sub-step, the difference between the data source weight and the initial data source weight corresponding to the data source weight in the initial data source weight set is determined to obtain a weight difference. Thus, the accuracy of the matching degree between product information and data source can be improved. In the second sub-step, the weight difference is detected at a preset period to obtain a detection result. Thus, the data source can be adjusted in time according to the detection result. In the third sub-step, in response to determining that the detection result indicates that the detection is abnormal, the data source corresponding to the data source weight in the at least one data source is dynamically adjusted according to the data source weight to obtain an adjusted data source. Thus, the data source can be adjusted in time according to the detection result, and the speed of generating the bound data model set is improved, thereby shortening the storage cycle of user information. In step 6, in response to determining that the weight corresponding to the adjusted data source in the at least one adjusted data source is greater than or equal to the preset weight condition, the above product information is bound to at least one adjusted data source greater than or equal to the preset weight condition to obtain a bound data model set. In this way, it is possible to dynamically bind the product information to the corresponding data source. Therefore, the speed of generating the bound data model set is improved, and the period of user information storage is shortened.

[0066] Step 103: Generate a user rating information set based on the above bound data model set.

[0067] In some embodiments, the execution entity may generate a user rating information set based on the bound data model set.

[0068] Here, the user rating information in the user rating information set may refer to the rating information of the user on the bound data model in the bound data model set. For example, the user rating information in the user rating information set may refer to [90 points, excellent].

[0069] As an example, the execution subject may first determine the user rating information for each bound data model in the bound data model set to generate user rating information and obtain a user rating information set.

[0070] Optionally, the execution subject may generate a user rating information set according to the bound data model set through the following steps:

[0071] The first step is, in response to determining that the first bound data model in the above-mentioned bound data model set is called, determining the rating information of the above-mentioned first bound data model for at least one user, and obtaining a first rating information set.

[0072] Here, the first rating information in the first rating information set may refer to the rating information of the user by the first data model after binding.

[0073] In the second step, at least one first rating information in the first rating information set that is greater than a preset first rating threshold is determined as a first user rating information set.

[0074] Here, the preset first scoring threshold may refer to a preset maximum score value that limits the first scoring information set. For example, the preset first scoring threshold may refer to 80.

[0075] In the third step, in response to determining that the second bound data model in the above-mentioned bound data model set is called, the second bound data model is determined to correspond to the rating information of at least one user of the above-mentioned first user rating information set, so as to obtain a second rating information set.

[0076] Here, the second rating information in the second rating information set may refer to the rating information of the user by the second data model after the binding.

[0077] In the fourth step, at least one second rating information in the second rating information set that is greater than a preset second rating threshold is determined as a second user rating information set.

[0078] Here, the preset second scoring threshold may refer to a preset maximum score value that limits the second scoring information set. For example, the preset second scoring threshold may refer to 70.

[0079] In a fifth step, in response to determining that the third bound data model in the above-mentioned bound data model set is called, the rating information of at least one user corresponding to the above-mentioned second user rating information set by the third bound data model is determined to obtain a third rating information set.

[0080] Here, the third rating information in the third rating information set may refer to the rating information of the user by the third data model after binding.

[0081] In a sixth step, at least one third rating information in the third rating information set that is greater than a preset third rating threshold is determined as a third user rating information set.

[0082] Here, the preset third scoring threshold may refer to a preset maximum score value that limits the third scoring information set. For example, the preset third scoring threshold may refer to 60.

[0083] In the seventh step, the first user rating information set, the second user rating information set and the third user rating information set are determined as user rating information sets.

[0084] Optionally, after the above “step 103”, the above method further includes:

[0085] In the first step, at least one user rating information in the user rating information set that is less than or equal to a preset rating threshold is determined as an abnormal user information set.

[0086] Here, the preset scoring threshold may refer to a preset maximum value of the scoring information. For example, the preset scoring threshold may refer to 50.

[0087] Optionally, the execution subject may determine at least one user rating information in the user rating information set that is less than or equal to a preset rating threshold as an abnormal user information set by the following steps:

[0088] In the first sub-step, at least one first scoring information in the first scoring information set of the user scoring information set that is less than or equal to the preset first scoring threshold is determined as a first abnormal user information set.

[0089] In the second sub-step, at least one second scoring information in the second scoring information set in the user scoring information set that is less than or equal to the preset second scoring threshold is determined as a second abnormal user information set.

[0090] In a third sub-step, at least one third scoring information in the third scoring information set in the user scoring information set that is less than or equal to the preset third scoring threshold is determined as a third abnormal user information set.

[0091] The fourth sub-step is to determine the first abnormal user information set, the second abnormal user information set and the third abnormal user information set as abnormal user information sets.

[0092] In the second step, in response to detecting that the user corresponding to the abnormal user information in the abnormal user information set accesses the shared database, the abnormal user corresponding to each abnormal user information in the abnormal user information set is intercepted to obtain an interception result.

[0093] In the third step, in response to determining that the interception result indicates successful interception, the abnormal user is added to a preset user list.

[0094] Here, the preset user list may refer to a list of pre-set stored users. For example, the preset user list may refer to a blacklist.

[0095] Step 104, performing level mapping on the above user rating information set to obtain a mapped user rating level information sequence.

[0096] In some embodiments, the execution entity may perform level mapping on the user rating information set to obtain a mapped user rating level information sequence.

[0097] Here, the above-mentioned mapped user rating level information sequence may refer to a sequence obtained by mapping the rating of each user in the user rating information set to the corresponding rating level information. For example, the user rating information set may refer to {user 1: 60 points, user 2: 70 points, user 3: 90 points}. The mapped user rating level information sequence may refer to {user 1: medium rating, user 2: good, user 3: excellent}.

[0098] As an example, the execution subject may first determine a rating level set. Then, the user rating information set is traversed to obtain a traversal result. Then, in response to determining that the traversal result indicates that the traversal is complete, each user rating information in the user rating information set is combined with the corresponding rating level in the rating level set to generate combined user rating level information, and a combined user rating level information sequence is obtained as a mapped user rating level information sequence.

[0099] Step 105 , marking the level of the user information corresponding to each mapped user rating level information in the mapped user rating level information sequence to obtain a marked user level information sequence.

[0100] In some embodiments, the execution subject may perform grade marking on the user information corresponding to each mapped user rating grade information in the mapped user rating grade information sequence to obtain a marked user grade information sequence.

[0101] As an example, the execution subject may use a labeling tool to label the user information corresponding to each mapped user rating level information in the mapped user rating level information sequence to obtain a labeled user level information sequence. For example, the labeling tool may be Prodigy.

[0102] Step 106: Push the preset product information to the user devices corresponding to the respective annotated user level information in the annotated user level information sequence to obtain a push result set.

[0103] In some embodiments, the execution entity may push the preset product information to the user devices corresponding to each annotated user level information in the annotated user level information sequence to obtain a push result set.

[0104] Here, the user device may refer to a user's mobile device. The pre-set product information may refer to pre-set financial product information. For example, the pre-set product information may refer to pre-set insurance product information.

[0105] As an example, the execution subject may determine the identifier of the user device corresponding to each annotated user level information in the annotated user level information sequence to obtain an identifier set. Then, the demand detection is performed on the user device corresponding to each annotated user level information in the annotated user level information sequence to obtain a demand detection information set. Next, the user device corresponding to each demand detection information representing normal demand in the demand detection information set and the identifier in the identifier set is determined as the user device to be pushed to obtain the user device set to be pushed. Finally, the preset product information is pushed to the user device set to be pushed to obtain a push result set.

[0106] Step 107 , performing a preset level screening process on the marked user level information sequence corresponding to the push result indicative of push failure in the above push result set to obtain a screened user level information sequence.

[0107] In some embodiments, the execution subject may perform a preset level screening process on the annotated user level information sequence corresponding to the push result indicative of push failure in the push result set to obtain a screened user level information sequence.

[0108] Here, the preset level may refer to a pre-set user level.

[0109] As an example, the execution subject may remove the annotated user level information corresponding to the push results indicating push failure in the push result set from the annotated user level information sequence to obtain an eliminated user level information sequence as the filtered user level information sequence.

[0110] Step 108: security reinforcement is performed on the above-screened user level information sequence to obtain a reinforced user level information sequence.

[0111] In some embodiments, the execution entity may perform security reinforcement on the filtered user level information sequence to obtain a reinforced user level information sequence.

[0112] Here, the above-mentioned reinforced user level information sequence may refer to a sequence consisting of multiple user level information after identity authentication reinforcement.

[0113] As an example, the execution entity may use a security protocol (e.g., TLS / SSL) to encrypt the screened user level information sequence to obtain an encrypted user level information sequence. Then, access control is performed on the encrypted user level information sequence to obtain a controlled user level information sequence. Next, identity verification is performed on the controlled user level information sequence to obtain a verified user level information sequence as a reinforced user level information sequence. The identity verification may refer to password verification. The identity verification may also refer to SMS verification.

[0114] Optionally, after the above “step 108”, the above method further includes:

[0115] The first step is to build a user behavior prediction model based on the filtered user level information sequence in the above shared database.

[0116] Here, the user behavior prediction model may refer to a machine learning model. The input layer of the user behavior prediction model may be used to input a user information set. The output layer of the user behavior prediction model may be used to output a user behavior information set.

[0117] The second step is to optimize the above user behavior prediction model to obtain an optimized user behavior prediction model.

[0118] As an example, the execution entity may optimize the user behavior prediction model using an adaptive learning rate algorithm to obtain an optimized user behavior prediction model.

[0119] The third step is to collect a user information set through at least one user device.

[0120] Here, the user device in the at least one user device may refer to a mobile phone device of the user. The user information in the user information set may refer to relevant information of the user. For example, the user information in the user information set may refer to the name of the user.

[0121] The fourth step is to generate a user rating information set based on the above optimized user behavior prediction model and the above user information set.

[0122] As an example, the execution subject may input the user information set into the optimized user behavior prediction model to obtain a user behavior information set. Then, each user behavior information in the user behavior information set is scored to generate scoring information, and a scoring information set is obtained as a user scoring information set.

[0123] The fifth step is to classify each user rating information in the above user rating information set into a preset level to generate user level information and obtain a user level information set.

[0124] Here, the preset level may refer to a preset user level. For example, the preset level may refer to {90 points or more for high-quality user level, 80 points to 90 points for good user level, 60 points to 80 points for general user level, and 60 points or less for poor user level}.

[0125] As an example, the execution subject may classify each user rating information in the user rating information set to obtain a classified user rating information set. Then, the classified user rating information in the classified user rating information set is classified according to a preset level to obtain a user level information set.

[0126] Step 6: Determine at least one user level information in the user level information set that is greater than a preset level threshold as a user level information sequence.

[0127] Here, the preset level threshold may refer to the maximum value of the preset user level. The preset level threshold may refer to the general user level, good user level and high-quality user level above 60 points.

[0128] The seventh step is to compare the user level information sequence with the filtered user level information sequence to obtain a user level difference information set.

[0129] As an example, the execution subject may determine the difference between the user level information sequence and the filtered user level information sequence to obtain a difference information set. Then, the difference information in the difference information set is annotated using an annotation tool to obtain an annotated difference information set as the user level difference information set.

[0130] In the eighth step, according to the user level difference information set, the parameters of the optimized user behavior prediction model are adjusted to obtain a user behavior prediction model after parameter adjustment.

[0131] As an example, the execution subject may adjust the learning rate of each user level difference information in the user level difference information set to generate adjusted difference information and obtain an adjusted difference information set. Then, the optimized user behavior prediction model is regularized according to each adjusted difference information in the adjusted difference information set using a learning curve to obtain a parameter-adjusted user behavior prediction model.

[0132] The ninth step is to generate an adjusted user rating information set based on the user behavior prediction model after the above parameters are adjusted and the above user information set.

[0133] As an example, the execution subject may input the user information set into the parameter adjusted user behavior prediction model to obtain an adjusted user behavior set. Then, each adjusted user behavior in the adjusted user behavior set is scored to generate user scoring information, and a user scoring information set is obtained as an adjusted user rating information set.

[0134] In the tenth step, behavior recognition is performed on user information corresponding to at least one adjusted user rating information greater than a preset rating threshold in the adjusted user rating information set to obtain a recognized user information set.

[0135] Here, the preset score threshold may refer to a preset maximum value of the user score. For example, the preset score threshold may refer to 80 points.

[0136] As an example, the execution entity may perform behavior identification on user information corresponding to at least one adjusted user rating information greater than a preset rating threshold in the adjusted user rating information set through cluster analysis to obtain an identified user information set.

[0137] In the eleventh step, in response to determining that the identified user information set contains the identified user information representing abnormal user information behavior, abnormal control is performed on the identified user information set to obtain a controlled user information set.

[0138] As an example, the execution subject may verify the identified user information set to obtain a verification result. Then, in response to determining that the verification result indicates a verification anomaly, the identified user information set is restricted in user rights to obtain a restricted user information set as a controlled user information set. The user rights may refer to the user's access rights.

[0139] The relevant contents in the first step to the eleventh step above are an inventive point of the present disclosure, which solves the technical problem 2 mentioned in the background technology, "Since it is impossible to determine whether the user's subsequent operation behavior is abnormal after the user level information is stored, the user information may be found to be leaked, resulting in low security of the user information". The factors that may cause the user information to be leaked and the user information to be low in security are often as follows: Since it is impossible to determine whether the user's subsequent operation behavior is abnormal after the user level information is stored, the user information may be found to be leaked, resulting in low security of the user information. If the above factors are solved, the effect of improving the security of the user information can be achieved. In order to achieve this effect, in the first step, a user behavior prediction model is constructed based on the filtered user level information sequence in the above shared database. Thus, the user's behavior can be predicted by the user behavior prediction model to determine whether the user's subsequent operation behavior is abnormal. In the second step, the above user behavior prediction model is optimized to obtain an optimized user behavior prediction model. Thus, the user's subsequent operation behavior can be determined more accurately. In the third step, a user information set is collected through at least one user device. Thus, the user's information can be more accurately understood. In the fourth step, a user rating information set is generated based on the above optimized user behavior prediction model and the above user information set. In the fifth step, each user rating information in the above user rating information set is divided into preset levels to generate user level information and obtain a user level information set. In this way, the possibility of user information being discovered and leaked can be avoided, and the security of user information is improved. In the sixth step, at least one user level information in the above user level information set that is greater than the preset level threshold is determined as a user level information sequence. In the seventh step, the above user level information sequence is compared with the above screened user level information sequence for information difference to obtain a user level difference information set. In the eighth step, according to the above user level difference information set, the parameters of the above optimized user behavior prediction model are adjusted to obtain a parameter-adjusted user behavior prediction model. In the ninth step, according to the above parameter-adjusted user behavior prediction model and the above user information set, an adjusted user rating information set is generated. In the tenth step, the user information corresponding to at least one adjusted user rating information in the above adjusted user rating information set that is greater than the preset rating threshold is identified to obtain an identified user information set. In this way, the identification of user behavior information is more accurate. In step 11, in response to determining that the identified user information set contains abnormal user information behavior, the identified user information set is abnormally controlled to obtain a controlled user information set. Thus, the security of the user information is improved. Therefore, the possibility of user information being discovered and leaked is avoided, and the security of the user information is improved.

[0140] Step 109: extracting user feedback information from at least one user device corresponding to the reinforced user level information sequence to obtain an extracted user feedback information set.

[0141] In some embodiments, the execution subject may extract user feedback information from at least one user device corresponding to the reinforced user level information sequence to obtain an extracted user feedback information set.

[0142] Here, the user feedback information may refer to the user's feedback information on the reinforced user level information sequence. For example, the user feedback information may refer to the user's consent information.

[0143] As an example, the execution subject may determine the user feedback information of at least one user device corresponding to the reinforced user level information sequence to obtain a user feedback information set, and then extract information from the user feedback information set to obtain an extracted user feedback information set.

[0144] Step 110 , in response to determining that the feedback ratio corresponding to the extracted user feedback information in the extracted user feedback information set representing normal feedback is greater than a preset ratio threshold, the filtered user level information sequence is stored in a shared database.

[0145] In some embodiments, the execution subject may store the filtered user level information sequence in a shared database in response to determining that the feedback ratio corresponding to the extracted user feedback information representing normal feedback in the extracted user feedback information set is greater than a preset ratio threshold.

[0146] The above-mentioned embodiments of the present disclosure have the following beneficial effects: through the user information storage method of some embodiments of the present disclosure, the security of user information is improved and the storage period of user information is shortened. Specifically, the reasons for the low security of user information and the long storage period of user information are: manually recording a large amount of user level information has the problems of large workload and low efficiency, which is easy to produce large errors, resulting in low credibility of user information storage, and thus unable to ensure that user information is not leaked, resulting in low security of user information. Since user level information is relatively complex, the speed of manual recording is slow, resulting in a long storage period of user information. Based on this, the user information storage method of some embodiments of the present disclosure, first, obtains product information and at least one data source corresponding to the above product information. Thus, it can provide convenience for subsequent processing. The above product information is bound to the above at least one data source with a preset weight to obtain a bound data model set. Thus, the association relationship between the product information and the above at least one data source can be established. According to the above bound data model set, a user rating information set is generated. Thus, it can avoid manually recording a large amount of user level information, solving the problem of large workload and low efficiency. The above user rating information set is grade mapped to obtain a mapped user rating grade information sequence. Thus, the user's evaluation of the product can be understood more intuitively, the error can be reduced, and the credibility of the user information storage can be improved. The user information corresponding to each mapped user rating level information in the above-mentioned mapped user rating level information sequence is graded to obtain a marked user level information sequence. Thus, it is convenient to understand the user. The preset product information is pushed to the user device corresponding to each marked user level information in the above-mentioned marked user level information sequence to obtain a push result set. Thus, the user's satisfaction and experience can be improved, and the push error can also be reduced. The marked user level information sequence corresponding to the push result representing the push failure in the above-mentioned push result set is subjected to a preset level screening process to obtain a screened user level information sequence. Thus, the marked user level information corresponding to the push result of the push failure can be removed, and the marked user level information that can be pushed successfully is retained, which can improve the credibility of the user information storage and solve the problem that the user level information is relatively complex. The above-mentioned screened user level information sequence is securely reinforced to obtain a reinforced user level information sequence. Thus, the user information can be prevented from being leaked and the security of the user information can be improved. The user feedback information of at least one user device corresponding to the reinforced user level information sequence is extracted to obtain an extracted user feedback information set. Thus, the feedback information of the user device mobile phone user can be used to extract the reinforced user level information that meets the requirements.In response to determining that the feedback ratio corresponding to the extracted user feedback information representing normal feedback in the extracted user feedback information set is greater than a preset ratio threshold, the filtered user level information sequence is stored in a shared database. Thus, the user information can be stored without manual recording, thereby shortening the user information storage period. Therefore, the security of the user information is improved and the user information storage period is shortened.

[0147] Further references Figure 2 As an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a user information storage method. These device embodiments are similar to Figure 1 Corresponding to the method embodiments shown, the device can be specifically applied to various electronic devices.

[0148] like Figure 2 As shown, the user information storage device 200 of some embodiments includes: an acquisition unit 201, a binding unit 202, a generation unit 203, a mapping unit 204, a labeling unit 205, a push unit 206, a screening unit 207, a security reinforcement unit 208, an extraction unit 209 and a storage unit 210. Among them, the acquisition unit 201 is configured to acquire product information and at least one data source corresponding to the above product information; the binding unit 202 is configured to bind the above product information with the above at least one data source by preset weights to obtain a bound data model set; the generation unit 203 is configured to generate a user rating information set according to the above bound data model set; the mapping unit 204 is configured to perform grade mapping on the above user rating information set to obtain a mapped user rating grade information sequence; the labeling unit 205 is configured to perform grade labeling on the user information corresponding to each mapped user rating grade information in the above mapped user rating grade information sequence to obtain a labeled user grade information sequence; the pushing unit 206 is configured to push the preset product information to each labeled user grade information in the above labeled user grade information sequence. The user device corresponding to the information obtains a push result set; the screening unit 207 is configured to perform preset level screening processing on the marked user level information sequence corresponding to the push result representing the push failure in the above push result set, and obtain a screened user level information sequence; the security reinforcement unit 208 is configured to perform security reinforcement on the above screened user level information sequence, and obtain a reinforced user level information sequence; the extraction unit 209 is configured to extract user feedback information from at least one user device corresponding to the above reinforced user level information sequence, and obtain an extracted user feedback information set; the storage unit 210 is configured to store the above screened user level information sequence in a shared database in response to determining that the feedback ratio corresponding to the extracted user feedback information representing normal feedback in the above extracted user feedback information set is greater than a preset ratio threshold.

[0149] It is understood that the units described in the device 200 are similar to those described in the reference Figure 1 Therefore, the operations, features and beneficial effects described above for the method are also applicable to the device 200 and the units included therein, and will not be described in detail here.

[0150] Reference below Figure 3 , which shows a schematic structural diagram of an electronic device (such as a computing device) 300 suitable for implementing some embodiments of the present disclosure. Figure 3 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0151] like Figure 3 As shown, the electronic device 300 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 304. In RAM 303, various programs and data required for the operation of the electronic device 300 are also stored. The processing device 301, ROM 302, and RAM 304 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0152] Typically, the following devices may be connected to the I / O interface 305: input devices 306 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 308 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 309. The communication devices 309 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 3 The electronic device 300 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead. Figure 3 Each block shown in the figure may represent one device, or may represent multiple devices as required.

[0153] In particular, according to some embodiments of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, some embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In some such embodiments, the computer program can be downloaded and installed from the network through the communication device 309, or installed from the storage device 308, or installed from the ROM 302. When the computer program is executed by the processing device 301, the functions defined in the method of some embodiments of the present disclosure are executed.

[0154] It should be noted that the computer-readable medium recorded in some embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In some embodiments of the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, device or device. In some embodiments of the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.

[0155] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (Hyper Text Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0156] The above-mentioned computer-readable medium may be included in the above-mentioned electronic device; or it may exist independently without being assembled into the electronic device. The above-mentioned computer-readable medium carries one or more programs. When the above-mentioned one or more programs are executed by the electronic device, the electronic device: obtains product information and at least one data source corresponding to the above-mentioned product information; binds the above-mentioned product information with the above-mentioned at least one data source by preset weights to obtain a bound data model set; generates a user rating information set according to the above-mentioned bound data model set; performs grade mapping on the above-mentioned user rating information set to obtain a mapped user rating grade information sequence; grades the user information corresponding to each mapped user rating grade information in the above-mentioned mapped user rating grade information sequence to obtain a graded user grade information sequence; pushes the preset product information to the above-mentioned graded user grade information set; The push result set is obtained by filtering the marked user level information sequence corresponding to the push result representing the push failure in the above push result set at a preset level to obtain a filtered user level information sequence; security reinforcement is performed on the above filtered user level information sequence to obtain a reinforced user level information sequence; user feedback information is extracted from at least one user device corresponding to the above reinforced user level information sequence to obtain an extracted user feedback information set; in response to determining that the feedback ratio corresponding to the extracted user feedback information representing normal feedback in the above extracted user feedback information set is greater than a preset ratio threshold, the above filtered user level information sequence is stored in a shared database.

[0157] Computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0158] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0159] The units described in some embodiments of the present disclosure may be implemented by software or by hardware. The described units may also be set in a processor, for example, it may be described as: a processor including: an acquisition unit, a binding unit, a generation unit, a mapping unit, a labeling unit, a push unit, a screening unit, a security reinforcement unit, an extraction unit and a storage unit. The names of these units do not constitute a limitation on the units themselves in some cases. For example, the acquisition unit may also be described as "a unit for acquiring product information and at least one data source corresponding to the above product information".

[0160] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chip (SOCs), complex programmable logic devices (CPLDs), and the like.

[0161] The above descriptions are only some preferred embodiments of the present disclosure and the explanation of the technical principles used above. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by the specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above invention concept. For example, the above features are replaced with the technical features with similar functions disclosed in the embodiments of the present disclosure (but not limited to) and the technical solutions formed.

Claims

1. A user information storage method, comprising: Acquire product information and at least one data source corresponding to the product information; Binding the product information with the at least one data source with a preset weight to obtain a bound data model set, wherein the binding of the product information with the at least one data source with a preset weight to obtain a bound data model set includes: In response to determining that the weight corresponding to the data source in the at least one data source is greater than or equal to a preset first weight value, binding the product information with the data source greater than or equal to the preset first weight value to obtain a bound first data model; In response to determining that the weight corresponding to the data source in the at least one data source is greater than or equal to a preset second weight value, the product information is bound to the data source whose weight is greater than or equal to the preset second weight value to obtain a second data model after binding; in response to determining that the weight corresponding to the data source in the at least one data source is greater than or equal to a preset third weight value, the product information is bound to the data source whose weight is greater than or equal to the preset third weight value to obtain a third data model after binding; Determine the first data model after binding, the second data model after binding and the third data model after binding as a data model set after binding; Generate a user rating information set according to the bound data model set, wherein the generating the user rating information set according to the bound data model set includes: In response to determining that a first bound data model in the bound data model set is called, determining rating information of the first bound data model for at least one user to obtain a first rating information set; Determine at least one first rating information in the first rating information set that is greater than a preset first rating threshold as a first user rating information set; In response to determining that a second bound data model in the bound data model set is called, determining that the second bound data model corresponds to rating information of at least one user of the first user rating information set, thereby obtaining a second rating information set; Determine at least one second rating information in the second rating information set that is greater than a preset second rating threshold as a second user rating information set; In response to determining that a third bound data model in the bound data model set is called, determining that the third bound data model corresponds to rating information of at least one user of the second user rating information set, thereby obtaining a third rating information set; Determine at least one third rating information in the third rating information set that is greater than a preset third rating threshold as a third user rating information set; Determine the first user rating information set, the second user rating information set and the third user rating information set as a user rating information set; Performing level mapping on the user rating information set to obtain a mapped user rating level information sequence; Performing grade marking on the user information corresponding to each mapped user rating grade information in the mapped user rating grade information sequence to obtain a marked user grade information sequence; Pushing the preset product information to the user devices corresponding to the respective annotated user level information in the annotated user level information sequence to obtain a push result set; Performing a preset level screening process on the marked user level information sequence corresponding to the push result in the push result set indicating the push failure, to obtain a screened user level information sequence; Performing security reinforcement on the filtered user level information sequence to obtain a reinforced user level information sequence; Extracting user feedback information from at least one user device corresponding to the reinforced user level information sequence to obtain an extracted user feedback information set; In response to determining that the feedback ratio corresponding to the extracted user feedback information in the extracted user feedback information set representing normal feedback is greater than a preset ratio threshold, the screened user level information sequence is stored in a shared database.

2. The method according to claim 1, wherein: After generating the user rating information set according to the bound data model set, the method further includes: Determine at least one user rating information in the user rating information set that is less than or equal to a preset rating threshold as an abnormal user information set; In response to detecting that a user corresponding to abnormal user information in the abnormal user information set accesses the shared database, intercepting abnormal users corresponding to each abnormal user information in the abnormal user information set to obtain an interception result; In response to determining that the interception result indicates successful interception, the abnormal user is added to a preset user list.

3. The method according to claim 2, wherein: The step of determining at least one user rating information in the user rating information set that is less than or equal to a preset rating threshold as an abnormal user information set includes: Determine at least one first scoring information in the first scoring information set of the user scoring information set that is less than or equal to the preset first scoring threshold as a first abnormal user information set; Determine at least one second scoring information in the second scoring information set of the user scoring information set that is less than or equal to the preset second scoring threshold as a second abnormal user information set; Determine at least one third scoring information in the third scoring information set in the user scoring information set that is less than or equal to the preset third scoring threshold as a third abnormal user information set; The first abnormal user information set, the second abnormal user information set and the third abnormal user information set are determined as abnormal user information sets.

4. A user information storage device, comprising: an acquisition unit, configured to acquire product information and at least one data source corresponding to the product information; The binding unit is configured to bind the product information with the at least one data source with a preset weight to obtain a bound data model set, wherein the binding of the product information with the at least one data source with a preset weight to obtain the bound data model set includes: In response to determining that the weight corresponding to the data source in the at least one data source is greater than or equal to a preset first weight value, binding the product information with the data source greater than or equal to the preset first weight value to obtain a bound first data model; In response to determining that the weight corresponding to the data source in the at least one data source is greater than or equal to a preset second weight value, the product information is bound to the data source whose weight is greater than or equal to the preset second weight value to obtain a second data model after binding; in response to determining that the weight corresponding to the data source in the at least one data source is greater than or equal to a preset third weight value, the product information is bound to the data source whose weight is greater than or equal to the preset third weight value to obtain a third data model after binding; Determine the first data model after binding, the second data model after binding and the third data model after binding as a data model set after binding; A generating unit is configured to generate a user rating information set according to the bound data model set, wherein the generating the user rating information set according to the bound data model set includes: In response to determining that a first bound data model in the bound data model set is called, determining rating information of the first bound data model for at least one user to obtain a first rating information set; Determine at least one first rating information in the first rating information set that is greater than a preset first rating threshold as a first user rating information set; In response to determining that a second bound data model in the bound data model set is called, determining that the second bound data model corresponds to rating information of at least one user of the first user rating information set, thereby obtaining a second rating information set; Determine at least one second rating information in the second rating information set that is greater than a preset second rating threshold as a second user rating information set; In response to determining that a third bound data model in the bound data model set is called, determining that the third bound data model corresponds to rating information of at least one user of the second user rating information set, thereby obtaining a third rating information set; Determine at least one third rating information in the third rating information set that is greater than a preset third rating threshold as a third user rating information set; Determine the first user rating information set, the second user rating information set and the third user rating information set as a user rating information set; A mapping unit, configured to perform level mapping on the user rating information set to obtain a mapped user rating level information sequence; A labeling unit is configured to label the user information corresponding to each mapped user rating grade information in the mapped user rating grade information sequence to obtain a labeled user grade information sequence; A push unit configured to push the preset product information to the user device corresponding to each annotated user level information in the annotated user level information sequence to obtain a push result set; A screening unit is configured to perform a preset level screening process on the marked user level information sequence corresponding to the push result indicating the push failure in the push result set to obtain a screened user level information sequence; A security reinforcement unit, configured to perform security reinforcement on the filtered user level information sequence to obtain a reinforced user level information sequence; an extraction unit configured to extract user feedback information from at least one user device corresponding to the reinforced user level information sequence to obtain an extracted user feedback information set; The storage unit is configured to store the screened user level information sequence in a shared database in response to determining that the feedback ratio corresponding to the extracted user feedback information representing normal feedback in the extracted user feedback information set is greater than a preset ratio threshold.

5. An electronic device comprising: one or more processors; a storage device having one or more programs stored thereon; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 3.

6. A computer readable medium having a computer program stored thereon, wherein: When the program is executed by a processor, the method according to any one of claims 1 to 3 is implemented.

Images