User data processing method and device based on user portrait and computer equipment

Abstract

The invention discloses a user data processing method and device based on a user portrait and computer equipment. The method comprises the following steps: acquiring target user data of a target user; based on a preset feature extraction strategy, obtaining current user features corresponding to the preset feature extraction strategy; obtaining a user tag corresponding to the current user feature, and forming a current user portrait; obtaining a target user portrait having the maximum user portrait similarity with the current user portrait in a user portrait library; and obtaining target user associated data of the target user portrait, and sending the target user associated data to a user terminal corresponding to the target user data. According to the embodiment of the invention, after a part of user data which the user terminal agrees to send is obtained from the user terminal in a user authorization mode, feature extraction and label conversion are carried out to obtain the user portrait, the user portrait and the user portrait library are compared and matched to obtain the target user portrait with the maximum similarity, and related data are obtained; and the acquisition efficiency of the target user portrait and the related data thereof is improved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a user data processing method, apparatus, and computer equipment based on user portraits. Background Art

[0002] Currently, with the continuous development of internet technology, the construction of user profiles based on acquired user data, and the push of relevant information based on user profiles, has been widely used in various technical fields such as financial technology, smart transportation, smart education, and online e-commerce. However, currently, when acquiring user data, each service server obtains rich user data containing both private and non-private data from the user terminal, then performs data pre-processing (such as desensitization) and feature engineering on the data before constructing the user profile. This makes user personal information vulnerable to leakage and reduces the security of user data. Summary of the Invention

[0003] The embodiments of the present invention provide a user data processing method, apparatus, and computer equipment based on user profiles, aiming to solve the problem in the prior art that business servers obtain user data by first obtaining rich user data including user privacy data and non-privacy data from user terminals, and then construct user profiles after performing data preprocessing and feature engineering, which makes user personal information easy to be leaked and reduces the security of user data.

[0004] In a first aspect, an embodiment of the present invention provides a method for processing user data based on user portraits, comprising:

[0005] In response to the user data processing instruction, obtaining target user data corresponding to the user data processing instruction and the user authorization acquisition instruction; wherein the target user data includes non-private data that the user agrees to send;

[0006] Based on a preset feature extraction strategy, obtaining current user features corresponding to the target user data;

[0007] Obtaining user tags corresponding to the current user features and forming a current user profile;

[0008] Obtaining a target user profile with the greatest user profile similarity to the current user profile from a pre-stored user profile library;

[0009] Target user associated data of the target user portrait is obtained, and the target user associated data is sent to a user terminal corresponding to the target user data.

[0010] In a second aspect, an embodiment of the present invention further provides a user data processing device based on user portraits, comprising:

[0011] a target user data acquisition unit, configured to, in response to a user data processing instruction, acquire target user data corresponding to the user data processing instruction and the user authorization acquisition instruction; wherein the target user data includes non-private data that the user agrees to send;

[0012] A current user feature acquisition unit, configured to acquire current user features corresponding to the target user data based on a preset feature extraction strategy;

[0013] A current user portrait acquisition unit, configured to acquire a user tag corresponding to the current user feature and form a current user portrait;

[0014] A target user portrait acquisition unit is used to acquire a target user portrait having the greatest user portrait similarity with the current user portrait from a pre-stored user portrait library;

[0015] The target user associated data acquisition unit is used to acquire the target user associated data of the target user portrait and send the target user associated data to the user terminal corresponding to the target user data.

[0016] In a third aspect, an embodiment of the present invention further provides a computer device comprising a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the method described in the first aspect is implemented.

[0017] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the method described in the first aspect can be implemented.

[0018] The embodiment of the present invention provides a user data processing method, device and computer equipment based on user portrait, the method comprising: in response to a user data processing instruction, obtaining target user data corresponding to the user data processing instruction and the user authorization acquisition instruction; wherein the target user data includes non-private data that the user agrees to send; based on a preset feature extraction strategy, obtaining the current user features corresponding to the target user data; obtaining the user tags corresponding to the current user features and forming the current user portrait; obtaining the target user portrait with the maximum user portrait similarity with the current user portrait in a pre-stored user portrait library; obtaining the target user associated data of the target user portrait, and sending the target user associated data to the user terminal corresponding to the target user data. The embodiment of the present invention can obtain part of the user data that the user terminal agrees to send from the user terminal in a user-authorized manner, perform feature extraction and label conversion to obtain a user portrait, compare and match the user portrait with the user portrait library to obtain the target user portrait with the maximum similarity and obtain related data, thereby improving the efficiency of obtaining the target user portrait and its related data. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0020] Figure 1 A schematic diagram of an application scenario of the user data processing method based on user portraits provided by an embodiment of the present invention;

[0021] Figure 2 A flowchart of a user data processing method based on user portraits provided by an embodiment of the present invention;

[0022] Figure 3 A schematic diagram of a sub-process of a user data processing method based on user portraits provided in an embodiment of the present invention;

[0023] Figure 4 A schematic diagram of another sub-flow of the user data processing method based on user portrait provided by an embodiment of the present invention;

[0024] Figure 5 A schematic diagram of another sub-flow of the user data processing method based on user portrait provided by an embodiment of the present invention;

[0025] Figure 6 A schematic block diagram of a user data processing device based on user portraits provided by an embodiment of the present invention;

[0026] Figure 7A schematic block diagram of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0027] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0028] It will be understood that when used in this specification and the appended claims, the terms “comprises” and “comprising” indicate the presence of described features, integers, steps, operations, elements and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof.

[0029] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the present invention. As used in the specification and appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0030] It should be further understood that the term "and / or" used in the present description and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0031] Please also refer to Figure 1 and Figure 2 ,in Figure 1 Schematic diagram of a scenario of a method for processing user data based on user portraits according to an embodiment of the present invention. Figure 2 FIG. 1 is a flow chart of a user data processing method based on user portrait provided by an embodiment of the present invention. Figure 1 As shown, the user data processing method based on user portrait provided by an embodiment of the present invention is applied to the server 10, and the server 10 is communicatively connected with the user terminal 20.

[0032] like Figure 2 As shown, the method includes the following steps S110-S150.

[0033] S110 . In response to a user data processing instruction, obtain target user data corresponding to the user data processing instruction and the user authorization acquisition instruction.

[0034] The target user data includes non-private data that the user agrees to send.

[0035] In this embodiment, the technical solution is described with the server as the execution entity. A user data processing platform is deployed on the server, and users log in to the platform using their user terminals and user accounts. Once the user's account passes the server's backend verification, to effectively protect the user's sensitive privacy data, the server can only combine the relevant non-sensitive privacy data corresponding to the user with the target user data. It should be noted that the data obtained by the server from the user terminal can only be sent when the user terminal detects the user authorization instruction triggered by the user authorization to obtain the data and send it to the server. Furthermore, in addition to obtaining the user's user data from the server itself, the server can also obtain historical user data corresponding to the user from a local database to form the target user data. This historical user data can also be legally and compliantly obtained by the server with the user's authorization over a certain historical period. The obtained target user data can be used to construct a subsequent user profile.

[0036] In one embodiment, if Figure 3 As shown, step S110 includes:

[0037] S111. Obtain a target user identifier corresponding to the user data processing instruction and the user authorization acquisition instruction;

[0038] S112: Acquire local target user non-privacy data corresponding to the target user identifier and stored in the server;

[0039] S113: Generate a terminal non-private data acquisition instruction corresponding to the target user identifier, and send the terminal non-private data acquisition instruction to the user terminal;

[0040] S114: Receive the target user's non-private data sent by the user terminal according to the terminal non-private data acquisition instruction, and a plurality of target user tags sent based on user authorization;

[0041] S115 . The target user data is composed of the local target user non-private data, the target user non-private data, and the plurality of target user tags.

[0042] In this embodiment, when the server needs to obtain the relevant data of the target user corresponding to the user data processing instruction and the user authorization acquisition instruction, it can first parse the user data processing instruction and the user authorization acquisition instruction to determine the target user at this time and the target user identifier corresponding thereto. After that, the server first locally obtains the local target user non-privacy data corresponding to the target user identifier, and these data are generally user data that has been desensitized. Then, the server also needs to obtain the target user non-privacy data from the user terminal of the target user, specifically by generating a terminal non-privacy data acquisition instruction corresponding to the target user identifier and sending it to the user terminal used by the target user. After the user terminal of the target user receives the terminal non-privacy data acquisition instruction, the terminal non-privacy data acquisition instruction can be parsed by the user terminal, and the required non-sensitive attribute data corresponding to the target user (each of these non-sensitive attribute data has a field name and a corresponding field value) and several user tags are obtained. Finally, the server receives the target user's non-private data and multiple target user tags sent by the target user's user terminal with the user's authorization. The target user data is composed of the local target user non-private data, the target user non-private data, and the multiple target user tags. This effectively protects the security of the user's data and prevents the server from obtaining the user's private data from the user terminal.

[0043] In one embodiment, after step S113, the method further includes:

[0044] A plurality of candidate user tags are obtained and sent to the user terminal in conjunction with the terminal non-privacy data acquisition instruction.

[0045] In this embodiment, when the server obtains multiple user tags from the target user's terminal, it no longer performs background data analysis based on the user data uploaded by the user terminal, which contains multiple sensitive sub-data. Instead, the target user can manually select a user tag from multiple candidate tags provided by the server and directly upload it to the server. This approach prevents the server from obtaining sensitive private data corresponding to the target user, while also enabling the server to obtain tag information corresponding to the target user based on the user tag selected by the target user from multiple candidate tags.

[0046] S120: Based on a preset feature extraction strategy, obtain current user features corresponding to the target user data.

[0047] In this embodiment, after the server obtains the target user data corresponding to the target user, it may perform feature extraction on each piece of attribute data included therein to obtain multiple user sub-features, thereby forming the current user feature.

[0048] In one embodiment, if Figure 4 As shown, step S120 includes:

[0049] S121, obtaining a natural language processing model in the feature extraction strategy;

[0050] S122: Acquire the local target user non-private data and a current user keyword set in the target user non-private data based on the natural language processing model;

[0051] S123: The current user feature is formed by the current user keyword set and the keywords corresponding to the multiple target user tags.

[0052] In this embodiment, in order to more quickly and accurately obtain user features from the target user data, a natural language processing model (i.e., an NLP model) in the feature extraction strategy can be first obtained. This natural language processing model is then used to obtain the current user keyword set from the local target user non-private data and the target user non-private data. For example, taking one of the attribute data in the target user non-private data as an example, where the field name is age and the field value is 30, the semantic information corresponding to this attribute data can be converted into "middle-aged" as the current user keyword after the natural language processing model obtains the semantic information. The above example is also used when the semantic understanding and keyword conversion of the local target user non-private data and other attribute data in the target user non-private data are performed based on the natural language processing model. Finally, after all current user keywords in the local target user non-private data and the target user non-private data are obtained, the current user features are formed by combining the current user keyword set and the keywords corresponding to the several target user tags. It can be seen that by combining the above method with natural language processing technology to quickly understand and convert non-label type data of user data, user features related to the target user can be quickly extracted.

[0053] S130: Obtain user tags corresponding to the current user features and compose a current user portrait.

[0054] In this embodiment, after the current user characteristics are obtained in the server based on the target user data, the current user keywords included in the current user characteristics cannot be directly used as user tags, and further processing is required to be converted into user tags. Only after the above processing is completed can the current user portrait be composed of the user tags corresponding to the current user characteristics.

[0055] In one embodiment, step S130 includes:

[0056] A local tag classification strategy is obtained, and based on the tag classification strategy, user tags corresponding to the keywords in the current user features are obtained to form the current user portrait.

[0057] In this embodiment, a tag classification engine can be pre-deployed in the server, and a tag classification strategy can be integrated into it. Afterwards, after the server obtains the current user characteristics of the target user, the tag classification engine is called to classify the keywords in the current user characteristics (mainly the keywords in the current user keyword set in the current user characteristics, and the several target user tags already included in the current user characteristics do not need to be specifically categorized by the tag classification strategy of the tag classification engine). For example, in addition to the current user keyword "middle-aged" in the above example, the current user characteristics also include the current user keyword "male". At this time, the tag classification strategy can simultaneously obtain the two current user keywords "middle-aged" and "male" and convert them into the user tag "middle-aged male".

[0058] The tag classification engine pre-sets multiple sets of user keyword combination relationships (e.g., the two current user keywords "middle-aged" and "male" in the above example have a user keyword combination relationship). Once each keyword in the current user's characteristics is converted into a user tag and these user tags are deduplicated, the current user profile can be formed. This allows for rapid acquisition of the current user profile through the tag classification and conversion method.

[0059] S140: Obtain a target user portrait having the greatest user portrait similarity to the current user portrait from a pre-stored user portrait library.

[0060] In this embodiment, after the server obtains the current user portrait of the target user, it can also obtain the target user portrait with the greatest user portrait similarity to the current user portrait from the user portrait library, and combine it with the relevant associated data corresponding to the target user portrait as reference data for the target user.

[0061] In one embodiment, if Figure 5 As shown, step S140 includes:

[0062] S141. Obtain current semantic vectors corresponding to all user tags in the current user portrait;

[0063] S142: Obtaining semantic vectors corresponding to respective user portraits in the user portrait library;

[0064] S143: Obtaining cosine similarity between the current semantic vector and the semantic vectors corresponding to each user portrait in the user portrait library, as user portrait similarity between the current user portrait and each user portrait in the user portrait library;

[0065] S144. From the semantic vectors corresponding to the user portraits in the user portrait library, obtain a semantic vector having the maximum cosine similarity with the current semantic vector as a target semantic vector;

[0066] S145. Obtain a user portrait corresponding to the target semantic vector as the target user portrait.

[0067] In this embodiment, when the user portraits in the user portrait library are obtained in the server and the user portrait has a user portrait similarity with the current user portrait, the current semantic vector corresponding to all user tags in the current user portrait is first obtained (because the user portrait can be regarded as a combination of multiple user tags, each user tag corresponds to a word vector, and then combined with the bag-of-words model, the multiple word vectors of the user portrait can be integrated to convert it into a semantic vector), as well as the semantic vectors corresponding to each user portrait in the user portrait library. Afterwards, the cosine similarity between the current semantic vector and the semantic vectors corresponding to each user portrait in the user portrait library is calculated, and it is regarded as the user portrait similarity between the current user portrait and each user portrait in the user portrait library. Finally, the semantic vector with the maximum cosine similarity with the current semantic vector is screened from the above multiple cosine similarities as the target semantic vector, and finally the user portrait corresponding to the target semantic vector is used as the target user portrait. It can be seen that, through the above method, the similarity matching process of the user portrait is converted into a semantic vector matching process, and the efficiency of obtaining the matching result is higher.

[0068] S150: Acquire target user associated data of the target user portrait, and send the target user associated data to a user terminal corresponding to the target user data.

[0069] In this embodiment, when the server obtains the target user portrait corresponding to the target user from the user portrait library, since the server has pre-set user association data for each user portrait in the user portrait library, the server can obtain the target user association data of the target user portrait and send the target user association data to the user terminal of the target user, thereby realizing timely data transmission of the target user association data for the target user to view in time.

[0070] In one embodiment, step S150 includes:

[0071] Acquire multi-dimensional associated attribute data of the target user portrait and form the target user associated data; wherein the multi-dimensional associated attribute data at least includes user estimated amount data.

[0072] In this embodiment, if the method of the present application is applied to a financial technology scenario as an example, if multi-dimensional associated attribute data of the target user portrait (such as at least user estimated amount data) is obtained, the multi-dimensional associated attribute data can be sent as reference data corresponding to the target user to its user terminal for timely viewing.

[0073] It can be seen that the embodiment of the method can obtain part of the user data that the user terminal agrees to send from the user terminal in a user-authorized manner, and then perform feature extraction and label conversion to obtain a user portrait. It compares and matches the user portrait with the user portrait library to obtain a target user portrait with the maximum similarity and obtains relevant data, thereby improving the efficiency of obtaining the target user portrait and its related data.

[0074] Figure 6 This is a schematic block diagram of a user data processing device based on user portraits provided by an embodiment of the present invention. Figure 6 As shown, corresponding to the above user data processing method based on user portrait, the present invention also provides a user data processing device 100 based on user portrait. The user data processing device 100 based on user portrait includes a unit for executing the above user data processing method based on user portrait. Figure 6 The user data processing device 100 based on user portrait includes: a target user data acquisition unit 110, a current user feature acquisition unit 120, a current user portrait acquisition unit 130, a target user portrait acquisition unit 140 and a target user associated data acquisition unit 150.

[0075] The target user data acquiring unit 110 is configured to, in response to a user data processing instruction, acquire target user data corresponding to the user data processing instruction and the user authorization acquiring instruction.

[0076] The target user data includes non-private data that the user agrees to send.

[0077] In this embodiment, the technical solution is described with the server as the execution entity. A user data processing platform is deployed on the server, and users log in to the platform using their user terminals and user accounts. Once the user's account passes the server's backend verification, to effectively protect the user's sensitive privacy data, the server can only combine the relevant non-sensitive privacy data corresponding to the user with the target user data. It should be noted that the data obtained by the server from the user terminal can only be sent when the user terminal detects the user authorization instruction triggered by the user authorization to obtain the data and send it to the server. Furthermore, in addition to obtaining the user's user data from the server itself, the server can also obtain historical user data corresponding to the user from a local database to form the target user data. This historical user data can also be legally and compliantly obtained by the server with the user's authorization over a certain historical period. The obtained target user data can be used to construct a subsequent user profile.

[0078] In one embodiment, the target user data acquiring unit 110 is specifically configured to:

[0079] Obtaining a target user identifier corresponding to the user data processing instruction and the user authorization acquisition instruction;

[0080] Acquire local target user non-privacy data corresponding to the target user identifier and stored in the server;

[0081] generating a terminal non-private data acquisition instruction corresponding to the target user identifier, and sending the terminal non-private data acquisition instruction to the user terminal;

[0082] receiving the target user's non-private data sent by the user terminal according to the terminal's non-private data acquisition instruction, and a plurality of target user tags sent based on user authorization;

[0083] The target user data is composed of the local target user non-private data, the target user non-private data and the multiple target user tags.

[0084] In this embodiment, when the server needs to obtain the relevant data of the target user corresponding to the user data processing instruction and the user authorization acquisition instruction, it can first parse the user data processing instruction and the user authorization acquisition instruction to determine the target user at this time and the target user identifier corresponding thereto. After that, the server first locally obtains the local target user non-privacy data corresponding to the target user identifier, and these data are generally user data that has been desensitized. Then, the server also needs to obtain the target user non-privacy data from the user terminal of the target user, specifically by generating a terminal non-privacy data acquisition instruction corresponding to the target user identifier and sending it to the user terminal used by the target user. After the user terminal of the target user receives the terminal non-privacy data acquisition instruction, the terminal non-privacy data acquisition instruction can be parsed by the user terminal, and the required non-sensitive attribute data corresponding to the target user (each of these non-sensitive attribute data has a field name and a corresponding field value) and several user tags are obtained. Finally, the server receives the target user's non-private data and multiple target user tags sent by the target user's user terminal with the user's authorization. The target user data is composed of the local target user non-private data, the target user non-private data, and the multiple target user tags. This effectively protects the security of the user's data and prevents the server from obtaining the user's private data from the user terminal.

[0085] In one embodiment, the target user data acquiring unit 110 is further specifically configured to:

[0086] A plurality of candidate user tags are obtained and sent to the user terminal in conjunction with the terminal non-privacy data acquisition instruction.

[0087] In this embodiment, when the server obtains multiple user tags from the target user's terminal, it no longer performs background data analysis based on the user data uploaded by the user terminal, which contains multiple sensitive sub-data. Instead, the target user can manually select a user tag from multiple candidate tags provided by the server and directly upload it to the server. This approach prevents the server from obtaining sensitive private data corresponding to the target user, while also enabling the server to obtain tag information corresponding to the target user based on the user tag selected by the target user from multiple candidate tags.

[0088] The current user feature acquisition unit 120 is configured to acquire the current user feature corresponding to the target user data based on a preset feature extraction strategy.

[0089] In this embodiment, after the server obtains the target user data corresponding to the target user, it may perform feature extraction on each piece of attribute data included therein to obtain multiple user sub-features, thereby forming the current user feature.

[0090] In one embodiment, the current user feature acquisition unit 120 is specifically configured to:

[0091] Obtaining a natural language processing model in the feature extraction strategy;

[0092] Acquire the local target user non-private data and a current user keyword set in the target user non-private data based on the natural language processing model;

[0093] The current user features are composed of the current user keyword set and the keywords corresponding to the multiple target user tags.

[0094] In this embodiment, in order to more quickly and accurately obtain user features from the target user data, a natural language processing model (i.e., an NLP model) in the feature extraction strategy can be first obtained. This natural language processing model is then used to obtain the current user keyword set from the local target user non-private data and the target user non-private data. For example, taking one of the attribute data in the target user non-private data as an example, where the field name is age and the field value is 30, the semantic information corresponding to this attribute data can be converted into "middle-aged" as the current user keyword after the natural language processing model obtains the semantic information. The above example is also used when the semantic understanding and keyword conversion of the local target user non-private data and other attribute data in the target user non-private data are performed based on the natural language processing model. Finally, after all current user keywords in the local target user non-private data and the target user non-private data are obtained, the current user features are formed by combining the current user keyword set and the keywords corresponding to the several target user tags. It can be seen that by combining the above method with natural language processing technology to quickly understand and convert non-label type data of user data, user features related to the target user can be quickly extracted.

[0095] The current user portrait acquisition unit 130 is configured to acquire a user tag corresponding to the current user feature and form a current user portrait.

[0096] In this embodiment, after the current user characteristics are obtained in the server based on the target user data, the current user keywords included in the current user characteristics cannot be directly used as user tags, and further processing is required to be converted into user tags. Only after the above processing is completed can the current user portrait be composed of the user tags corresponding to the current user characteristics.

[0097] In one embodiment, the current user portrait obtaining unit 130 is specifically configured to:

[0098] A local tag classification strategy is obtained, and based on the tag classification strategy, user tags corresponding to the keywords in the current user features are obtained to form the current user portrait.

[0099] In this embodiment, a tag classification engine can be pre-deployed in the server, and a tag classification strategy can be integrated into it. Afterwards, after the server obtains the current user characteristics of the target user, the tag classification engine is called to classify the keywords in the current user characteristics (mainly the keywords in the current user keyword set in the current user characteristics, and the several target user tags already included in the current user characteristics do not need to be specifically categorized by the tag classification strategy of the tag classification engine). For example, in addition to the current user keyword "middle-aged" in the above example, the current user characteristics also include the current user keyword "male". At this time, the tag classification strategy can simultaneously obtain the two current user keywords "middle-aged" and "male" and convert them into the user tag "middle-aged male".

[0100] The tag classification engine pre-sets multiple sets of user keyword combination relationships (e.g., the two current user keywords "middle-aged" and "male" in the above example have a user keyword combination relationship). Once each keyword in the current user's characteristics is converted into a user tag and these user tags are deduplicated, the current user profile can be formed. This allows for rapid acquisition of the current user profile through the tag classification and conversion method.

[0101] The target user portrait acquisition unit 140 is configured to acquire a target user portrait having the greatest user portrait similarity to the current user portrait from a pre-stored user portrait library.

[0102] In this embodiment, after the server obtains the current user portrait of the target user, it can also obtain the target user portrait with the greatest user portrait similarity to the current user portrait from the user portrait library, and combine it with the relevant associated data corresponding to the target user portrait as reference data for the target user.

[0103] In one embodiment, the target user portrait acquisition unit 140 is specifically configured to:

[0104] Obtaining current semantic vectors corresponding to all user tags in the current user portrait;

[0105] Obtaining semantic vectors corresponding to respective user portraits in the user portrait library;

[0106] Obtaining the cosine similarity between the current semantic vector and the semantic vectors corresponding to each user portrait in the user portrait library as the user portrait similarity between the current user portrait and each user portrait in the user portrait library;

[0107] From the semantic vectors corresponding to the user portraits in the user portrait library, a semantic vector having the maximum cosine similarity with the current semantic vector is obtained as a target semantic vector;

[0108] Obtain a user portrait corresponding to the target semantic vector as the target user portrait.

[0109] In this embodiment, when the user portraits in the user portrait library are obtained in the server and the user portrait has a user portrait similarity with the current user portrait, the current semantic vector corresponding to all user tags in the current user portrait is first obtained (because the user portrait can be regarded as a combination of multiple user tags, each user tag corresponds to a word vector, and then combined with the bag-of-words model, the multiple word vectors of the user portrait can be integrated to convert it into a semantic vector), as well as the semantic vectors corresponding to each user portrait in the user portrait library. Afterwards, the cosine similarity between the current semantic vector and the semantic vectors corresponding to each user portrait in the user portrait library is calculated, and it is regarded as the user portrait similarity between the current user portrait and each user portrait in the user portrait library. Finally, the semantic vector with the maximum cosine similarity with the current semantic vector is screened from the above multiple cosine similarities as the target semantic vector, and finally the user portrait corresponding to the target semantic vector is used as the target user portrait. It can be seen that, through the above method, the similarity matching process of the user portrait is converted into a semantic vector matching process, and the efficiency of obtaining the matching result is higher.

[0110] The target user associated data acquisition unit 150 is configured to acquire target user associated data of the target user portrait and send the target user associated data to a user terminal corresponding to the target user data.

[0111] In this embodiment, when the server obtains the target user portrait corresponding to the target user from the user portrait library, since the server has pre-set user association data for each user portrait in the user portrait library, the server can obtain the target user association data of the target user portrait and send the target user association data to the user terminal of the target user, thereby realizing timely data transmission of the target user association data for the target user to view in time.

[0112] In one embodiment, the target user associated data acquiring unit 150 is specifically configured to:

[0113] Acquire multi-dimensional associated attribute data of the target user portrait and form the target user associated data; wherein the multi-dimensional associated attribute data at least includes user estimated amount data.

[0114] In this embodiment, if the method of the present application is applied to a financial technology scenario as an example, if multi-dimensional associated attribute data of the target user portrait (such as at least user estimated amount data) is obtained, the multi-dimensional associated attribute data can be sent as reference data corresponding to the target user to its user terminal for timely viewing.

[0115] It can be seen that the embodiment of the device can obtain part of the user data that the user terminal agrees to send from the user terminal in a user-authorized manner, and then perform feature extraction and label conversion to obtain a user portrait. It compares and matches the user portrait with the user portrait library to obtain a target user portrait with the maximum similarity and obtains relevant data, thereby improving the efficiency of obtaining the target user portrait and its related data.

[0116] The above user data processing device based on user profile can be implemented in the form of a computer program. The computer program can be used in Figure 7 Runs on the computer equipment shown.

[0117] See also Figure 7 , Figure 7 This is a schematic block diagram of a computer device provided by an embodiment of the present invention. The computer device integrates any user profile-based user data processing device provided by an embodiment of the present invention.

[0118] See Figure 7 The computer device 400 includes a processor 402 , a memory, and a network interface 405 connected via a system bus 401 , wherein the memory may include a storage medium 403 and an internal memory 404 .

[0119] The storage medium 403 may store an operating system 4031 and a computer program 4032. The computer program 4032 includes program instructions, which, when executed, may enable the processor 402 to execute a user data processing method based on a user profile.

[0120] The processor 402 is used to provide computing and control capabilities to support the operation of the entire computer device.

[0121] The internal memory 404 provides an environment for the operation of the computer program 4032 in the storage medium 403. When the computer program 4032 is executed by the processor 402, the processor 402 can execute the above-mentioned user data processing method based on user portrait.

[0122] The network interface 405 is used to communicate with other devices through the network. Figure 7 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present invention and does not constitute a limitation on the computer device to which the solution of the present invention is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0123] The processor 402 is configured to execute a computer program 4032 stored in the memory to implement the user data processing method based on user portrait as described above.

[0124] It should be understood that in the embodiment of the present invention, the processor 402 may be a central processing unit (CPU), and the processor 402 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0125] Those skilled in the art will appreciate that all or part of the steps in the method of the above-described embodiment can be implemented by instructing the relevant hardware through a computer program. The computer program includes program instructions, which can be stored in a storage medium that is computer-readable. The program instructions are executed by at least one processor in the computer system to implement the steps in the method of the above-described embodiment.

[0126] Therefore, the present invention further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, wherein the computer program includes program instructions. When the program instructions are executed by a processor, the processor executes the user data processing method based on user profiles as described above.

[0127] The storage medium may be any computer-readable storage medium that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a magnetic disk, or an optical disk.

[0128] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the composition and steps of each example according to function. 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.

[0129] In the several embodiments provided herein, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the various units is merely a logical functional division, and actual implementation may employ other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be omitted or not implemented.

[0130] The steps in the methods of the embodiments of the present invention may be adjusted in order, combined, or deleted as needed. The units in the devices of the embodiments of the present invention may be combined, divided, or deleted as needed. Furthermore, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit.

[0131] If this integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the existing technology, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a personal computer, terminal, or network device, etc.) to execute all or part of the steps of the method described in various embodiments of the present invention.

[0132] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and such modifications or substitutions are intended to be within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be subject to the scope of protection of the claims.

Claims

1. A user data processing method based on user portrait, characterized in that: include: In response to the user data processing instruction, obtaining target user data corresponding to the user data processing instruction and the user authorization acquisition instruction; wherein the target user data includes non-private data that the user agrees to send; Based on a preset feature extraction strategy, obtaining current user features corresponding to the target user data; Obtaining user tags corresponding to the current user features and forming a current user profile; Obtaining a target user profile with the greatest user profile similarity to the current user profile from a pre-stored user profile library; Target user associated data of the target user portrait is obtained, and the target user associated data is sent to a user terminal corresponding to the target user data.

2. The method according to claim 1, characterized in that The acquiring of target user data corresponding to the user data processing instruction and the user authorization acquisition instruction includes: Obtaining a target user identifier corresponding to the user data processing instruction and the user authorization acquisition instruction; Acquire local target user non-privacy data corresponding to the target user identifier and stored in the server; generating a terminal non-private data acquisition instruction corresponding to the target user identifier, and sending the terminal non-private data acquisition instruction to the user terminal; receiving the target user's non-private data sent by the user terminal according to the terminal's non-private data acquisition instruction, and a plurality of target user tags sent based on user authorization; The target user data is composed of the local target user non-private data, the target user non-private data and the multiple target user tags.

3. The method according to claim 2, characterized in that After the step of generating a terminal non-private data acquisition instruction corresponding to the target user identifier and sending the terminal non-private data acquisition instruction to the user terminal, the method further includes: A plurality of candidate user tags are obtained and sent to the user terminal in conjunction with the terminal non-privacy data acquisition instruction.

4. The method according to claim 2, characterized in that The acquiring of the current user features corresponding to the target user data based on a preset feature extraction strategy includes: Obtaining a natural language processing model in the feature extraction strategy; Acquire the local target user non-private data and a current user keyword set in the target user non-private data based on the natural language processing model; The current user features are composed of the current user keyword set and the keywords corresponding to the multiple target user tags.

5. The method according to claim 4, characterized in that The obtaining of the user tag corresponding to the current user feature and forming a current user profile includes: A local tag classification strategy is obtained, and based on the tag classification strategy, user tags corresponding to the keywords in the current user features are obtained to form the current user portrait.

6. The method according to claim 1, characterized in that The step of obtaining a target user portrait having the greatest user portrait similarity to the current user portrait from a pre-stored user portrait library includes: Obtaining current semantic vectors corresponding to all user tags in the current user portrait; Obtaining semantic vectors corresponding to respective user portraits in the user portrait library; Obtaining the cosine similarity between the current semantic vector and the semantic vectors corresponding to each user portrait in the user portrait library as the user portrait similarity between the current user portrait and each user portrait in the user portrait library; From the semantic vectors corresponding to the user portraits in the user portrait library, a semantic vector having the maximum cosine similarity with the current semantic vector is obtained as a target semantic vector; Obtain a user portrait corresponding to the target semantic vector as the target user portrait.

7. The method according to claim 1, characterized in that The step of obtaining target user associated data of the target user portrait includes: Acquire multi-dimensional associated attribute data of the target user portrait and form the target user associated data; wherein the multi-dimensional associated attribute data at least includes user estimated amount data.

8. A user data processing device based on user portrait, characterized in that: include: a target user data acquisition unit, configured to, in response to a user data processing instruction, acquire target user data corresponding to the user data processing instruction and the user authorization acquisition instruction; wherein the target user data includes non-private data that the user agrees to send; A current user feature acquisition unit, configured to acquire current user features corresponding to the target user data based on a preset feature extraction strategy; A current user portrait acquisition unit, configured to acquire a user tag corresponding to the current user feature and form a current user portrait; A target user portrait acquisition unit is used to acquire a target user portrait having the greatest user portrait similarity with the current user portrait from a pre-stored user portrait library; The target user associated data acquisition unit is used to acquire the target user associated data of the target user portrait and send the target user associated data to the user terminal corresponding to the target user data.

9. A computer device, characterized in that: The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the user data processing method based on user portrait as described in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which includes program instructions. When the program instructions are executed by a processor, the user data processing method based on user portraits according to any one of claims 1 to 7 can be implemented.

Images