User portrait query method and device and related equipment
By performing target logical operations and bitmap data query on user query information, the problem of poor user portrait determination effect is solved, efficiency and accuracy are improved, and cost is reduced.
Patent Information
- Application Number
- CN202410994808.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-24
- Publication Date
- 2024-11-26
AI Technical Summary
The current user profile is poor, and the operation and maintenance cost of the big data analysis technology stack is relatively high and the efficiency is low.
Provide a user portrait query method, which performs target logical operations by receiving query information, generates composite query information, querys corresponding bitmap data from the target database, determines user portraits, and improves query efficiency and effect.
By performing target logical operations on query information, quickly query user portraits, improving the determination efficiency and accuracy of user portraits, and reducing operation and maintenance costs.
Smart Images

Figure CN119025521A_ABST
Abstract
Description
Technical Field
[0001] Embodiments of the present invention relate to the field of big data technology, and in particular, to a user portrait query method, device and related equipment. Background Art
[0002] With the continuous development of big data technology, it is usually necessary to use a customer data asset platform to store user data, and the customer data asset platform usually uses a big data analysis technology stack to analyze user data to obtain user portraits. However, due to the high operation and maintenance costs of the big data analysis technology stack and the low efficiency of determining user portraits, it can be seen that the current determination effect of user portraits is poor. Summary of the invention
[0003] The embodiments of the present invention provide a user portrait query method, apparatus and related equipment to solve the problem that the current determination effect of user portrait is poor.
[0004] To solve the above problems, the present invention is achieved as follows:
[0005] In a first aspect, an embodiment of the present invention provides a user portrait query method, comprising:
[0006] Receiving M query information, and performing target logic operation on the M query information to obtain composite query information;
[0007] Querying the second bitmap data corresponding to the composite query information from the N first bitmap data stored in the target database;
[0008] Determine a user portrait according to the second bitmap data;
[0009] Wherein, M and N are both integers greater than 1.
[0010] In a second aspect, an embodiment of the present invention provides a user portrait query device, including:
[0011] A receiving module, used for receiving M query information, and performing target logic operation on the M query information to obtain composite query information;
[0012] A query module, used to query the second bitmap data corresponding to the composite query information from the N first bitmap data stored in the target database;
[0013] A determination module, used to determine a user portrait according to the second bitmap data;
[0014] Wherein, M and N are both integers greater than 1.
[0015] In a third aspect, an embodiment of the present invention further provides an electronic device, comprising: a memory, a processor, and a program stored in the memory and executable on the processor; the processor is used to read the program in the memory to implement the steps in the method described in the first aspect above.
[0016] In a fourth aspect, an embodiment of the present invention further provides a readable storage medium for storing a program, wherein the program, when executed by a processor, implements the steps in the method described in the first aspect.
[0017] In a fifth aspect, an embodiment of the present invention further provides a computer program product, comprising computer instructions, which, when executed by a processor, implement the steps in the method described in the first aspect above.
[0018] In an embodiment of the present invention, M query information are received, and target logic operations are performed on the M query information to obtain composite query information; second bitmap data corresponding to the composite query information are queried from N first bitmap data stored in a target database; and a user portrait is determined based on the second bitmap data. In this way, by performing target logic operations on the M query information, the user portrait can be queried arbitrarily and quickly, thereby improving the efficiency of user portrait query and enhancing the effect of user portrait determination. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.
[0020] Figure 1 is a flow chart of a user portrait query method provided by an embodiment of the present invention;
[0021] Figure 2 is a schematic diagram of the corresponding relationship between Y and X provided in an embodiment of the present invention;
[0022] Figure 3 It is a structural schematic diagram of a user portrait query device provided by an embodiment of the present invention;
[0023] Figure 4 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0024] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0025] The terms "first", "second" etc. in the embodiments of the present invention are used to distinguish similar objects, and need not be used to describe a specific order or sequential order. In addition, the terms "include" and "have" and any variation thereof are intended to cover non-exclusive inclusions, for example, the process, method, system, product or equipment comprising a series of steps or units need not be limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or equipment. In addition, "and / or" is used in the present application to represent at least one of the connected objects, such as A and / or B and / or C, which represents 7 situations including single A, single B, single C, and A and B all exist, B and C all exist, A and C all exist, and A, B and C all exist.
[0026] See also Figure 1 , Figure 1 is a flow chart of a user portrait query method provided by an embodiment of the present invention. The embodiment of the present invention can be applied to a server, such as Figure 1 As shown, the user portrait query method may include the following steps:
[0027] Step 101: Receive M query information, and perform target logic operation on the M query information to obtain composite query information.
[0028] Among them, the query information can be information input by the user. Optionally, the user can input the above query information through an electronic device connected to the server, or, again optionally, the user can input the above query information through an external input device on the server, or, again optionally, the user can input the above query information through the touch display screen of the server.
[0029] The specific type of the target logical operation is not limited here. Optionally, the target logical operation may include at least one of the following: AND, OR, NOT.
[0030] For example, when the target logical operation includes AND, an AND operation (ie, AND operation) can be performed on M query information, so that composite query information can be obtained, and the composite query information can include the contents of the above M query information at the same time.
[0031] Step 102: Query the second bitmap data corresponding to the composite query information from the N first bitmap data stored in the target database.
[0032] The target database may refer to a Remote Dictionary Server (reids) database.
[0033] Among them, the first bitmap data can correspond to the user tag information, that is, the user tag information can be stored in the first bitmap data, and the user tag information stored in different first bitmap data is different, and the second bitmap data can be understood as the bitmap data corresponding to the composite query information in N first bitmap data, that is, the second bitmap data can be queried through the composite query information.
[0034] Step 103: determine the user portrait according to the second bitmap data; wherein M and N are both integers greater than 1.
[0035] Among them, the user portrait can be determined according to the label information corresponding to the second bitmap data.
[0036] It should be noted that the number of second bitmap data is not limited here. Optionally, the number of second bitmap data can be M, that is, the number of second bitmap data can correspond to the number of query information. In this way, the more the number of second bitmap data, the higher the accuracy of the finally determined user portrait.
[0037] In an embodiment of the present invention, through steps 101 to 103, M query information are received, and target logical operations are performed on the M query information to obtain composite query information; second bitmap data corresponding to the composite query information are queried from N first bitmap data stored in the target database; and the user portrait is determined based on the second bitmap data. In this way, by performing target logical operations on the M query information, the user portrait can be queried arbitrarily and quickly, thereby improving the efficiency of user portrait query and enhancing the effect of user portrait determination.
[0038] For example, when performing a portrait query on the user group as the front-end group, specifically when counting the high-value user portraits in group n, you can perform an AND operation (i.e., target logical operation) from the bitmaps with keys user_tag_0_1 (i.e., a certain first bitmap data) and user_tag_1_4 (another first bitmap data) in reids (i.e., the target database) to obtain the number of high-value users in group n (i.e., the second bitmap data). In this way, when redis has the bitmap data of all tag values, you can quickly and arbitrarily combine and query user portraits through logical operations.
[0039] As an optional implementation, before searching for second bitmap data corresponding to the composite query information from the N first bitmap data stored in the target database, the method further includes:
[0040] Extract information from the pre-acquired user data to obtain N user tag information;
[0041] The N user tag information is numerically processed to obtain the N first bitmap data, wherein the user tag information corresponds to the first bitmap data one by one, and the first bitmap data is stored in the target database in the form of numerical values.
[0042] The user data may be data stored on a server corresponding to a customer data platform (CDP).
[0043] Among them, information extraction is performed on the pre-acquired user data to obtain N user label information, which can be understood as: the user data can be called basic data, and by extracting information from the basic data, N user label information can be obtained, and the label type corresponding to each user label information can be different, that is, N types of user label information can be obtained through information extraction.
[0044] It should be noted that N user tag information can be stored in the tag table, so that the storage effect of N user tag information can be enhanced. At the same time, in order to improve the establishment efficiency and content richness of the entire tag system (i.e., the tag system composed of multiple user tag information), different user data can be obtained from the CDP at every preset period to extract different user tag information.
[0045] The above-mentioned obtaining different user data from the CDP at every preset period can also be understood as: obtaining different user data synchronously from the CDP at every preset period, and the synchronization method can be a structured query language (Structured Query Language server, SQL) synchronization method.
[0046] In the implementation manner of the present invention, N user tag information is numerically processed to obtain N first bitmap data, that is, the N user tag information is stored in the first bitmap data in a numerical form, thereby reducing the data volume of the N user tag information and further reducing the consumption of storage resources.
[0047] For example, user tag information may include a user_tags field, and the user_tags field may be stored in the form of a json array, and the storage form of the json array may be a numerical type.
[0048] As an optional implementation, the N user tag information includes: user attribute tag information and user behavior and hobby tag information, and the information extraction of the pre-acquired user data to obtain the N user tag information includes:
[0049] Obtaining a user attribute table and a behavior table in the user data;
[0050] Information is extracted from the user attribute table to obtain the user attribute label information, and information is extracted from the behavior table to obtain the user behavior preference label information.
[0051] The user attribute table may include a user identification (one id) field _sys_one_id of the user, and the user attribute table may also correspond to a placeholder.
[0052] It should be noted that there may be multiple user attribute tables, and the types of user attribute label information extracted from the multiple user attribute tables may be different. For example, user attribute label information may be divided into high-value users, medium-value users, low-value users, and the like.
[0053] The behavior table may store user behavior information, such as user behavior details. Thus, by extracting information from the behavior table, user behavior hobby label information may be obtained. For example, user behavior hobby label information may indicate that the user's favorite sports are running or playing basketball.
[0054] In the implementation manner of the present invention, information extraction is performed on the user attribute table and the behavior table respectively to obtain user attribute label information and user behavior preference label information respectively, thereby reducing the influence of interference information on the information extraction results, and further improving the accuracy of the obtained user attribute label information and user behavior preference label information.
[0055] As an optional implementation manner, the N user tag information further includes: user group tag information; the information extraction of the pre-acquired user data to obtain the N user tag information further includes:
[0056] Performing user grouping processing on at least part of the user data to obtain user grouping information;
[0057] The user grouping information is labeled to obtain the user grouping label information.
[0058] Among them, labeling the user grouping information to obtain the user grouping label information can be understood as: converting the user grouping information into the user grouping label information, for example: when the user grouping label information is 0, the user belongs to the user group; when the user grouping label information is 1, the user does not belong to the user group.
[0059] The user grouping label information may also be numerical information, that is, the user grouping label information may be numerically processed, thereby further reducing the data volume of the user grouping label information and further reducing the consumption of storage resources.
[0060] In the implementation manner of the present invention, user grouping label information can be obtained, thereby further increasing the diversity of types of user label information, that is, the user label information can be reflected in multiple dimensions.
[0061] It should be noted that user attribute label information, user behavior and hobby label information, and user group label information can be stored in a unified manner, reducing the amount of data storage. While achieving rapid determination of user portraits, it can also reduce product operation and maintenance costs.
[0062] It should be noted that when user attribute tag information, user behavior and hobby tag information, and user group tag information are stored in the target database in numerical form, the numerical values corresponding to the user attribute tag information, the numerical values corresponding to the user behavior and hobby tag information, and the numerical values corresponding to the user group tag information can be respectively referred to as enumeration values. In this way, by numerically processing the user tag information and storing the user tag information in numerical form, it can not only meet the upper-level data processing and query requirements, but also reduce the amount of data storage, further reducing costs and increasing efficiency.
[0063] For example: when the data stored in the user attribute table is user consumption behavior data, the user attribute label information can be user value label information, which can specifically include: high-value users, medium-value users, and low-value users. The self-incrementing ID when storing user value label information in MySQL is used to assign unique numerical identifiers (i.e., the numerical values corresponding to the user value label information) to the above-mentioned high-value users, medium-value users, and low-value users, as follows: high-value users (1), medium-value users (2), and low-value users (3). That is, the numerical value 1 indicates that the user value label information of the user is a high-value user, the numerical value 2 indicates that the user value label information of the user is a medium-value user, and the numerical value 3 indicates that the user value label information of the user is a low-value user.
[0064] In addition, the high-value users, medium-value users, and low-value users may be respectively assigned a unique storage address (position) in the user value tag system (the subscript of the json array of the user_tags field in the user_tag table).
[0065] When the first bitmap data is stored in the target database in the form of a numerical value, for example: the first placeholder in the numerical value is the value of the numeric subscript position of the label (that is, the numerical value of the position corresponding to the first placeholder is used to represent the user value label information of the user. For example, when the numerical value of the position corresponding to the first placeholder is 1, it indicates that the user value label information of the user is a high-value user), the second placeholder is the select statement of the user attribute label information (for example: the user attribute label information can be selected from the user consumption behavior details, and the _sys_one_id and user_tags fields must be included).
[0066] When the N user tag information also includes: user group tag information, the user group tag information can be regarded as a group tag, that is, a certain user either belongs to this group or does not belong to this group, that is, the user group tag information is: belongs to a certain group, and the tag enumeration value is: true, false. According to the above statement, when position is 1, the enumeration value is: true (4), false (5), that is, when the value of the first placeholder corresponding position is 4, it means that the user belongs to this group, and when the value of the first placeholder corresponding position is 5, it means that the user does not belong to this group.
[0067] Optionally, the user grouping tag information can be stored as follows: the first placeholder is the value of the tag's numeric subscript position, which is 1 in this implementation; the second placeholder is a false enumeration value: 5; the third placeholder is a true enumeration value: 4; and the fourth placeholder is the tag's select statement (user grouping data is selected from the user attribute table and behavior table, and must include the _sys_one_id and user_tags fields).
[0068] As an optional implementation manner, the numerical processing of the N user tag information to obtain the N first bitmap data includes:
[0069] Numerically processing the N user tag information to obtain N sample bitmap data, wherein the sample bitmap data corresponds to the user tag information one by one;
[0070] The N sample bitmap data are subjected to target processing to obtain the N first bitmap data, wherein the target processing is used to adjust the number of fields included in each sample bitmap data of the N sample bitmap data.
[0071] The specific method of target processing is not limited here. Optionally, the target processing may include deleting the number of fields, concatenating fields to increase the number of fields, etc.
[0072] In an implementation manner of the present invention, the number of fields included in each sample bitmap data in N sample bitmap data can be adjusted through target processing, thereby ensuring that the number of fields stored in the first bitmap data is maintained within a reasonable target range, reducing the amount of data and further reducing the consumption of storage resources.
[0073] As an optional implementation manner, the target processing of the N sample bitmap data to obtain the N first bitmap data includes:
[0074] Obtaining target data corresponding to each sample bitmap data, wherein the target data includes at least one of the following: the number of users corresponding to each sample bitmap data, the discreteness of user tag information, and the digitization processing time;
[0075] The number of fields included in each sample bitmap data is adjusted according to the target data corresponding to each sample bitmap data to obtain the N first bitmap data.
[0076] The user quantity may refer to the amount of user data stored in the sample bitmap data, the discreteness of the user tag information may refer to the dispersion degree of the user tag information, and the digitization processing time may refer to the duration of the digitization processing of the user tag information.
[0077] In the implementation manner of the present invention, the number of fields included in each sample bitmap data is adjusted according to the target data corresponding to each sample bitmap data. In this way, the flexibility and diversity of the adjustment method of the number of fields included in each sample bitmap data can be enhanced.
[0078] The following is an example of a specific embodiment to illustrate the implementation of the present invention:
[0079] The number of fields included in each sample bitmap data can be referred to as the number of ramn fields, the number of users can be referred to as the size of the user amount, and the discreteness of the user tag information can be referred to as the discreteness of the tag enumeration value. The details are as follows:
[0080] According to the amount of users of user data in CDP (i.e., the server storing user data), select the number of ramn fields, i.e., ram0 to ramn. Generally, the more users there are, the larger n is, so that the number of records of user_bitmap_tag_m can be guaranteed to maintain a stable value.
[0081] Assuming that the number of user data users in CDP is x, then the maximum number of records for m tags (the tag enumeration value has a maximum of y) is: x*y / 64*(n+1), but the discreteness of the enumeration value of tag m in the users covered by each tag_index will be less than or equal to y, so the actual number of records can be roughly expressed by the formula: x*tag enumeration discreteness / 64*(n+1). If the discreteness of the tag enumeration value remains unchanged, the more n there are, the greater the compression ratio of the number of data records, but at this time the storage capacity of each record is more (the number of ramn fields increases, so the storage capacity used is more 64*n), so it is necessary to measure whether the value of n is reasonable through the subsequent tag data bitmap time and the correlation analysis between the tag discreteness and n. In the embodiment of the present invention, n can be taken as 3 as an example (the initialization value of each tag).
[0082] Among them, user_tag_m_tag (m is the m tag, tag is the tag value in user_bitmap_tag_m), so each enumeration value of each tag is stored as a bitmap in redis (target database). Where bitIndex = tag_index*256+index (where tag_index is the tag_index value in user_bitmap_tag_m, and index is the position of 1 in the binary number of ram0 / ram1 / ram2 / ram3). The time complexity of the above processing is O(x*y / 64*(n+1)). The discreteness of the tag enumeration value of each tag_index is different, and the number of ramn fields is different, resulting in different processing time for each tag. In addition, the fitting relationship between the discreteness of the enumeration value of tag m and the number of ramn cannot be predicted during the first run. Therefore, the initial value of ramn is not the best value. The tag processing time (generation time of user_bitmap_tag_m table + bitmap processing time) of each tag m is recorded. The number of ramn fields processed each time is derived from the last processing time: first add 1 to the initial value n. If the processing time is less than the first run time, then the subsequent processing n is still added by 1. If the processing time is greater than the last operation, the subsequent processing n value is subtracted by 1. Therefore, the number of ramn in each processing converges to minimize the processing time. Finally, the number of ramn fluctuates slightly up and down under the scenario of minimizing the processing time.
[0083] It should be noted that the discreteness of the user tag information can be expressed as follows: After the above processing, the number of ramn at the minimum time of the tag bitmap can be obtained, and the discreteness of the enumeration value of each tag (that is, the discreteness of the user tag information) can be determined by the following method:
[0084] CV = σ / X;
[0085] Where CV is the coefficient of variation, σ is the sample standard deviation, and X is the sample mean. The sample is the enumeration value of the label of all users (that is, the value corresponding to the label information of N users). The CV of each label is obtained by the above formula to represent the discrete value of the label.
[0086] Let X be the value of CV, Y be the number of ramn, and through polynomial regression, the best fitting function of X and Y is obtained: y = a + b * x^2, see Figure 2 Therefore, when the sample values of X and Y are sufficient, the best fitting function of X and Y with the shortest bitmap time can be obtained, and the number of ramn can be predicted for the new label, which will greatly reduce the time of adaptive adjustment of ramn process.
[0087] Through the above method, the number of ramn fields is adjusted according to the size of the user volume and the discreteness of the tag enumeration value, that is, the data is maintained at a stable compression ratio. Because each tag has an isolated preprocessing table, the number of ramn fields can have different values according to the number of enumeration values of each tag. Therefore, the number of user_bitmap_tag_m records can be dynamically adjusted according to the number of users and the number of tag enumeration values, thereby ensuring that the data volume of user tag information is small and reducing the consumption of storage resources.
[0088] It should be noted that the prediction of the number of initialized ramns by using the polynomial regression technology reduces the time for adaptively adjusting the number of ramns.
[0089] It should be noted that the embodiment of the present invention utilizes a simple technology stack, namely mysql+bitmap+redis, so as to realize full-dimensional user tags (specifically including user attribute tag information, user behavior hobby tag information and user grouping tag information).
[0090] As an optional implementation manner, the numerical processing of the N user tag information to obtain the N first bitmap data includes:
[0091] Dynamically compressing the N user label information to obtain N sample label information;
[0092] The N sample label information is numerically processed to obtain the N first bitmap data.
[0093] Among them, the dynamic compression processing of N user tag information can be understood as: performing mysql bit operation on N user tag information, so as to realize dynamic compression processing, thereby providing data support for upper-level fast query.
[0094] Among them, the numerical processing of N sample label information can be understood as: converting the N sample label information into corresponding numerical values, for example: when the sample label information is a high-value user, the corresponding numerical value can be 100, and when the sample label information is a medium-value user, the corresponding numerical value can be 200.
[0095] In the implementation manner of the present invention, by sequentially performing dynamic compression processing and digitization processing on N user tag information, the amount of first bitmap data can be further reduced, thereby further reducing the consumption of storage resources.
[0096] See also Figure 3 , Figure 3 is a structural diagram of a user portrait query device provided by an embodiment of the present invention, such as Figure 3 As shown, the user portrait query device 300 includes:
[0097] The receiving module 301 is used to receive M query information and perform target logic operation on the M query information to obtain composite query information;
[0098] A query module 302, configured to query the second bitmap data corresponding to the composite query information from the N first bitmap data stored in the target database;
[0099] A determination module 303, configured to determine a user portrait according to the second bitmap data;
[0100] Wherein, M and N are both integers greater than 1.
[0101] As an optional implementation manner, the user portrait query device 300 further includes:
[0102] An information extraction module is used to extract information from pre-acquired user data to obtain N user tag information;
[0103] The numerical processing module is used to perform numerical processing on the N user tag information to obtain the N first bitmap data, wherein the user tag information corresponds to the first bitmap data one by one, and the first bitmap data is stored in the target database in the form of numerical values.
[0104] As an optional implementation, the N user tag information includes: user attribute tag information and user behavior and hobby tag information, and the information extraction module includes:
[0105] An acquisition submodule, used to acquire a user attribute table and a behavior table in the user data;
[0106] The information extraction submodule is used to extract information from the user attribute table to obtain the user attribute label information, and to extract information from the behavior table to obtain the user behavior preference label information.
[0107] As an optional implementation manner, the N user label information further includes: user group label information; the information extraction module further includes:
[0108] A grouping processing submodule, used to perform user grouping processing on at least part of the user data to obtain user grouping information;
[0109] The label processing submodule is used to perform label processing on the user grouping information to obtain the user grouping label information.
[0110] As an optional implementation, the digitization processing module includes:
[0111] A first numerical processing submodule is used to perform numerical processing on the N user tag information to obtain N sample bitmap data, where the sample bitmap data corresponds to the user tag information one by one;
[0112] The target processing submodule is used to perform target processing on the N sample bitmap data to obtain the N first bitmap data, wherein the target processing is used to adjust the number of fields included in each sample bitmap data in the N sample bitmap data.
[0113] As an optional implementation, the target processing submodule includes:
[0114] An acquisition unit, configured to acquire target data corresponding to each sample bitmap data, wherein the target data includes at least one of the following: the number of users corresponding to each sample bitmap data, the discreteness of user tag information, and the digitization processing time;
[0115] The adjusting unit is used to adjust the number of fields included in each sample bitmap data according to the target data corresponding to each sample bitmap data, so as to obtain the N first bitmap data.
[0116] As an optional implementation, the digitization processing module includes:
[0117] A dynamic compression processing submodule is used to perform dynamic compression processing on the N user label information to obtain N sample label information;
[0118] The second numerical processing submodule is used to perform numerical processing on the N sample label information to obtain the N first bitmap data.
[0119] The user portrait query device 300 can implement the embodiment of the present invention Figure 1 The various processes of the method embodiment and the same beneficial effects are achieved, and will not be described again here to avoid repetition.
[0120] The embodiment of the present invention also provides an electronic device. Figure 4 , the electronic device may include a processor 401, a memory 402, and a program 4021 stored in the memory 402 and executable on the processor 401. When the program 4021 is executed by the processor 401, Figure 1 Any steps in the corresponding method embodiments and achieving the same beneficial effects will not be repeated here.
[0121] A person skilled in the art can understand that all or part of the steps of implementing the above-mentioned embodiment method can be completed by hardware related to program instructions, and the program can be stored in a readable medium. The embodiment of the present invention also provides a readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the above-mentioned Figure 1 Any steps in the corresponding method embodiments can achieve the same technical effect and will not be described again here to avoid repetition.
[0122] The storage medium is, for example, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.
[0123] The embodiment of the present invention also provides a computer program product, including computer instructions, which can achieve the above-mentioned Figure 1 Any steps in the corresponding method embodiments can achieve the same technical effect and will not be described again here to avoid repetition.
[0124] The above is a preferred implementation of the embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.
Claims
1. A user portrait query method, characterized in that: include: Receiving M query information, and performing target logic operation on the M query information to obtain composite query information; Querying the second bitmap data corresponding to the composite query information from the N first bitmap data stored in the target database; Determine a user portrait according to the second bitmap data; Wherein, M and N are both integers greater than 1.
2. The method according to claim 1, characterized in that Before searching for the second bitmap data corresponding to the composite query information from the N first bitmap data stored in the target database, the method further includes: Extract information from the pre-acquired user data to obtain N user tag information; The N user tag information is numerically processed to obtain the N first bitmap data, the user tag information corresponds to the first bitmap data one by one, and the first bitmap data is stored in the target database in the form of numerical values.
3. The method according to claim 2, characterized in that The N user tag information includes: user attribute tag information and user behavior and hobby tag information. The information extraction of the pre-acquired user data obtains the N user tag information, including: Obtaining a user attribute table and a behavior table in the user data; Information is extracted from the user attribute table to obtain the user attribute label information, and information is extracted from the behavior table to obtain the user behavior preference label information.
4. The method according to claim 3, characterized in that The N user tag information also includes: user group tag information; the information extraction of the pre-acquired user data to obtain the N user tag information also includes: Performing user grouping processing on at least part of the user data to obtain user grouping information; The user grouping information is labeled to obtain the user grouping label information.
5. The method according to any one of claims 2 to 4, characterized in that The performing numerical processing on the N user tag information to obtain the N first bitmap data includes: Numerically processing the N user tag information to obtain N sample bitmap data, wherein the sample bitmap data corresponds to the user tag information one by one; The N sample bitmap data are subjected to target processing to obtain the N first bitmap data, wherein the target processing is used to adjust the number of fields included in each sample bitmap data of the N sample bitmap data.
6. The method according to claim 5, characterized in that The target processing of the N sample bitmap data to obtain the N first bitmap data includes: Obtaining target data corresponding to each sample bitmap data, wherein the target data includes at least one of the following: the number of users corresponding to each sample bitmap data, the discreteness of user tag information, and the numerical processing time; The number of fields included in each sample bitmap data is adjusted according to the target data corresponding to each sample bitmap data to obtain the N first bitmap data.
7. The method according to any one of claims 2 to 4, characterized in that The performing numerical processing on the N user tag information to obtain the N first bitmap data includes: Dynamically compressing the N user label information to obtain N sample label information; The N sample label information is numerically processed to obtain the N first bitmap data.
8. A user portrait query device, characterized in that: include: A receiving module, used for receiving M query information, and performing target logic operation on the M query information to obtain composite query information; A query module, used to query the second bitmap data corresponding to the composite query information from the N first bitmap data stored in the target database; A determination module, used to determine a user portrait according to the second bitmap data; Wherein, M and N are both integers greater than 1.
9. An electronic device, comprising: A memory, a processor, and a program stored in the memory and executable on the processor; characterized in that the processor is used to read the program in the memory to implement the steps in the user portrait query method as described in any one of claims 1 to 7.
10. A readable storage medium for storing a program, characterized in that: When the program is executed by a processor, the steps of the user portrait query method as described in any one of claims 1 to 7 are implemented.
11. A computer program product, characterized in that It includes computer instructions, which, when executed by a processor, implement the steps in the user portrait query method as described in any one of claims 1 to 7.
Citation Information
Patent Citations
User tag data storage method, device and system, equipment and storage medium
CN113434513A
Bitmap-based user data analysis method and device and computer equipment
CN114328632A
User tag processing method and device, electronic equipment and storage medium
CN116701713A
User portrait determination method and device, equipment and storage medium
CN117390045A
User data query method and device, equipment and storage medium
CN117951137A
