User classification method, device and equipment

Abstract

The embodiments of this specification provide a user classification method, device and equipment. The method includes: obtaining user information of a target user; dividing the user information into user classification information corresponding to at least one preset information category; calculating the category evaluation value of the target user corresponding to each preset information category according to the user classification information; combining the weight value corresponding to each preset information category and the category evaluation value to obtain the user evaluation result corresponding to the target user; determining the user category of the target user based on the user evaluation result; wherein different user categories correspond to different processing schemes; wherein different processing schemes occupy different processing resources. The above method evaluates the target user based on the information of the target user, and determines the user category according to the evaluation result to allocate different processing resources to process the user, thereby reducing the waste of time and resources.

Description

Technical Field

[0001] The embodiments of this specification relate to the field of big data technology, and in particular to a user classification method, device and equipment. Background Art

[0002] In real life, user monitoring is often involved in many scenarios. With the development of information technology and big data technology, user monitoring can collect various types of information corresponding to users based on user terminals, thereby achieving comprehensive and real-time monitoring of users.

[0003] However, in the actual application process, the system often needs to set up more operation nodes when monitoring users. Different operation nodes need to execute corresponding steps based on the corresponding instructions of the previous node, that is, the processing of each task will consume a long time and more resources. If a better monitoring effect is achieved for the user, it often takes more time and resources. When there are many monitored users, it is often impossible to allocate sufficient resources to each user, which seriously affects the monitoring process of the user. Therefore, there is an urgent need for a technical solution that can efficiently realize the monitoring of users. Summary of the invention

[0004] The purpose of the embodiments of this specification is to provide a user classification method, device and equipment to solve the problem of how to effectively allocate resources to ensure efficient execution of tasks.

[0005] In order to solve the above technical problems, the present application provides a user classification method, including:

[0006] Get the user information of the target user;

[0007] Classifying the user information into user classification information corresponding to at least one preset information category;

[0008] Calculate the category evaluation value of the target user corresponding to each preset information category according to the user classification information;

[0009] Combining the weight values ​​corresponding to the preset information categories and the category evaluation values, obtaining a user evaluation result corresponding to the target user;

[0010] The user category of the target user is determined based on the user evaluation result; wherein different user categories correspond to different processing solutions; wherein different processing solutions occupy different processing resources.

[0011] The embodiment of this specification also proposes a user classification device, including:

[0012] A user information acquisition module is used to obtain user information of a target user;

[0013] A user information classification module, used to classify the user information into user classification information corresponding to at least one preset information category;

[0014] A category evaluation value calculation module, used to calculate the category evaluation value of the target user corresponding to each preset information category according to the user classification information;

[0015] A user evaluation result obtaining module, used to obtain a user evaluation result corresponding to the target user by combining the weight values ​​corresponding to each preset information category and the category evaluation value;

[0016] The user category determination module is used to determine the user category of the target user based on the user evaluation result; wherein different user categories correspond to different processing solutions; wherein different processing solutions occupy different processing resources.

[0017] The embodiments of this specification also propose a user classification device, including a memory and a processor; the memory is used to store computer program instructions; the processor is used to execute the computer program instructions to implement the following steps: obtaining user information of a target user; dividing the user information into user classification information corresponding to at least one preset information category; calculating the category evaluation value of the target user corresponding to each preset information category according to the user classification information; combining the weight value corresponding to each preset information category and the category evaluation value to obtain a user evaluation result corresponding to the target user; determining the user category of the target user based on the user evaluation result; wherein different user categories correspond to different processing schemes; wherein different processing schemes occupy different processing resources.

[0018] It can be seen from the technical solutions provided by the above embodiments of this specification that, before determining the processing scheme for the target user, the embodiments of this specification first obtain the user information of the target user, and classify the user information according to the pre-set categories, and after evaluating the user classification information in each preset information category, determine the user evaluation result corresponding to the target user according to the weight value and category evaluation value corresponding to each preset information category, so that the user category corresponding to the target user and the corresponding processing scheme can be determined based on the user evaluation result, so that the corresponding processing resources can be allocated to the user. Before processing the user, the above scheme first evaluates the target user based on the target user's information, and determines the processing scheme according to the evaluation result, thereby ensuring the effective allocation of processing resources, improving the processing efficiency of the business, and reducing the waste of time and resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of this specification or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0020] Figure 1 This is a flow chart of a user classification method according to an embodiment of this specification;

[0021] Figure 2 This is a module diagram of a user classification device according to an embodiment of this specification;

[0022] Figure 3 This is a structural diagram of a user classification device according to an embodiment of this specification. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of this specification to clearly and completely describe the technical solutions in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this specification.

[0024] In order to solve the above technical problems, a user classification method is introduced in the embodiment of this specification. The execution subject of the method is a user classification device, which includes but is not limited to a server, an industrial computer, a PC, etc. Figure 1 As shown, the user classification method includes the following specific implementation steps.

[0025] S110: Obtain user information of the target user.

[0026] The target user is the user who may need to take monitoring measures. The target user may be some suspicious users, so it may be necessary to take monitoring measures for these suspicious users, or it may not be necessary to consume resources to monitor the target user. The specific monitoring plan needs to be determined after analyzing the target user.

[0027] The target users may be obtained by directly taking all users in the group as target users. For example, when selecting personnel in each department based on their integrity, all staff members in all departments may be taken as target users. The target users may also be obtained by screening all personnel using certain judgment conditions, determining certain suspicious users, and then taking these suspicious users as corresponding target users.

[0028] In actual applications, the method for determining the target user can be set according to specific needs and is not limited to the above examples, which will not be repeated here.

[0029] The user information may include various information describing the user, such as the user's personal information, or information about other persons or organizations associated with the user. Based on the user information, a character portrait of the target user can be achieved, so that the characteristics and properties of the user can be better described. In subsequent steps, the target user can also be judged based on the user information to determine the evaluation result of the target user.

[0030] In some implementations, the user information may include at least one of user profile information, user economic information, user social relationship information, and user work information.

[0031] The user profile information may include the target user's basic profile information, that is, information that can be obtained from the target user's personal profile. For example, the user profile information may include the target user's name, date of birth, address and other basic information, and may also include the target user's contact information, education experience, work resume, part-time work experience, assessment and evaluation records, judicial litigation records, travel records and other information in the basic profile.

[0032] In the embodiment, the purpose is to monitor the integrity of the target user, that is, when the target user is a leader or employee in a department, the user file information may also include the integrity file information of the target user, such as the target user's reward and punishment records, inspection records, violation handling records and other information.

[0033] The user economic information may be information related to the target user's economy, such as information corresponding to the target user's account or information belonging to the user's property. Specifically, it may be information such as the target user's bank account information, resource liability information, real estate information, related enterprise information, personal salary information, family member liability information, etc.

[0034] The user social relationship information may be information about other users who have a blood relationship or a strong social relationship with the target, and may include, for example, information about the target user's relatives, marital status, or details of major events that have occurred between the target user and his relatives.

[0035] The user work information may be corresponding information corresponding to the work file of the target user, for example, it may be the specific work situation, historical work information, deposit and loan information, purchase record information, etc. of the target user.

[0036] In actual applications, other information may also be selected as the user information corresponding to the target user, and is not limited to the above examples, which will not be described in detail here.

[0037] The specific method of obtaining the target user may be to directly retrieve the information in the user's electronic file, or to query the information of other accounts associated with the user based on the electronic file, so as to obtain the corresponding user information. Alternatively, an instruction to obtain the corresponding information may be sent to the target user, and the target user may feedback the relevant information required in the instruction. Accordingly, after receiving the information fed back by the target user, the fed back information may also be verified, and the subsequent steps may be performed using the user information after the verification is passed.

[0038] In actual applications, a corresponding method for obtaining the user information of the target user may be selected according to specific needs, and is not limited to the above examples, which will not be described in detail here.

[0039] S120: Divide the user information into user classification information corresponding to at least one preset information category.

[0040] The preset information category is a category obtained by pre-dividing the information. The preset information category can be set according to specific needs, and the user information in different preset information categories may have different degrees of influence on the evaluation results. Therefore, the preset information category can be classified according to the characteristics of the information itself, or it can be classified based on the degree of influence of different user information. The specific method of determining the preset information category can be set according to the needs of actual application, which will not be repeated here.

[0041] In some embodiments, the preset information category may include at least one of an income data category, an asset data category, a family information category, an assessment and evaluation category, a work information category, and a social relationship category.

[0042] The income data category can be used to cover information corresponding to various types of income of the user, such as the target user's work income information, part-time income information, and information on income obtained through other means.

[0043] The asset data category may be used to include information about the assets corresponding to the target user, such as real estate information belonging to the target user, inheritance information acquired by the target user, etc.

[0044] The family information category may be various information about the target user's family members, such as the family members' work, basic information, contacts, and other information.

[0045] The assessment and evaluation category may be information obtained after an assessment is conducted on the target user. The assessment may be an assessment conducted on the target user by the unit where the target user works, or by other individuals or organizations.

[0046] The work information category can be used to cover the work information of the target user or information related to work.

[0047] The social relationship category may be used to cover the social relationship information of the target user, for example, information of the target user's colleagues, relatives, or people with whom the target user has close daily contact, that is, information that can determine the target user's social relationship based on the social relationship information.

[0048] In actual applications, other classification methods may also be adopted, and are not limited to the preset information categories in the above implementation mode, and will not be described in detail here.

[0049] Since different categories of information may have different degrees of influence on the determination of the final result, by classifying different information and assigning certain weight values ​​to different preset information categories, the importance of different user information can be effectively combined to evaluate the target users in subsequent steps.

[0050] The user classification information is information corresponding to each preset information category after the user information is classified according to the preset information category.

[0051] Since there are certain differences in situations in actual applications, when multiple preset information categories are determined, there may not be corresponding user classification information corresponding to each preset information category, and there is no limitation on this.

[0052] In some implementations, the user information may be subjected to denoising before being divided. The acquired user information may contain certain noise data, such as missing data, inconsistent data, duplicate data, or erroneous data. In order to avoid interference of these noise data on the processing results in the subsequent use of the data, these data may be subjected to denoising. The specific method of denoising the user information may be set according to the needs of the actual application, and will not be described in detail here.

[0053] In some implementations, the user information may also be standardized before being divided. Since the acquired user information contains data from multiple sources or even multiple systems, for example, when the target user has multiple terminal devices, each terminal device corresponds to corresponding user information, or when the target user has accounts corresponding to multiple applications, these account information also correspond to information in different applications. The standardized processing is to correspond the data of different sources of the target user to the target user, and no longer divide the user information based on the source of information, so that a user portrait can be uniformly constructed for the target user based on information from different sources.

[0054] It should be noted that in actual applications, only denoising processing may be performed on the user information, only standardization processing may be performed on the user information, or both denoising processing and standardization processing may be performed on the user information at the same time. In the case of performing denoising processing and standardization processing at the same time, there is no restriction on the execution order of the two processing methods.

[0055] S130: Calculating the category evaluation value of the target user corresponding to each preset information category according to the user classification information.

[0056] After the user classification information is acquired, the category evaluation value of the target user corresponding to each preset information category may be calculated respectively according to the user classification information.

[0057] In some implementations, user portrait technology may be used to determine the category evaluation value of the target user corresponding to each preset information category. Specifically, various data of the target user may be visualized, so as to achieve a better description of the user in different preset information categories, effectively improving the accuracy of the description of the target user. The specific method of using user portrait technology to determine the category evaluation value can be set according to the needs of the actual application, and will not be repeated here.

[0058] In some implementations, an evaluation value calculation model may be used to calculate the category evaluation value of the target user corresponding to each preset information category. The evaluation value calculation model may process the user classification information to obtain the corresponding category evaluation value.

[0059] In the embodiments of the present specification, the evaluation value calculation model may be a mathematical model for determining the evaluation values ​​corresponding to the user classification information in different preset information categories. The evaluation value calculation model may be a classification model or a clustering model. Specifically, the evaluation value calculation model may be a Bayesian classification model, a support vector machine classification model (SVM), or a convolutional neural network classification model (CNN).

[0060] In some embodiments, after obtaining the evaluation value calculation model, the evaluation value calculation model can also be verified. The specific verification method can be, for example, to use the evaluation value calculation model to calculate certain verification information and analyze the calculation result. If the calculation result basically meets the verification information, the evaluation value calculation model can be applied to the above embodiment; if the calculation result does not meet the result corresponding to the verification information, the evaluation value calculation model can be adjusted according to the specific calculation result so that the adjusted model meets the actual needs. The specific method of verifying and adjusting the evaluation value calculation model can be set according to specific needs, and is not limited to the above example, and will not be repeated here.

[0061] S140: Combining the weight values ​​corresponding to the preset information categories and the category evaluation values, obtaining a user evaluation result corresponding to the target user.

[0062] After obtaining the category evaluation value, the user evaluation result corresponding to the target user can be obtained based on the category evaluation value and the weight value corresponding to each preset information category.

[0063] The weight values ​​are used to represent the weights of different preset information categories. Since in actual applications, different preset information categories may have different evaluation weights when determining the evaluation results of users, corresponding weight values ​​may be set for different preset information categories to effectively and reasonably use the information in each preset information category to calculate the evaluation results for the target user.

[0064] In some embodiments, when obtaining the weight value, the historical record information of at least one historical record user can be obtained first, and the information proportion corresponding to each preset information category can be determined based on the historical record information, and then the time decay degree corresponding to each preset information category can be calculated, so that the weight value corresponding to each preset information category can be determined respectively according to the information proportion and the time decay degree.

[0065] In some specific examples, the formula Calculate the information ratio, where w u,i is the proportion of information corresponding to the preset information category i, Among them, n u,i is the number of historical records of information items of user u corresponding to the preset information category i, m u is the number of all historical records of user u, n u,k is the number of information items corresponding to the preset information category k of user u, Among them, t i is the number of historically recorded users corresponding to user information category i, T is the number of preset information categories, t k is the number of historical record users corresponding to user information category k.

[0066] Based on the above example, we can use the formula Calculate the time decay degree, where f i is the time screening degree corresponding to the preset information category i, α and β are time attenuation coefficients, t is the current time, is the most recent entry time of the historical record information corresponding to the preset information category i.

[0067] Correspondingly, based on the above example, we can also use the formula Calculate the weight value, where: is the weight value corresponding to the preset information category i, f i is the time screening degree corresponding to the preset information category i, w u,i is the proportion of information corresponding to the preset information category i.

[0068] In actual applications, other methods may be used to obtain weight values ​​corresponding to various preset information categories as required, which are not limited to the above examples and will not be described in detail here.

[0069] In some embodiments, the user evaluation result may be an evaluation value, so as to achieve a quantitative evaluation of the target user. After obtaining the weight values ​​corresponding to each preset information category, the evaluation value corresponding to the target user may be calculated based on the weight values ​​and the category evaluation values ​​corresponding to each preset information category. Specifically, for example, the evaluation value corresponding to the target user may be obtained by weighted summation.

[0070] S150: Determine a user category of the target user based on the user evaluation result; wherein different user categories correspond to different processing solutions; wherein different processing solutions occupy different processing resources.

[0071] After obtaining the user evaluation result, the user category corresponding to the target user can be determined according to the user evaluation result. The user category classifies different target users so that they correspond to corresponding processing schemes. The processing scheme can be used to indicate the amount of processing resources allocated to the target user. For example, in the case where the target user has a good user evaluation result, a more relaxed processing scheme can be formulated to allocate fewer processing resources to the target user; in the case where the target user has a poor user evaluation result, more processing resources can be allocated to the target user to obtain a better processing result for the target user.

[0072] The processing resources may be time resources, i.e., the time consumed for processing users of different user categories; the processing resources may also be computing resources, etc. For example, in the case of a limited number of processes, different processes may be set as corresponding processing resources, and corresponding processing resources may be allocated according to the needs of users of different user categories. The processing resources are generally limited, so it is necessary to allocate the processing resources based on the needs of different processing solutions to ensure the effective processing of different processing solutions.

[0073] In some specific examples, the processing resources may be resources used to monitor the target user. For example, a certain process is allocated to obtain the information of the target user. Correspondingly, the processing resources may also be the time for monitoring the target user. In the case of limited processing resources, the time for monitoring a certain number of users is also limited, so corresponding time can be allocated for different processing to monitor different target users. In actual applications, the corresponding processing resources can also be determined based on other requirements, which are not limited to the above examples and will not be repeated here.

[0074] Based on the user evaluation results in step S140, that is, when the user evaluation results of the target user are normal users, suspicious users, and serious users, respectively, corresponding monitoring plans can be determined for the above user evaluation results. Accordingly, in the implementation, the monitoring plan can include a zero monitoring plan, a timed monitoring plan, and a real-time monitoring plan. When the user evaluation result is a normal user, the monitoring plan corresponding to the target user can be determined to be a zero monitoring plan; when the user evaluation result is a suspicious user, the monitoring plan corresponding to the target user can be determined to be a timed monitoring plan; when the user evaluation result is a serious user, the monitoring plan corresponding to the target user can be determined to be a real-time monitoring plan.

[0075] After the evaluation value of the target user is calculated, the user category corresponding to the evaluation value is determined according to the preset evaluation standard. Determining the user category corresponding to the target user by the preset evaluation standard can accurately and effectively determine the classification result.

[0076] In some embodiments, the preset evaluation criteria include a normal user judgment threshold and a severe user judgment threshold. Among them, the normal user judgment threshold is greater than the severe user judgment threshold. After obtaining the evaluation value corresponding to the target user, the evaluation value can be compared with the normal user judgment threshold and the severe user judgment threshold respectively. If the evaluation value is not less than the normal user judgment threshold, it is determined that the user category corresponding to the target user is a normal user category. If the evaluation value is less than the normal user judgment threshold and not less than the severe user judgment threshold, it can be determined that the user category corresponding to the target user is a suspicious user category. If the evaluation value is less than the severe user judgment threshold, it can be determined that the user category corresponding to the target user is a severe user category.

[0077] The normal user judgment threshold and the severe user judgment threshold can be set by the user, or can be trained based on samples to obtain the corresponding normal user judgment threshold and severe user judgment threshold. For example, multiple different thresholds are pre-set and the accuracy of the analysis results of different thresholds is determined to determine the final normal user judgment threshold and severe user judgment threshold. In actual applications, the severe user judgment threshold and the normal user judgment threshold can also be obtained by other methods, which are not limited to the above examples and will not be repeated here.

[0078] The normal user category can be used to indicate that after analyzing the target user, it is determined that the target user is relatively normal, and a more relaxed treatment plan can be adopted for the target user in the subsequent steps, and fewer processing resources can be allocated in the subsequent process; the suspicious user category indicates that the user is somewhat suspicious, and certain processing resources can be appropriately allocated to monitor the target user; the serious user category indicates that the target user is highly suspicious, and more processing resources need to be allocated to monitor the target user, such as real-time monitoring of users in the serious user category, etc. The specific way of processing different users according to different user categories can be set according to the needs of actual applications, and will not be repeated here.

[0079] Specifically, the zero monitoring scheme means that the corresponding monitoring resources may not be allocated to the normal users, that is, the normal users will not be monitored; the scheduled monitoring scheme means that the target users may be monitored regularly, for example, a certain longer monitoring period is selected, and the target is monitored every time the monitoring period is separated, so as to minimize the allocation of monitoring resources to the target users while ensuring the monitoring of the target users; the real-time monitoring scheme may mean that the target users are monitored at all times, and the real-time may be to obtain the information of the target users at all times to realize the monitoring of the target users, or to set a shorter monitoring time interval for the target users, and obtain the information corresponding to the target users every time the monitoring time interval to realize the corresponding monitoring results. In actual applications, the above-mentioned different monitoring schemes can be used and the corresponding monitoring schemes can be adjusted according to needs, which will not be elaborated here.

[0080] The embodiment of the above method is explained using a specific scenario example. When it is necessary to determine the corresponding monitoring plan for user A, the user information of user A can be obtained first, and the user information of the three users can be classified according to the user economic information, user work information and user profile information. The category evaluation values ​​of the three users in each category are determined based on the pre-trained evaluation value calculation model. It is assumed that the category evaluation values ​​of user A for the above three preset information categories are 4, 8, and 5 respectively. The predetermined weight values ​​corresponding to the above three preset information categories are 0.5, 0.2, and 0.3 respectively, and the user evaluation value can be calculated to be 5.1. Assuming that the preset normal user judgment threshold is 8 and the severe user judgment threshold is 5, it can be determined that the user evaluation result of user A is a suspicious user, and the user A can be monitored regularly to obtain the corresponding user information, that is, the monitoring plan corresponding to the user A is determined to be a scheduled monitoring plan.

[0081] Through the introduction of the embodiments and scenario examples of the above user classification method, it can be seen that before determining the processing scheme for the target user, the user information of the target user is first obtained, and the user information is classified according to the pre-set categories. After evaluating the user classification information in each preset information category, the user evaluation result corresponding to the target user is determined according to the weight value and category evaluation value corresponding to each preset information category, so that the user category corresponding to the target user and the corresponding processing scheme can be determined based on the user evaluation result, so that the corresponding processing resources can be allocated to the user. Before processing the user, the above scheme first evaluates the target user based on the target user's information, and determines the processing scheme according to the evaluation result, thereby ensuring the effective allocation of processing resources, improving the processing efficiency of the business, and reducing the waste of time and resources.

[0082] based on Figure 1 The corresponding user classification method introduces a user classification device in the embodiment of this specification. The user classification device can be set in the user classification device. Figure 2 As shown, the user classification device includes the following modules.

[0083] A user information acquisition module 210 is used to acquire user information of a target user;

[0084] A user information classification module 220, configured to classify the user information into user classification information corresponding to at least one preset information category;

[0085] A category evaluation value calculation module 230, configured to calculate the category evaluation value of the target user corresponding to each preset information category according to the user classification information;

[0086] A user evaluation result obtaining module 240 is used to obtain a user evaluation result corresponding to the target user by combining the weight values ​​corresponding to each preset information category and the category evaluation value;

[0087] The user category determination module 250 is used to determine the user category of the target user based on the user evaluation result; wherein different user categories correspond to different processing schemes; wherein different processing schemes occupy different processing resources.

[0088] based on Figure 1 Corresponding to the user classification method, the embodiment of this specification also provides a user classification device. Figure 3 As shown, the user classification device may include a memory and a processor.

[0089] In this embodiment, the memory may be implemented in any appropriate manner. For example, the memory may be a read-only memory, a mechanical hard disk, a solid-state hard disk, or a USB flash drive, etc. The memory may be used to store computer program instructions.

[0090] In this embodiment, the processor can be implemented in any appropriate manner. For example, the processor can take the form of a computer-readable medium such as a microprocessor or a processor and a computer-readable program code (such as software or firmware) that can be executed by the (micro)processor, a logic gate, a switch, an application-specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller, etc. The processor can execute the computer program instructions to implement the following steps: obtaining user information of the target user; dividing the user information into user classification information corresponding to at least one preset information category; calculating the category evaluation value of the target user corresponding to each preset information category according to the user classification information; combining the weight value corresponding to each preset information category and the category evaluation value, obtaining the user evaluation result corresponding to the target user; determining the user category of the target user based on the user evaluation result; wherein different user categories correspond to different processing schemes; wherein different processing schemes occupy different processing resources.

[0091] In the 1990s, improvements to a technology could be clearly distinguished as hardware improvements (for example, improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the method flow). However, with the development of technology, many improvements to the method flow today can be regarded as direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that an improvement in a method flow cannot be implemented using a hardware entity module. For example, a programmable logic device (PLD) (such as a field programmable gate array (FPGA)) is such an integrated circuit whose logical function is determined by the user's programming of the device. Designers can "integrate" a digital system on a PLD by programming it themselves, without having to ask a chip manufacturer to design and produce a dedicated integrated circuit chip. Moreover, nowadays, instead of manually making integrated circuit chips, this kind of programming is mostly implemented by "logic compiler" software, which is similar to the software compiler used when developing and writing programs, and the original code before compilation must also be written in a specific programming language, which is called hardware description language (HDL). There is not only one HDL, but many kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also know that it is only necessary to program the method flow slightly in the above-mentioned hardware description languages ​​and program it into the integrated circuit, and then it is easy to obtain the hardware circuit that implements the logic method flow.

[0092] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0093] It can be known from the above description of the implementation mode that the technicians in this field can clearly understand that the present specification can be implemented by means of software plus the necessary first hardware platform. Based on such an understanding, the technical solution of the present specification can be essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present specification or some parts of the embodiments.

[0094] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0095] This specification can be used in many first or special computer system environments or configurations, such as personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc.

[0096] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0097] Although the present specification is described through embodiments, those skilled in the art will appreciate that there are many modifications and changes to the present specification without departing from the spirit of the present specification, and it is intended that the appended claims include these modifications and changes without departing from the spirit of the present specification.

Claims

1. A user classification method, characterized in that: include: Get the user information of the target user; Classifying the user information into user classification information corresponding to at least one preset information category; Calculate the category evaluation value of the target user corresponding to each preset information category according to the user classification information; Combining the weight values ​​corresponding to each preset information category and the category evaluation value, obtaining a user evaluation result corresponding to the target user; the weight value is obtained by: obtaining historical record information of at least one historical record user; determining the information proportion corresponding to each preset information category according to the historical record information; calculating the time decay degree corresponding to each preset information category; Determine the weight value corresponding to each preset information category according to the information proportion and the time decay degree; Determining a user category of the target user based on the user evaluation result; wherein different user categories correspond to different processing solutions; wherein different processing solutions occupy different processing resources; The determining of the information proportion corresponding to each preset information category according to the historical record information includes: Using the formula Calculate the information ratio, where w u,i is the proportion of information corresponding to the preset information category i, Among them, n u,i is the number of historical records of information items of user u corresponding to the preset information category i, m u is the number of all historical records of user u, n u,k is the number of information items corresponding to the preset information category k of user u, Among them, t i is the number of historically recorded users corresponding to user information category i, T is the number of preset information categories, t k is the number of historical record users corresponding to user information category k; The determining of the weight value corresponding to each preset information category according to the information proportion and the time attenuation degree respectively includes: Using the formula Calculate the weight value, where: is the weight value corresponding to the preset information category i, f i is the time attenuation degree corresponding to the preset information category i, w u,i is the proportion of information corresponding to the preset information category i.

2. The method according to claim 1, characterized in that The user information includes at least one of user profile information, user economic information, user social relationship information, and user work information.

3. The method according to claim 1, characterized in that Before classifying the user information into user classification information corresponding to at least one preset information category, the method further includes: The user information is subjected to denoising processing.

4. The method according to claim 1, characterized in that Before classifying the user information into user classification information corresponding to at least one preset information category, the method further includes: The user information is standardized based on similarity of the user information.

5. The method according to claim 1, characterized in that The preset information categories include at least one of an income data category, an asset data category, a family information category, an assessment and evaluation category, a work information category, and a social relationship category.

6. The method according to claim 1, characterized in that The calculating, according to the user classification information, the category evaluation value of the target user corresponding to each preset information category includes: Based on the user classification information, an evaluation value calculation model is used to calculate the category evaluation value of the target user corresponding to each preset information category; the evaluation value calculation model includes a clustering model and / or a classification model.

7. The method according to claim 1, characterized in that The calculating of the time decay degree corresponding to each preset information category includes: Using the formula Calculate the time decay degree, where f i is the time decay degree corresponding to the preset information category i, α and β are the time decay coefficients, t is the current time, is the most recent entry time of the historical record information corresponding to the preset information category i.

8. The method according to claim 1, characterized in that The user evaluation result includes an evaluation value; and determining the user category of the target user based on the user evaluation result includes: The user category corresponding to the evaluation value is determined according to a preset evaluation standard.

9. The method according to claim 8, characterized in that The preset evaluation criteria include a normal user evaluation threshold and a severe user evaluation threshold, and the normal user evaluation threshold is greater than the severe user evaluation threshold; accordingly, determining the user category of the target user based on the user evaluation result includes: When the evaluation value is not less than the normal user judgment threshold, determining that the user category corresponding to the target user is a normal user category, or, When the evaluation value is less than the normal user judgment threshold and not less than the serious user judgment threshold, determining that the user category corresponding to the target user is a suspicious user category, or, When the evaluation value is less than the severe user judgment threshold, it is determined that the user category corresponding to the target user is a severe user category.

10. The method according to claim 9, characterized in that The processing scheme includes at least one of a real-time monitoring scheme, a timed monitoring scheme and a zero monitoring scheme; the processing resources occupied by the real-time monitoring scheme are more than the processing resources occupied by the timed monitoring scheme; The timed monitoring scheme occupies more processing resources than the zero monitoring scheme; Accordingly, the normal user corresponds to the zero monitoring scheme; the suspicious user category corresponds to the timed monitoring scheme; and the serious user category corresponds to the real-time monitoring scheme.

11. A user classification device, characterized in that: include: A user information acquisition module is used to obtain user information of a target user; A user information classification module, used to classify the user information into user classification information corresponding to at least one preset information category; A category evaluation value calculation module, used to calculate the category evaluation value of the target user corresponding to each preset information category according to the user classification information; The user evaluation result obtaining module is used to obtain the user evaluation result corresponding to the target user by combining the weight value corresponding to each preset information category and the category evaluation value; the weight value is obtained by: obtaining the historical record information of at least one historical record user; determining the information proportion corresponding to each preset information category according to the historical record information; calculating the time decay degree corresponding to each preset information category; Determine the weight value corresponding to each preset information category according to the information proportion and the time decay degree; A user category determination module, used to determine the user category of the target user based on the user evaluation result; wherein different user categories correspond to different processing schemes; wherein different processing schemes occupy different processing resources; The determining of the information proportion corresponding to each preset information category according to the historical record information includes: Using the formula Calculate the information ratio, where w u,i is the proportion of information corresponding to the preset information category i, Among them, n u,i is the number of historical records of information items of user u corresponding to the preset information category i, m u is the number of all historical records of user u, n u,k is the number of information items corresponding to the preset information category k of user u, Among them, t i is the number of historically recorded users corresponding to user information category i, T is the number of preset information categories, t k is the number of historical record users corresponding to user information category k; The determining of the weight value corresponding to each preset information category according to the information proportion and the time attenuation degree respectively includes: Using the formula Calculate the weight value, where: is the weight value corresponding to the preset information category i, f i is the time attenuation degree corresponding to the preset information category i, w u,i is the proportion of information corresponding to the preset information category i.

12. A user classification device, comprising a memory and a processor; The memory is used to store computer program instructions; The processor is used to execute the computer program instructions to implement the following steps: obtaining user information of a target user; dividing the user information into user classification information corresponding to at least one preset information category; calculating the category evaluation value of the target user corresponding to each preset information category according to the user classification information; obtaining a user evaluation result corresponding to the target user by combining the weight value corresponding to each preset information category and the category evaluation value; the weight value is obtained by: obtaining historical record information of at least one historical record user; determining the information proportion corresponding to each preset information category according to the historical record information; and calculating the time decay degree corresponding to each preset information category. Determine the weight value corresponding to each preset information category according to the information proportion and the time decay degree; determine the user category of the target user based on the user evaluation result; wherein, Different user categories have different corresponding processing solutions; different processing solutions occupy different processing resources; The determining of the information proportion corresponding to each preset information category according to the historical record information includes: Using the formula Calculate the information ratio, where w u,i is the proportion of information corresponding to the preset information category i, Among them, n u,i is the number of historical records of information items of user u corresponding to the preset information category i, m u is the number of all historical records of user u, n u,k is the number of information items corresponding to the preset information category k of user u, Among them, t i is the number of historically recorded users corresponding to user information category i, T is the number of preset information categories, t k is the number of historical record users corresponding to user information category k; The determining of the weight value corresponding to each preset information category according to the information proportion and the time attenuation degree respectively includes: Using the formula Calculate the weight value, where: is the weight value corresponding to the preset information category i, f i is the time attenuation degree corresponding to the preset information category i, w u,i is the proportion of information corresponding to the preset information category i.

Images