Attribute classification method and device and computer device

Abstract

The application relates to an attribute classification method and device, computer equipment, a storage medium and a computer program product. The attribute classification method comprises the following steps: obtaining historical data of a target object; calculating a first attribute value corresponding to the target object according to a preset interactive object label and historical information; calculating a second attribute value corresponding to the target object according to a referral identity label carried by the target object and a pre-stored label list; and determining a target classification attribute corresponding to the target object according to the first attribute value and the second attribute value. Through the arrangement, the attribute division of the target object can be more accurate, and the target classification attribute obtained finally can be more consistent with the actual attribute of the target object.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of big data processing, and in particular to an attribute classification method and device, computer equipment, a storage medium and a computer program product. BACKGROUND

[0002] With the advent of the era of big data, networked interaction processes are gradually emerging, and more and more functions can be implemented with the help of the Internet. Any interaction action will generate relevant interaction data, and in order to provide targeted services that meet actual needs, service providers generally distinguish customer attributes directly according to historical interaction data generated by customers.

[0003] However, the attribute classification methods commonly used are based on relevant data of customer historical behavior, which makes the final attribute classification result lag and unable to accurately reflect the attribute information of customers. SUMMARY

[0004] Therefore, it is necessary to provide an attribute classification method, device, computer equipment, storage medium and computer program product capable of accurately obtaining a customer attribute classification result.

[0005] In a first aspect, the present application provides an attribute classification method, comprising:

[0006] obtaining historical data of a target object;

[0007] calculating a first attribute value corresponding to the target object according to a preset interaction object label and the historical information;

[0008] calculating a second attribute value corresponding to the target object according to a referral identity label carried by the target object and a pre-stored label list;

[0009] determining a target classification attribute corresponding to the target object according to the first attribute value and the second attribute value.

[0010] In one embodiment, the historical data includes historical interaction data.

[0011] The calculating of the first attribute value corresponding to the target object according to the preset interaction object label and the historical information comprises:

[0012] calculating the first attribute value corresponding to the target object according to the interaction object label and the historical interaction data.

[0013] In one embodiment, the calculating of the first attribute value corresponding to the target object according to the interaction object label and the historical interaction data comprises:

[0014] filtering, from the historical interaction data, historical interaction data carrying the interaction object label;

[0015] calculating, according to the historical interaction data carrying the interaction object label, a first sub-attribute value corresponding to the target object;

[0016] determining, according to the historical interaction data, an interaction frequency value of the target object;

[0017] matching, from preset at least one interaction frequency range, an interaction frequency range to which the interaction frequency value belongs; the at least one interaction frequency range corresponds to at least one interaction frequency attribute value in one-to-one manner;

[0018] taking an interaction frequency attribute value corresponding to the matched interaction frequency range as a second sub-attribute value corresponding to the target object;

[0019] calculating the first attribute value according to the first sub-attribute value and the second sub-attribute value.

[0020] In one embodiment, the calculating, according to the historical interaction data carrying the interaction object label, the first sub-attribute value corresponding to the target object comprises:

[0021] determining a historical interaction number value of the historical interaction data carrying the interaction object label;

[0022] matching, from preset at least one interaction number value range, an interaction number value range to which the historical interaction number value belongs; the at least one interaction number value range corresponds to at least one interaction frequency attribute value in one-to-one manner;

[0023] taking an interaction frequency attribute value corresponding to the matched interaction number value range as the first sub-attribute value corresponding to the target object.

[0024] In one embodiment, the label list comprises a mapping relationship of at least one identity label and at least one referral number value;

[0025] The calculating, according to the referral identity label carried by the target object and the pre-stored label list, the second attribute value corresponding to the target object comprises:

[0026] matching, according to the referral identity label carried by the target object, a corresponding identity label from the label list;

[0027] taking a referral number value corresponding to the matched identity label as the second attribute value.

[0028] In one embodiment, the taking a referral number value corresponding to the matched identity label as the second attribute value comprises:

[0029] When the target object carries multiple referral identity tags, the referral values corresponding to the matched multiple identity tags are sorted in descending order;

[0030] The referral value with the highest ranking is taken as the second attribute value.

[0031] In one embodiment, the historical data includes historical operation data.

[0032] After obtaining the historical data of the target object, the method further includes:

[0033] According to the at least one login frequency range, the at least one task value range, and the historical operation data, a third attribute value corresponding to the target object is calculated.

[0034] In one embodiment, the calculation of the third attribute value corresponding to the target object according to the at least one login frequency range, the at least one task value range, and the historical operation data includes:

[0035] According to the historical operation data, a historical operation frequency of the target object is determined.

[0036] From the at least one login frequency range, a login frequency range to which the historical operation frequency belongs is matched; the at least one login frequency range corresponds to at least one login frequency attribute value one by one.

[0037] The login frequency attribute value corresponding to the matched login frequency range is taken as the third sub-attribute value corresponding to the target object.

[0038] The historical operation data is matched with at least one preset task condition to obtain a task value of the preset task condition that the historical operation data meets.

[0039] From the at least one task value range, a task value range to which the task value belongs is matched; the at least one task value range corresponds to at least one task value attribute value one by one.

[0040] The task value attribute value corresponding to the matched task value range is taken as the fourth sub-attribute value corresponding to the target object.

[0041] According to the third sub-attribute value and the fourth sub-attribute value, the third attribute value is calculated.

[0042] In one embodiment, the determination of the target classification attribute corresponding to the target object according to the first attribute value and the second attribute value includes:

[0043] According to the first attribute value, the second attribute value, the third attribute value, and preset first weight values, second weight values, and third weight values, a target attribute value corresponding to the target object is calculated;

[0044] From preset at least one attribute value range, an attribute value range corresponding to the target attribute value is matched; at least one attribute value range corresponds to at least one classification attribute one by one;

[0045] The classification attribute corresponding to the matched attribute value range is taken as a target classification attribute corresponding to the target object.

[0046] In a second aspect, the present application further provides an attribute classification device, comprising:

[0047] An acquisition module is configured to acquire historical data of a target object.

[0048] A first calculation module is configured to calculate a first attribute value corresponding to the target object according to preset interaction object labels and the historical information.

[0049] A second calculation module is configured to calculate a second attribute value corresponding to the target object according to a referral identity label carried by the target object and a pre-stored label list.

[0050] A determination module is configured to determine a target classification attribute corresponding to the target object according to the first attribute value and the second attribute value.

[0051] In a third aspect, the present application further provides a computer device. The computer device comprises a memory and a processor, the memory stores a computer program, and the processor implements the fault diagnosis method of any one of the above-mentioned embodiments when executing the computer program.

[0052] In a fourth aspect, the present application further provides a computer readable storage medium. The computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the fault diagnosis method of any one of the above-mentioned embodiments.

[0053] In a fifth aspect, the present application further provides a computer program product. The computer program product comprises a computer program, and the computer program product is executed by a processor to implement the fault diagnosis method of any one of the above-mentioned embodiments.

[0054] The attribute classification method, device, computer device, storage medium and computer program product can obtain interaction related data and operation related data generated by all interaction actions of a target object in the past, filter some specific data from the interaction related data according to a pre-set interaction object label, and calculate a first attribute value, so as to reflect the influence of a specific object that generates an interaction action with the target object and actual interaction content indicated by the interaction action on the attribute of the target object. The second attribute value can also be calculated according to a referral identity label carried by the target object, so as to reflect the influence of an associated object that provides attribute endorsement for the target object on the attribute of the target object. Through the above setting, the attribute division of the target object is more accurate, and the finally obtained target classification attribute can be more consistent with the actual attribute of the target object. BRIEF DESCRIPTION OF DRAWINGS

[0055] Figure 1 An application environment diagram of an attribute classification method in an embodiment;

[0056] Figure 2 A flowchart of an attribute classification method in an embodiment;

[0057] Figure 3 A flowchart of an attribute classification method in an embodiment;

[0058] Figure 4 A flowchart of an attribute classification method in an embodiment;

[0059] Figure 5 A flowchart of an attribute classification method in an embodiment;

[0060] Figure 6 A flowchart of an attribute classification method in an embodiment;

[0061] Figure 7 A flowchart of an attribute classification method in an embodiment;

[0062] Figure 8 A flowchart of an attribute classification method in an embodiment;

[0063] Figure 9 A flowchart of an attribute classification method in an embodiment;

[0064] Figure 10 A structural block diagram of an attribute classification device in an embodiment;

[0065] Figure 11 A structural block diagram of an attribute classification device in an embodiment;

[0066] Figure 12 An internal structure diagram of a computer device in an embodiment. DETAILED DESCRIPTION

[0067] In order to make the purposes, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and not used to limit the present application.

[0068] The attribute classification method provided by the embodiments of the present application can be applied to an application environment as shown in the figure. Figure 1 As shown in the figure, the terminal 102 communicates with the server 104 through the network.

[0069] For example, the attribute classification method is applied to the terminal 102. After receiving the instruction for classifying the attributes of the target object issued by the user through the human-computer interaction interface, the terminal 102 can obtain the historical data of the target object from the data storage system of the server 104. Then, the terminal 102 calculates the first attribute value corresponding to the target object according to the preset interactive object label and the historical information. And the terminal 102 calculates the second attribute value corresponding to the target object according to the referral identity label carried by the target object and the pre-stored label list. Finally, the terminal 102 determines the target classification attribute corresponding to the target object according to the first attribute value and the second attribute value. The terminal 102 can be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, Internet of Things devices and portable wearable devices. The Internet of Things device can be a smart speaker, a smart television, a smart air conditioner, a smart vehicle device, etc. The portable wearable device can be a smart watch, a smart bracelet, a head-mounted device, etc. The server 104 can be implemented by an independent server or a server cluster composed of multiple servers. The terminal 102 and the server 104 can be directly or indirectly connected through wired or wireless communication, such as network connection.

[0070] For another example, the attribute classification method is applied to the server 104. After receiving the instruction for classifying the attributes of the target object issued by the user through the human-computer interaction interface, the terminal 102 can send the instruction to the server 104. The server 104 obtains the historical data of the target object from the data storage system. Then, the server 104 calculates the first attribute value corresponding to the target object according to the preset interactive object label and the historical information. And the server 104 calculates the second attribute value corresponding to the target object according to the referral identity label carried by the target object and the pre-stored label list. Finally, the server 104 determines the target classification attribute corresponding to the target object according to the first attribute value and the second attribute value. It can be understood that the data storage system can be an independent storage device, or the data storage system is located on the server, or the data storage system is located on another terminal.

[0071] In an embodiment, a property classification method is provided, which is exemplified by being applied to a processor, which can be located on a terminal or a server.

[0072] As shown in Figure 2 the property classification method comprises:

[0073] Step 202, obtaining historical data of a target object.

[0074] The target object can be any account that has completed registration in advance on a specified platform, and the historical data can be interaction-related data and operation-related data generated based on all interaction actions generated by the account and any interaction object. The historical data can reflect all operations performed by the target object in the past.

[0075] Step 204, calculating a first property value corresponding to the target object according to a preset interaction object label and historical information.

[0076] The interaction object label can be composed of at least one of letters, characters or numbers, and can be used to identify an object that generates an interaction action with the target object, or to identify actual interaction content to which the interaction action of the target object refers.

[0077] According to the interaction object label, the processor can filter out historical information corresponding to the interaction object label from the historical information. The user can control the specific value of the first property value of the target object by deleting, modifying or adding the interaction object label.

[0078] The first property value is used to represent a score related to the interaction of the target object, and the first property value can reflect the influence of the object that generates the interaction action with the target object and the actual interaction content to which the interaction action refers on the property of the target object.

[0079] Step 206, calculating a second property value corresponding to the target object according to a referral identity label carried by the target object and a pre-stored label list.

[0080] The referral identity label can also be composed of at least one of letters, characters or numbers, and can be used to represent the identity of an associated object that provides property endorsement for the target object. The associated object can be an object that has completed property classification in the specified platform.

[0081] The referral identity tag carried by the target object can be automatically generated according to information input by the user when the user registers in advance on the designated platform. The process of automatically generating the referral identity tag may, for example, include: receiving text information input by the user on a human-computer interaction interface, the text information may include at least one information segment, matching the text information with at least one information segment of the identity of the pre-set associated object, wherein the at least one information segment corresponds to at least one referral identity tag in one-to-one correspondence, and mapping the referral identity tag corresponding to the matched information segment to the account corresponding to the target object.

[0082] The second attribute value is used to represent the score of the target object related to the associated object. The second attribute value can reflect the influence of the associated object providing attribute endorsement on the attribute of the target object.

[0083] Step 208, determining the target classification attribute corresponding to the target object according to the first attribute value and the second attribute value.

[0084] The target classification attribute is used to indicate the interaction habits or operation habits corresponding to different accounts.

[0085] As an example, the processor can take the sum of the first attribute value and the second attribute value as the final attribute value of the target object, match the final attribute value with at least one attribute value range, obtain the attribute value range to which the attribute value of the target object belongs, and at least one classification attribute corresponds to at least one attribute value range. The classification attribute corresponding to the attribute value range to which the attribute value of the target object belongs is taken as the target classification attribute.

[0086] In the above attribute classification method, the processor can obtain the interaction-related data and operation-related data generated by all past interaction actions of the target object, and according to the pre-set interaction object label, filter some specific data from the interaction-related data, calculate the first attribute value, and thus reflect the influence of the specific object that generates the interaction action with the target object and the actual interaction content indicated by the interaction action on the attribute of the target object. Further, the processor can also calculate the second attribute value according to the referral identity tag carried by the target object, so as to reflect the influence of the associated object providing attribute endorsement on the attribute of the target object. Through such a setting, the attribute division of the target object is more accurate, and the target classification attribute obtained finally can be more consistent with the actual attribute of the target object.

[0087] As shown in Figure 3 In some optional embodiments, the historical data includes historical interaction data; and step 204 includes: step 204a, calculating the first attribute value corresponding to the target object according to the interaction object label and the historical interaction data.

[0088] The historical interaction data refers to interaction-related data generated by the target object and any other object in the past. For example, the historical interaction data can refer to historical transaction data generated by the target object. Correspondingly, the historical transaction data can include interaction object information and interaction content information of the target object, and the interaction object information includes but is not limited to the interaction object name, the interaction object account, the interaction object identifier, etc. The interaction content information includes but is not limited to the interaction date, the interaction amount, the interaction number, the interaction state, etc.

[0089] As an example, the historical interaction data in the present embodiment can be transaction data generated by the target object and other objects in the past within a preset time length. The preset time length can be a fixed time period set in advance by the staff based on experience in the past attribute classification process, which can be one month or half a month.

[0090] In the present embodiment, when the processor obtains the historical interaction data, the processor can take the newly generated historical interaction data as a starting point to obtain all historical interaction data within the past preset time length, and calculate the first attribute value according to the interaction object label and all historical interaction data within the past preset time length, so as to reflect the influence of the specific object that generates the interaction action with the target object within the past preset time length and the actual interaction content represented by the interaction action on the attribute of the target object.

[0091] As shown in FIG. 2B, in some optional embodiments, step 204a includes: Figure 4

[0092] Step 2042, filtering historical interaction data carrying the interaction object label from the historical interaction data;

[0093] Step 2044, calculating the first sub-attribute value corresponding to the target object according to the historical interaction data carrying the interaction object label;

[0094] Step 2046, determining the interaction frequency value of the target object according to the historical interaction data;

[0095] Step 2048, matching the interaction frequency range to which the interaction frequency value belongs from the preset at least one interaction frequency range; the at least one interaction frequency range corresponds to the at least one interaction frequency attribute value in a one-to-one manner;

[0096] Step 20410, taking the interaction frequency attribute value corresponding to the matched interaction frequency range as the second sub-attribute value corresponding to the target object;

[0097] Step 20412, calculating the first attribute value according to the first sub-attribute value and the second sub-attribute value.

[0098] In the present embodiment, the interaction object label is used to identify the object that generates the interaction action with the target object. ​

[0099] The first sub-attribute value is used to characterize the score related to the interaction between the target object and a specific interactive object. The first sub-attribute value can reflect the impact of the specific interactive object that interacts with the target object on the target object's attributes.

[0100] The interaction frequency value refers to the frequency at which the target object interacts with any other object.

[0101] As an example, the processor calculates the interaction frequency of the target object within a preset time period based on all historical interaction data generated by the target object within the preset time period.

[0102] The interaction frequency attribute value is used to characterize the attribute value corresponding to each interaction frequency range, and the interaction frequency attribute value corresponding to each interaction frequency range can be preset.

[0103] The second sub-attribute value is used to characterize the score related to the frequency of interactive actions generated by the target object. The second sub-attribute value can reflect the impact of the frequency of interactive actions generated by the target object on the attributes of the target object.

[0104] The processor can add the first sub-attribute value and the second sub-attribute value, or multiply the first sub-attribute value and the second sub-attribute value by different weight values ​​and then add them together to obtain the first attribute value.

[0105] like Figure 5 As shown, in some optional embodiments, step 2044 includes:

[0106] Step 20442: Determine the historical interaction values ​​that carry historical interaction data with interactive object tags;

[0107] Step 20444: Match the interaction value range to which the historical interaction value belongs from at least one preset interaction value range; at least one interaction value range corresponds one-to-one with at least one interaction frequency attribute value;

[0108] Step 20446: Use the interaction frequency attribute value corresponding to the matched interaction value range as the first sub-attribute value of the target object.

[0109] like Figure 6 As shown, in some optional embodiments, the tag list includes a mapping relationship between at least one identity tag and at least one referral value; step 206 includes:

[0110] Step 2062: Match the corresponding identity tag from the tag list based on the referral identity tag carried by the target object;

[0111] Step 2064: Use the referral value corresponding to the matched identity tag as the second attribute value.

[0112] In one embodiment, when the target object carries multiple referral identity tags, step 206 sorts the referral values corresponding to the matched multiple identity tags in descending order, and takes the referral value with the highest order as the second attribute value.

[0113] In another embodiment, when the target object carries multiple referral identity tags, step 206 can match the referral value and the weight value corresponding to each referral identity tag from the mapping relationship between the tag list and the pre-set at least one identity tag and at least one weight value, and respectively multiply the referral value and the corresponding weight value to obtain the final second attribute value.

[0114] As an example, step 206 calculates the second attribute value using the following formula:

[0115] N=a1N1+a2N2+…anNn n N n

[0116] Wherein, N represents the second attribute value, a1 represents the weight value corresponding to the first referral identity tag carried by the target object, N1 represents the referral value corresponding to the first referral identity tag carried by the target object; a2 represents the weight value corresponding to the second referral identity tag carried by the target object, N2 represents the referral value corresponding to the second referral identity tag carried by the target object; an represents the weight value corresponding to the n-th referral identity tag carried by the target object, Nn represents the referral value corresponding to the n-th referral identity tag carried by the target object. n Wherein, N represents the second attribute value, a1 represents the weight value corresponding to the first referral identity tag carried by the target object, N1 represents the referral value corresponding to the first referral identity tag carried by the target object; a2 represents the weight value corresponding to the second referral identity tag carried by the target object, N2 represents the referral value corresponding to the second referral identity tag carried by the target object; an represents the weight value corresponding to the n-th referral identity tag carried by the target object, Nn represents the referral value corresponding to the n-th referral identity tag carried by the target object. n Wherein, N represents the second attribute value, a1 represents the weight value corresponding to the first referral identity tag carried by the target object, N1 represents the referral value corresponding to the first referral identity tag carried by the target object; a2 represents the weight value corresponding to the second referral identity tag carried by the target object, N2 represents the referral value corresponding to the second referral identity tag carried by the target object; an represents the weight value corresponding to the n-th referral identity tag carried by the target object, Nn represents the referral value corresponding to the n-th referral identity tag carried by the target object.

[0117] The identity tag can also be at least one of letters, characters or numbers. The identity tag is used to refer to any object that has completed attribute classification, and these objects that have completed attribute classification correspond to a referral value according to a pre-set mapping rule. The referral value is a kind of attribute value, which is used to reflect the influence of the object that has completed attribute classification on the attribute of the target object.

[0118] As shown in some optional embodiments, the historical data includes historical operation data. Figure 7

[0119] After step 2042, it further includes step 203: calculating the third attribute value corresponding to the target object according to the pre-set at least one login frequency range, at least one task value range and historical operation data.

[0120] ​Historical operation data refers to the data on various operations performed by the target account on a specified platform. This data can be stored in the operation logs of the target account, and may include information such as login actions, browsing duration, and page information viewed on the specified platform.

[0121] The third attribute value is used to characterize the score of the account corresponding to the target object in performing various operations on the specified platform. The third attribute value can reflect the impact of the account corresponding to the target object performing various operations on the specified platform on the attributes of the target object.

[0122] like Figure 8 As shown, in some optional embodiments, step 203 includes:

[0123] Step 2032: Determine the historical operation frequency of the target object based on historical operation data;

[0124] Step 2034: Match the login frequency range to which the historical operation frequency belongs from at least one login frequency range; at least one login frequency range corresponds one-to-one with at least one login frequency attribute value;

[0125] Step 2036: Use the login frequency attribute value corresponding to the matched login frequency range as the third sub-attribute value of the target object;

[0126] Step 2038: Match the historical operation data with at least one preset task condition to obtain the task value of the preset task condition that the historical operation data meets.

[0127] Step 20310: Match the task value range to which the task value belongs from at least one task value range; at least one task value range corresponds one-to-one with at least one task value attribute value;

[0128] Step 20312: Use the task value attribute value corresponding to the matched task value range as the fourth sub-attribute value of the target object;

[0129] Step 20314: Calculate the value of the third attribute based on the values ​​of the third and fourth sub-attributes.

[0130] The login frequency attribute value is used to represent the attribute value corresponding to each login frequency range, and the login frequency attribute value corresponding to each login frequency range can be preset.

[0131] The third sub-attribute value is used to characterize the score related to the frequency of the target object's login action. The third sub-attribute value can reflect the impact of the frequency of the target object's login action on the target object's attributes.

[0132] The fourth sub-attribute value is used to represent a score related to a number of historical operation data generated by the target object meeting the preset task condition, and the third sub-attribute value can reflect an influence of the number of historical operation data generated by the target object meeting the preset task condition on the attribute of the target object.

[0133] As shown in Figure 9 In some optional embodiments, step 208 includes:

[0134] Step 2082, calculating a target attribute value corresponding to the target object according to the first attribute value, the second attribute value, the third attribute value, and the preset first weight value, the second weight value and the third weight value.

[0135] Step 2084, matching an attribute value range corresponding to the target attribute value from at least one preset attribute value range; the at least one attribute value range corresponds to at least one classification attribute one by one.

[0136] Step 2086, taking the classification attribute corresponding to the matched attribute value range as a target classification attribute corresponding to the target object.

[0137] As an example, the first weight value, the second weight value and the third weight value can be set in advance by the staff according to the experience of previous attribute classification.

[0138] Further, since the first attribute value is composed of the first sub-attribute value and the second sub-attribute value, and the third attribute value is composed of the third sub-attribute value and the fourth sub-attribute value, correspondingly, the second weight value can also include a first sub-weight value and a second sub-weight value corresponding to the first sub-attribute value and the second sub-attribute value respectively, and the third weight value can also include a third sub-weight value and a fourth sub-weight value corresponding to the third sub-attribute value and the fourth sub-attribute value respectively.

[0139] As an example, the target attribute value is calculated in step 2082 using the following formula:

[0140] S=ω1A+ω2N+ω3V+ω4T+ω5R

[0141] Wherein, S represents the target attribute value, ω1 represents the first sub-weight value, A represents the first sub-attribute value; ω2 represents the second sub-weight value, N represents the second sub-attribute value; ω3 represents the second weight value, V represents the second attribute value; ω4 represents the third sub-weight value, T represents the third sub-attribute value; ω5 represents the fourth sub-weight value, and R represents the fourth sub-attribute value.

[0142] In the aforementioned attribute classification method, the processor can acquire all interaction-related data and operation-related data generated by the target object's past interactive actions. Based on pre-set interactive object tags, it filters specific data from the interaction-related data, calculates the first sub-attribute value and the second sub-attribute value respectively, and further calculates the first attribute value. This reflects the impact of the specific interactive object that interacts with the target object and the frequency of the target object's interactive actions on the target object's attributes. Furthermore, the processor can also calculate the second attribute value based on the referral identity tag carried by the target object, reflecting the impact of the associated object that provides attribute endorsement for the target object on the target object's attributes. Additionally, the processor can also filter specific data from the operation-related data based on preset login frequency ranges and task value ranges, calculate the third and fourth sub-attribute values ​​respectively, and further calculate the third attribute value. This reflects the impact of the frequency of the target object's login actions and the number of historical operation data generated by the target object that meet preset task conditions on the target object's attributes. Through this setting, the attribute classification of the target object becomes more accurate, and the final target classification attributes are more consistent with the actual attributes of the target object.

[0143] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0144] Based on the same inventive concept, this application also provides an attribute classification apparatus for implementing the attribute classification method described above. The solution provided by this apparatus is similar to the implementation described in the above method; therefore, the specific limitations in one or more attribute classification apparatus embodiments provided below can be found in the limitations of the memory data access method described above, and will not be repeated here.

[0145] In one embodiment, such as Figure 10 As shown, an attribute classification device 1000 is provided, including: an acquisition module 1002, a first calculation module 1004, a second calculation module 1006, and a determination module 1008, wherein:

[0146] The acquisition module 1002 is configured to acquire historical data of a target object.

[0147] The first calculation module 1004 is configured to calculate a first attribute value corresponding to the target object according to a preset interaction object label and historical information.

[0148] The second calculation module 1006 is configured to calculate a second attribute value corresponding to the target object according to a referral identity label carried by the target object and a pre-stored label list.

[0149] The determination module 1008 is configured to determine a target classification attribute corresponding to the target object according to the first attribute value and the second attribute value.

[0150] In some optional embodiments, the historical data includes historical interaction data.

[0151] The first calculation module 1004 is further configured to:

[0152] calculate the first attribute value corresponding to the target object according to the interaction object label and the historical interaction data.

[0153] In some optional embodiments, the first calculation module 1004 is further configured to:

[0154] filter historical interaction data carrying the interaction object label from the historical interaction data;

[0155] calculate a first sub-attribute value corresponding to the target object according to the historical interaction data carrying the interaction object label;

[0156] determine an interaction frequency value of the target object according to the historical interaction data;

[0157] match an interaction frequency range to which the interaction frequency value belongs from preset at least one interaction frequency range; the at least one interaction frequency range corresponds to at least one interaction frequency attribute value in a one-to-one manner;

[0158] take an interaction frequency attribute value corresponding to the matched interaction frequency range as a second sub-attribute value corresponding to the target object;

[0159] calculate the first attribute value according to the first sub-attribute value and the second sub-attribute value.

[0160] In some optional embodiments, the first calculation module 1004 is further configured to:

[0161] determine a historical interaction value of the historical interaction data carrying the interaction object label;

[0162] match an interaction value range to which the historical interaction value belongs from preset at least one interaction value range; the at least one interaction value range corresponds to at least one interaction frequency attribute value in a one-to-one manner;

[0163] The interaction frequency attribute value corresponding to the matched interaction value range is used as the first sub-attribute value of the target object.

[0164] In some optional embodiments, the tag list includes a mapping relationship between at least one identity tag and at least one referral value;

[0165] The second computing module 1006 is also configured as follows:

[0166] Based on the referral identity tag carried by the target object, the corresponding identity tag is matched from the tag list;

[0167] Use the referral value corresponding to the matched identity tag as the second attribute value.

[0168] In some optional embodiments, the second computing module 1006 is further configured to:

[0169] When the target object carries multiple referral identity tags, the referral values ​​corresponding to the matched identity tags will be sorted in descending order.

[0170] The referral value that appears first in the sort will be used as the second attribute value.

[0171] like Figure 11 As shown, in some optional embodiments, historical data includes historical operation data;

[0172] The attribute classification device 1000 also includes:

[0173] The third calculation module 1003 is used to calculate the third attribute value corresponding to the target object based on at least one preset login frequency range, at least one task value range, and historical operation data.

[0174] In some optional embodiments, the third computing module 1003 is further configured to:

[0175] Determine the historical operation frequency of the target object based on historical operation data;

[0176] Match the login frequency range to which the historical operation frequency belongs from at least one login frequency range; at least one login frequency range corresponds one-to-one with at least one login frequency attribute value;

[0177] The login frequency attribute value corresponding to the matched login frequency range is used as the third sub-attribute value of the target object;

[0178] Match historical operation data with at least one preset task condition to obtain the task value of the preset task condition that the historical operation data meets.

[0179] match the task value range to which the task value belongs from the at least one task value range; the at least one task value range corresponds to the at least one task value attribute value one by one;

[0180] take the task value attribute value corresponding to the matched task value range as the fourth sub-attribute value corresponding to the target object;

[0181] calculate the third attribute value according to the third sub-attribute value and the fourth sub-attribute value.

[0182] In some optional embodiments, the determining module 1008 is further configured to:

[0183] calculate the target attribute value corresponding to the target object according to the first attribute value, the second attribute value, the third attribute value, and the preset first weight value, the second weight value, and the third weight value;

[0184] match the attribute value range corresponding to the target attribute value from the preset at least one attribute value range; the at least one attribute value range corresponds to the at least one classification attribute one by one;

[0185] take the classification attribute corresponding to the matched attribute value range as the target classification attribute corresponding to the target object.

[0186] Each module in the attribute classification apparatus can be realized by software, hardware, and a combination thereof, in whole or in part. Each module can be embedded in or independent of a processor in a computer device in a hardware form, or can be stored in a memory in a computer device in a software form, so as to be called and executed by a processor to perform operations corresponding to each module.

[0187] In one embodiment, a computer device is provided, which can be a terminal, and an internal structure diagram of the computer device can be as shown in FIG. 8. Figure 12As shown in the figure. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. Among them, the processor, the memory and the input / output interface are connected through the system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control ability. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with the external terminal in a wired or wireless manner. The wireless manner can be realized through WIFI, mobile cellular network, NFC (near field communication) or other technologies. The computer program is executed by the processor to realize an attribute classification method. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or a key, trackball or touchpad arranged on the shell of the computer device, or an external keyboard, touchpad or mouse, etc.

[0188] Those skilled in the art can understand that, Figure 12 The skilled in the art can understand that,

[0189] In one embodiment, a computer readable storage medium is provided, and the computer readable storage medium stores a computer program. The computer program is executed by the processor to realize the steps of the attribute classification method.

[0190] In one embodiment, a computer program product is provided, and the computer program product includes a computer program. The computer program product is executed by the processor to realize the steps of the attribute classification method.

[0191] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (Read-Only Memory, ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive random access memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric memory (Ferroelectric Random Access Memory, FRAM), phase change memory (Phase Change Memory, PCM), graphene memory, etc. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, etc. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0192] Any combination of the technical features of the above embodiments can be made. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combination of the technical features does not exist contradictory, it should be considered as the scope of the present application.

[0193] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent of the present application. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are within the scope of protection of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. An attribute classification method, characterized in that, include: Acquire historical data of the target object; the historical data includes historical interaction data. Calculate the first attribute value corresponding to the target object based on the preset interactive object tags and historical information; Based on the referral identity tag carried by the target object and a pre-stored tag list, the second attribute value corresponding to the target object is calculated; the referral identity tag is used to characterize the identity of the associated object that provides attribute endorsement for the target object; the associated object is an object in the specified platform that has already completed attribute classification; Based on the first attribute value and the second attribute value, the target classification attribute corresponding to the target object is determined; The step of calculating the first attribute value corresponding to the target object based on the interaction object tag and the historical interaction data includes: Filter out historical interaction data carrying the tags of the interaction objects from the historical interaction data; Calculate the first sub-attribute value corresponding to the target object based on the historical interaction data carrying the tag of the interaction object; Based on the historical interaction data, determine the interaction frequency value of the target object; Match the interaction frequency range to which the interaction frequency value belongs from at least one preset interaction frequency range; at least one of the interaction frequency ranges corresponds one-to-one with at least one interaction frequency attribute value; The interaction frequency attribute value corresponding to the matched interaction frequency range is used as the second sub-attribute value of the target object; Calculate the first attribute value based on the first sub-attribute value and the second sub-attribute value; The tag list includes a mapping relationship between at least one identity tag and at least one referral value; The step of calculating the second attribute value corresponding to the target object based on the referral identity tag carried by the target object and a pre-stored tag list includes: Based on the referral identity tag carried by the target object, the corresponding identity tag is matched from the tag list; Use the referral value corresponding to the matched identity tag as the second attribute value.

2. The method according to claim 1, characterized in that, The step of calculating the first attribute value corresponding to the target object based on the preset interactive object tags and the historical information includes: Calculate the first attribute value corresponding to the target object based on the interaction object label and the historical interaction data.

3. The method according to claim 1, characterized in that, The step of calculating the first sub-attribute value corresponding to the target object based on historical interaction data carrying the interaction object tag includes: Determine the historical interaction values ​​carrying the historical interaction data of the interactive object tags; Match the historical interaction value to the corresponding interaction value range from at least one preset interaction value range; at least one of the interaction value ranges corresponds one-to-one with at least one interaction frequency attribute value; The interaction frequency attribute value corresponding to the matched interaction value range is used as the first sub-attribute value of the target object.

4. The method according to claim 1, characterized in that, The step of using the referral value corresponding to the matched identity tag as the second attribute value includes: When the target object carries multiple referral identity tags, the referral values ​​corresponding to the matched identity tags are sorted in descending order; The referral value that appears first in the sorted list will be used as the second attribute value.

5. The method according to claim 1, characterized in that, The historical data includes historical operation data; After obtaining the historical data of the target object, the process also includes: The third attribute value corresponding to the target object is calculated based on at least one preset login frequency range, at least one task value range, and the historical operation data.

6. The method according to claim 5, characterized in that, The step of calculating the third attribute value corresponding to the target object based on at least one preset login frequency range, at least one task value range, and the historical operation data includes: Based on the historical operation data, determine the historical operation frequency of the target object; The login frequency range to which the historical operation frequency belongs is matched from the at least one login frequency range; at least one login frequency range corresponds one-to-one with at least one login frequency attribute value; The login frequency attribute value corresponding to the matched login frequency range is used as the third sub-attribute value of the target object; The historical operation data is matched with at least one preset task condition to obtain the task value of the preset task condition that the historical operation data meets. Match the task value range to which the task value belongs from the at least one task value range; at least one task value range corresponds one-to-one with at least one task value attribute value. The task value attribute value corresponding to the matched task value range is used as the fourth sub-attribute value of the target object; The third attribute value is calculated based on the third sub-attribute value and the fourth sub-attribute value.

7. The method according to claim 5 or 6, characterized in that, The step of determining the target classification attribute corresponding to the target object based on the first attribute value and the second attribute value includes: The target attribute value corresponding to the target object is calculated based on the first attribute value, the second attribute value, the third attribute value, and the preset first weight value, second weight value, and third weight value. From at least one preset range of attribute values, match the range of attribute values ​​corresponding to the target attribute value; at least one range of attribute values ​​corresponds one-to-one with at least one classification attribute; The category attribute corresponding to the matched attribute value range is taken as the target category attribute of the target object.

8. An attribute classification device, characterized in that, include: The acquisition module is used to acquire historical data of the target object; the historical data includes historical interaction data. The first calculation module is used to calculate the first attribute value corresponding to the target object based on the preset interactive object tags and historical information. The second calculation module is used to calculate the second attribute value corresponding to the target object based on the referral identity tag carried by the target object and a pre-stored tag list; the referral identity tag is used to characterize the identity of the associated object that provides attribute endorsement for the target object; the associated object is an object in the specified platform that has already completed attribute classification; The determining module is used to determine the target classification attribute corresponding to the target object based on the first attribute value and the second attribute value; The first calculation module is further configured to filter out historical interaction data carrying the interaction object tag from the historical interaction data; and calculate the first sub-attribute value corresponding to the target object based on the historical interaction data carrying the interaction object tag. Based on the historical interaction data, determine the interaction frequency value of the target object; The interaction frequency range to which the interaction frequency value belongs is matched from at least one preset interaction frequency range; at least one interaction frequency range corresponds one-to-one with at least one interaction frequency attribute value; the interaction frequency attribute value corresponding to the matched interaction frequency range is used as the second sub-attribute value corresponding to the target object; the first attribute value is calculated based on the first sub-attribute value and the second sub-attribute value. The tag list includes a mapping relationship between at least one identity tag and at least one referral value; The second calculation module is further configured to match the corresponding identity tag from the tag list based on the referral identity tag carried by the target object; and use the referral value corresponding to the matched identity tag as the second attribute value.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the attribute classification method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the attribute classification method according to any one of claims 1 to 7.

11. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the attribute classification method according to any one of claims 1 to 7.

Images