Method for acquiring target category label, electronic equipment and storage medium

Abstract

The invention provides a method for obtaining a target category label, electronic equipment and a storage medium, and relates to the technical field of APP classification, the method comprises the following steps: obtaining a first key label corresponding to a target APP name according to a category label of an APP in a preset third-party application downloading platform in the preset third-party application downloading platform, further acquiring a second key APP name list corresponding to the first key tag, and acquiring a second key tag list and a third key tag list acquired from the second key APP name list based on target category tags of APPs of which target category tags are not NULL in a target database, and according to the number of the second key tags which are the same as the third key tags in the second key tag list, the target category tag of the target APP is determined, the influence caused by the downloading amount and popularity of the target APP is reduced in the process of obtaining the target category tag, and the accuracy of obtaining the target category tag is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of APP classification, and in particular to a method for obtaining a target category label, an electronic device and a storage medium. Background Art

[0002] In the target database, due to the rapid uploading of new apps, omissions or errors in the automated classification process, delays in manual classification, information loss during data migration or integration, changes in category definitions, inaccurate information submitted by users, and apps with functions spanning multiple categories, there are a large number of unclassified apps in the target database, namely, target apps. Classifying the target apps and obtaining their category labels in the target database, namely, target category labels, is an effective way to organize and manage target apps. In the prior art, the method for obtaining the target category label of the target app is to directly reference the category label in a third-party application download platform, and use the category label of the target app in the third-party application download platform as the target category label of the target app.

[0003] However, the above method also has the following technical problems:

[0004] For apps with low download volume or low popularity, third-party app download platforms may not have enough attention or resources to provide accurate category labels for the apps. Therefore, when the target app has low download volume or low popularity, the accuracy of the target category label obtained based on the above method is low. Summary of the invention

[0005] In view of the above technical problems, the technical solution adopted by the present invention is:

[0006] According to a first aspect of the present invention, a method for obtaining a target category label is provided, where the target category label is a category label of an APP in a target database, and the method comprises the following steps:

[0007] S1. Get the target APP name list A = {A 1 , A 2 , …, A i , …, A m}, A i is the name of the i-th target APP, the value of i ranges from 1 to m, m is the number of target APP names, the target APP name is the name of the target APP, and the target APP is the APP with the target category label of NULL in the target database.

[0008] S2, according to the first key APP name list B = {B 1 , B 2 , …, B j , …, Bn}, get the first key tag list C corresponding to A = {C 1 , C 2 , …, C i , …, C m}, where A i =B j When B j The corresponding third-party category label is C i , B j is the jth first key APP name, j ranges from 1 to n, n is the number of first key APP names, C i A i The corresponding first key tag, the first key APP name is the name of the first key APP, the first key APP is an APP in the preset third-party application download platform, and the third-party category tag is the category tag of the first key APP in the preset third-party application download platform.

[0009] S3, traverse B, when B j The corresponding third-party category label and C i If the same, j As C i The corresponding second key APP name to obtain C i Corresponding second key APP name list D i ={D i1 , D i2 , …, D ie , …, D if(i)}, D ie C i The corresponding e-th second key APP name, the value of e is 1 to f(i), f(i) is C i The number of corresponding second key APP names.

[0010] S4, according to the intermediate APP name list E = {E 1 , E 2 ,…,E r ,…,E s}, get D i The corresponding second key tag list F i ={F i1 , F i2 , …, F ie , …, F if(i)}, and for F i1 , F i2 , …, F ie , …, F if(i) Perform deduplication to obtain D i The corresponding third key tag list G i = {Gi1 , G i2 , …, G ik , …, G it(i)}, where D ie =E r When E r The corresponding target category label is F ie , E r is the name of the rth intermediate APP, r ranges from 1 to s, s is the number of intermediate APP names, the intermediate APP name is the name of the intermediate APP, and the intermediate APP is the APP whose target category label is not NULL in the target database. ie D ie The corresponding second key tag, G ik D i The corresponding kth third key tag, k ranges from 1 to t(i), t(i) is D i The number of corresponding third key tags.

[0011] S5, when G 0 ik =max(G 0 i1 , G 0 i2 , …, G 0 ik , …, G 0 it(i) ),G ik As A i The corresponding target category label of the target APP, G 0 ik F i1 , F i2 , …, F ie , …, F if(i) Middle and G ik The number of identical second key tags. max() is the maximum value acquisition function.

[0012] According to a second aspect of the present invention, a non-transitory computer-readable storage medium is provided, in which a computer program is stored. The computer program is loaded and executed by a processor to implement the aforementioned method.

[0013] According to a third aspect of the present invention, there is provided an electronic device, comprising: a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor implements the aforementioned method when executing the computer program.

[0014] The present invention has at least the following beneficial effects:

[0015] The present invention provides a method for obtaining a target category label, an electronic device and a storage medium. The method can obtain a first key label corresponding to a target APP name according to a third-party category label corresponding to a first key APP name, wherein the first key APP is an APP in a preset third-party application download platform, and the third-party category label is a category label of the first key APP in the preset third-party application download platform. A second key APP name list corresponding to the first key label is further obtained, and a second key label list and a third key label list obtained from the second key APP name list are obtained based on the target category label of an intermediate APP name, wherein the intermediate APP is an APP whose target category label is not NULL in a target database, and a target category label of the target APP is determined according to the number of second key labels in the second key label list that is the same as the third key label. It can be seen that the above method obtains the target category label of the target APP based on the category label of the first key APP in the preset third-party application download platform and the target category label corresponding to the intermediate APP name, and reduces the impact of the download volume and popularity of the target APP in the process of obtaining the target category label, which is conducive to improving the accuracy of obtaining the target category label. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 A flowchart of a method for obtaining a target category label provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0019] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar tasks, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.

[0020] An embodiment of the present invention provides a method for obtaining a target category label, wherein the target category label is a category label of an APP in a target database, and the method comprises the following steps: Figure 1 As shown:

[0021] S1. Get the target APP name list A = {A 1 , A 2 , …, A i , …, A m}, A i is the name of the i-th target APP, the value of i ranges from 1 to m, m is the number of target APP names, the target APP name is the name of the target APP, and the target APP is the APP with the target category label of NULL in the target database.

[0022] Specifically, the target database includes several APPs and APP information of each APP. The APP information at least includes the name of the APP, the installation package name of the installation package corresponding to the APP, and the target category label of the APP. The above is only some APP information given as an example. There may also be other APP information, such as: the size of the installation package corresponding to the APP, the version of the installation package corresponding to the APP, which will not be repeated here.

[0023] Furthermore, the target category label of APP can be NULL.

[0024] Specifically, the category label is a label used to describe the type of APP, such as: entertainment, learning, work, sports, which will not be repeated here.

[0025] S2, according to the first key APP name list B = {B 1 , B 2 , …, B j , …, B n}, get the first key tag list C corresponding to A = {C 1 , C 2, …, C i , …, C m}, where A i =B j When B j The corresponding third-party category label is C i , B j is the jth first key APP name, j ranges from 1 to n, n is the number of first key APP names, C i A i Corresponding to the first key tag, the first key APP name is the name of the first key APP, the first key APP is an APP in the preset third-party application download platform, and the third-party category tag is the category tag of the first key APP in the preset third-party application download platform. Those skilled in the art know that the preset third-party application download platform is a third-party application download platform predetermined by those skilled in the art according to actual needs, and will not be repeated here.

[0026] S3, traverse B, when B j The corresponding third-party category label and C i If the same, j As C i The corresponding second key APP name to obtain C i Corresponding second key APP name list D i ={D i1 , D i2 , …, D ie , …, D if(i)}, D ie C i The corresponding e-th second key APP name, the value of e is 1 to f(i), f(i) is C i The number of corresponding second key APP names.

[0027] S4, according to the intermediate APP name list E = {E 1 , E 2 ,…,E r ,…,E s}, get D i The corresponding second key tag list F i ={F i1 , F i2 , …, F ie , …, F if(i)}, and for F i1 , F i2 , …, F ie , …, F if(i) Perform deduplication to obtain D i The corresponding third key tag list G i = {Gi1 , G i2 , …, G ik , …, G it(i)}, where D ie =E r When E r The corresponding target category label is F ie , E r is the name of the rth intermediate APP, r ranges from 1 to s, s is the number of intermediate APP names, the intermediate APP name is the name of the intermediate APP, and the intermediate APP is the APP whose target category label is not NULL in the target database. ie D ie The corresponding second key tag, G ik D i The corresponding kth third key tag, k ranges from 1 to t(i), t(i) is D i As for the number of the corresponding third key tags, those skilled in the art are aware that any deduplication processing method in the prior art belongs to the protection scope of the present invention and will not be described in detail here.

[0028] Specifically, if D ie With E 1 , E 2 ,…,E r ,…,E s If they are not the same, then determine F ie is NULL.

[0029] S5, when G 0 ik =max(G 0 i1 , G 0 i2 , …, G 0 ik , …, G 0 it(i) ),G ik As A i The corresponding target category label of the target APP, G 0 ik F i1 , F i2 , …, F ie , …, F if(i) Middle and G ik The number of identical second key tags. max() is the maximum value acquisition function.

[0030] Through the above steps, the first key tag corresponding to the target APP name is obtained according to the third-party category tag corresponding to the first key APP name, the first key APP is an APP in a preset third-party application download platform, and the third-party category tag is the category tag of the first key APP in the preset third-party application download platform. The second key APP name list corresponding to the first key tag is further obtained, and based on the target category tag of the intermediate APP name, the second key tag list and the third key tag list obtained from the second key APP name list are obtained. The intermediate APP is an APP whose target category tag is not NULL in the target database. According to the number of second key tags in the second key tag list that is the same as the third key tag, the target category tag of the target APP is determined. In the process of obtaining the target category tag, the impact of the download volume and popularity of the target APP is reduced, which is conducive to improving the accuracy of obtaining the target category tag.

[0031] In a specific embodiment, after step S2, the following steps S10-S50 are also included:

[0032] S10, when B 1 , B 2 , …, B j , …, B n With A i If they are not the same, A i In the corresponding target installation package name string, the substring after the first preset delimiter from right to left is used as A i The corresponding first string R i , where the target installation package name string is a string representing the installation package name of the installation package corresponding to the target APP, including multiple substrings connected by a preset separator. For example, if the preset separator is ".", then A i The corresponding target installation package name string is abcd.1234.firewall, then R i For firewall.

[0033] S20, according to the preset string list set J = {J 1 , J 2 , …, J g , …, J h}, get R i The corresponding second string list, where when K i ≤max(J 0 1 , J 0 2 , …, J 0 g , …, J 0 h ) and Ki =J 0 g When J g As R i The corresponding second string list, J g is the g-th preset string list, the value of g ranges from 1 to h, h is the number of preset string lists, each preset string list includes a number of preset strings, K i For R i The string length, J 0 g For J g The corresponding preset string length, J g The lengths of all preset strings in J 0 g Similarly, the second string list includes a plurality of second strings, and the preset string is a string that can extract information, for example: firewall, talkback.

[0034] S30, obtain the third string list L corresponding to E = {L 1 , L 2 , …, L r , …, L s}, L r For E r The corresponding third string, E r The corresponding third string is E r In the corresponding intermediate installation package name string, the substring after the first preset separator from right to left, the intermediate installation package name string is a string representing the installation package name of the installation package corresponding to the intermediate APP, containing multiple substrings and connected by preset separators.

[0035] S40, when R i With R i If any second string in the corresponding second string list is the same, get R i Corresponding third key APP name list M i ={M i1 , M i2 , …, M ix , …, M ip(i)} and M i The corresponding fourth key tag list N i = {N i1 , N i2 ,…,N ix ,…,N ip(i)}, which will be i The same L r The corresponding E r As Ri The corresponding third key APP name, the E r The corresponding target category label is used as the fourth key label corresponding to the third key APP name, M ix For R i The corresponding xth third key APP name, x ranges from 1 to p(i), p(i) is R i The number of corresponding third key APP names, N ix M ix The corresponding fourth key tag.

[0036] S50, for N i1 , N i2 ,…,N ix ,…,N ip(i) Perform deduplication processing to obtain R i The corresponding first intermediate label list P i = {P i1 , P i2 ,…,P iy ,…,P iq(i)} and based on P i Get A i The corresponding target category label of the target APP, where P iy For R i The corresponding y-th first intermediate label, y ranges from 1 to q(i), q(i) is R i The number of first intermediate labels corresponding to P 0 iy =max(P 0 i1 , P 0 i2 ,…,P 0 iy ,…,P 0 iq(i) ), P iy As A i The corresponding target category label of the target APP, P 0 iy N i1 , N i2 ,…,N ix ,…,N ip(i) Zhong and P iy The number of identical fourth key tags.

[0037] Through the above steps, when the target APP name is different from any first key APP name, obtain the first string corresponding to the target APP name, obtain the second string list corresponding to the first string according to the preset string list set, obtain the third string corresponding to the intermediate APP name, obtain the third key APP name list and the fourth key tag list corresponding to the first string according to the first string, the second string list and the third string, obtain the first intermediate tag list corresponding to the first string according to the fourth key tag list corresponding to the first string, and obtain the target category tag corresponding to the target APP based on the number of fourth key tags in the fourth key tag list that are the same as the first intermediate tag. Even if the target APP is not included in the preset third-party application download platform, the target category tag of the target APP can be obtained, which is conducive to improving the accuracy of obtaining the target category tag.

[0038] In a specific embodiment, after step S40, the following steps S100-S500 are also included:

[0039] S100, when K i >max(J 0 1 , J 0 2 , …, J 0 g , …, J 0 h ) or R i With R i When all second character strings in the corresponding second character string list are different, the process goes to step S200 .

[0040] S200, when c(i)≥H, obtain A i Corresponding specified device ID list Q i = {Q i1 , Q i2 , …, Q ia , …, Q ic(i)}, where c(i) is A i The number of corresponding specified device IDs, H is the preset device quantity threshold, Q ia A i The corresponding a-th specified device ID, a value ranges from 1 to c(i), A i The corresponding specified device is installed with A i The device corresponding to the target APP.

[0041] Specifically, the designated device ID is the identity identifier of the designated device.

[0042] S300, according to Q i , get Q iThe corresponding specified APP name list set S i ={S i1 , S i2 , …, S ia , …, S ic(i)}, where S ia Q ia The corresponding specified APP name list includes several specified APP names, the specified APP name is the APP name of the specified APP, and the specified APP is the APP currently installed in the specified device.

[0043] S400, taking the target category label corresponding to the intermediate APP name that is the same as the specified APP name as the second intermediate label corresponding to the specified APP name, to obtain S i The corresponding second intermediate label list set S 0 i ={S 0 i1 , S 0 i2 , …, S 0 ia , …, S 0 ic(i)},S 0 ia For S ia The corresponding second intermediate label list, S 0 ia Including S ia The second middle label corresponding to each specified APP name in.

[0044] Specifically, if all the intermediate APP names in the intermediate APP name list are different from the specified APP name, it is determined that the second intermediate tag corresponding to the specified APP name is NULL.

[0045] S500, S 0 i1 , S 0 i2 , …, S 0 ia , …, S 0 ic(i) All second intermediate labels in are deduplicated to obtain S 0 i The corresponding third intermediate label list T i ={T i1 , T i2 ,…,T ib ,…,T id(i)}, and according to S 0 i and T i Get Ai The target category label of the corresponding target APP, where T ib For S 0 i The corresponding b-th third middle label, b ranges from 1 to d(i), d(i) is S 0 i The number of corresponding third middle labels.

[0046] Specifically, the steps are based on S 0 i and T i Get A i The target category tag of the corresponding target APP also includes the following steps S501-S504:

[0047] S501, obtain S 0 ia Medium T ib The corresponding TGI value U aib , U aib Meet the following conditions:

[0048] U aib =V aib / V 0 ia / (∑ c(i) a＝1 V aib / ∑ c(i) a＝1 V 0 ia )×100, where V aib For S 0 ia Medium and T ib The number of the same second middle label, V 0 ia For S 0 ia The number of second middle labels in .

[0049] S502, obtain S 0 ia Medium T ib The corresponding target weight W aib , W aib Meet the following conditions:

[0050] W aib =V aib / V 0 ia .

[0051] Specifically, the target weight is used to indicate the importance of the third intermediate label. The larger the target weight is, the more important the corresponding third intermediate label is.

[0052] S503, according to U aib and W aib Get T ib The corresponding weighted average TGI value Z ib , Z ib Meet the following conditions:

[0053] Z ib =∑ c(i) a＝1 (W aib ×U aib ) / ∑ c(i) a＝1 W aib .

[0054] S504, when Z ib =max(Z i1 , Z i2 , …, Z ib , …, Z id(i) ),T ib As A i The target category label of the corresponding target APP.

[0055] Through the above steps, when the second string list corresponding to the first string cannot be obtained, or all the second strings in the second string list corresponding to the first string are different, the number of designated device IDs corresponding to the target APP name is obtained, and when the number of designated device IDs corresponding to the target APP name is not less than the preset device number threshold, the designated APP name list set corresponding to the designated device ID list corresponding to the target APP name is obtained, and the second intermediate label list set is obtained according to the designated APP name list set and the target category label corresponding to the intermediate APP name. Further, the third intermediate label list is obtained, and the weighted average TGI value corresponding to the third intermediate label in the second intermediate label list is obtained according to the TGI value and target weight corresponding to the third intermediate label, and the target category label of the target APP is obtained according to the weighted average TGI value corresponding to the third intermediate label. Even if the target APP is not included in the preset third-party application download platform, the target category label of the target APP can be obtained, and the impact of the download volume and popularity of the target APP is reduced, which is conducive to improving the accuracy of obtaining the target category label.

[0056] In a specific embodiment, after step S200, the following steps S1000-S5000 are also included:

[0057] S1000, when c(i)<H, A i As the name of the APP to be classified, A iThe corresponding target APP is used as the APP to be classified corresponding to the APP name to be classified, so as to obtain a list of APP names to be classified, wherein the list of APP names to be classified includes several APP names to be classified.

[0058] S2000, obtain the initial user ID list X={X 1 , X 2 , …, X u , …, X v}, X u is the u-th initial user ID, the value of u ranges from 1 to v, v is the number of initial user IDs, the initial user is the user using the key device, and the key device is the device that has installed any APP to be classified corresponding to the name of the APP to be classified in the list of APP names to be classified.

[0059] Specifically, the initial user ID is the unique identity of the initial user.

[0060] S3000, obtain the initial user tag list set Y corresponding to X = {Y 1 , Y 2 , …, Y u , …, Y v}, where Y u For X u The corresponding initial user tag list, Y u Includes X u The corresponding several initial user tags, the initial user tag corresponding to the initial user ID is the user tag of the initial user corresponding to the initial user ID. Among them, those skilled in the art know that any method of obtaining user tags in the prior art belongs to the protection scope of the present invention and will not be repeated here.

[0061] Specifically, the initial user ID is the unique identity of the initial user.

[0062] S4000, based on the K-means clustering algorithm and Y, obtain the total set of clustered user tag list sets JL = {JL (1) , J.L. (2) , …, JL (ai) , …, JL (am)}, JL (ai) ={JL (ai)(1) , J.L. (ai)(2) , …, JL (ai)(aj) , …, JL (ai)(an)}, where JL (ai) is the ai-th cluster user label list set, ai ranges from 1 to am, am is the number of cluster user label list sets, JL (ai)(aj) For JL (ai)The ajth clustering user label list in , the value of aj ranges from 1 to an, an is the number of clustering user label lists in the clustering user label list set, and the clustering user label list includes several clustering user labels.

[0063] Specifically, the value range of am is [3, 5].

[0064] Specifically, step S4000 includes the following steps S4100-S4300:

[0065] S4100, for Y u Perform vectorization processing to obtain Y u The corresponding first label vector Y 0 u , Y 0 u The dimension of Y u The number of initial user tags is the same, wherein those skilled in the art know that any vectorization processing method in the prior art belongs to the protection scope of the present invention and will not be described in detail here.

[0066] S4200, use K-means clustering algorithm to 0 1 , Y 0 2 , …, Y 0 u , …, Y 0 v The corresponding label vectors are clustered to obtain the second label vector list set Y corresponding to Y 1 = {Y 1 (1) , Y 1 (2) , …, Y 1 (ai) , …, Y 1 (am)},Y 1 (ai) = {Y 1 (ai)(1) , Y 1 (ai)(2) , …, Y 1 (ai)(aj) , …, Y 1 (ai)(an)},Y 1 (ai) is the list of the second label vectors corresponding to the aith order of Y, Y 1 (ai)(aj) Y 1 (ai)The ajth second label vector in , where the second label vector is the clustered first label vector, wherein a second label vector list can be understood as a cluster.

[0067] S4300, when Y 0 u =Y 1 (ai)(aj) When Y u As JL (ai)(aj) .

[0068] Through the above steps, the initial user label list is vectorized, the first label vector corresponding to the initial user label list is obtained, all the first label vectors are clustered to obtain a second label vector list set, and the similar first label vectors can be clustered into the same cluster, and the total set of clustered user label list sets is further obtained, which is conducive to improving the accuracy of obtaining the total set of clustered user label list sets. According to the initial user label list set and the total set of clustered user label list sets, the target category label of the APP to be classified is obtained. Even if the target APP is not included in the preset third-party application download platform, the target category label of the target APP can be obtained, and the impact of the download volume and popularity of the target APP is reduced, which is conducive to improving the accuracy of obtaining the target category label.

[0069] S5000. Based on Y and JL, obtain target category labels of all APPs to be classified corresponding to the names of the APPs to be classified.

[0070] Step S5000 also includes the following steps S5100-S5400:

[0071] S5100, for Y 1 , Y 2 , …, Y u , …, Y v All initial user tags in are deduplicated to obtain the intermediate user tag list ZJ={ZJ (1) , ZJ (2) , …, ZJ (ae) , …, ZJ (af)}, ZJ (ae) is the ae-th intermediate user tag, the value of ae ranges from 1 to af, and af is the number of intermediate user tags.

[0072] S5200, Get JL (ai) Medium ZJ (ae) The corresponding TGI value tgi (ai)(ae) , tgi (ai)(ae) Meet the following conditions:

[0073] tgi (ai)(ae) =∑an aj＝1 AA (ae) (ai)(aj) / ∑ an aj＝1 AB (ai)(aj) / (∑ am ai＝1 ∑ an aj＝1 AA (ae) (ai)(aj) / ∑ am ai＝1 ∑ an aj＝1 AB (ai)(aj) )×100,

[0074] AA (ae) (ai)(aj) For JL (ai)(aj) Zhong and ZJ (ae) The number of the same cluster user labels, AB (ai)(aj) For JL (ai)(aj) The number of clustered user labels.

[0075] S5300, according to tgi (ai)(ae) Get ZJ (ae) The corresponding total TGI value Z-tgi (ae) , Z-tgi (ae) Meet the following conditions:

[0076] Z-tgi (ae) =∑ am ai＝1 tgi (ai)(ae) .

[0077] S5400, when Z-tgi (ae) =max(Z-tgi (1) , Z-tgi (2) ,…,Z-tgi (ae) ,…,Z-tgi (af) ),ZJ (ae) do

[0078] It is the target category label of the APP to be classified corresponding to the name of all APPs to be classified.

[0079] Through the above steps, when the number of designated device IDs corresponding to the target APP name is less than the preset device number threshold, the target APP name is used as the APP name to be classified, and the target APP corresponding to the target APP name is used as the APP to be classified. The initial user ID list is obtained according to the list of APP names to be classified. Further, the initial user label list set corresponding to the initial user ID list is obtained, and based on the K-means clustering algorithm and the initial user label list set, the total set of cluster user label list sets is obtained, and the intermediate user label list is obtained according to the initial user label list. Based on the number of cluster user labels in the cluster user label list that are the same as the intermediate user label and the number of cluster user labels in the cluster user label list, the total TGI value corresponding to the intermediate user label is obtained. According to the total TGI value corresponding to the intermediate user label, the target category label of the APP to be classified is obtained. Even if the target APP is not included in the preset third-party application download platform, the target category label of the target APP can be obtained, and the impact of the download volume and popularity of the target APP is reduced, which is conducive to improving the accuracy of obtaining the target category label.

[0080] In a specific embodiment, step S200 further includes the following steps S210-S250 to obtain H:

[0081] S210 , obtaining a second preset quantity value γ corresponding to the first preset quantity value θ, wherein θ is initially 1, and γ=θ+1.

[0082] S220, obtain the candidate device ID list set AC corresponding to E = {AC 1 , A.C. 2 ,…,AC r ,…,AC s}, where AC r For E r Corresponding candidate device ID list, E r The corresponding candidate device ID list includes E r The corresponding β candidate device IDs, E r The corresponding candidate device is the one with E r The corresponding intermediate APP device.

[0083] Specifically, the candidate device ID is a unique identification of the candidate device.

[0084] S220, let β = θ and adopt the steps S300-S500 according to Q i , get A i The same way as the target category label of the corresponding target APP, according to AC r Get E r The first candidate category label AD of the corresponding intermediate APP r, to obtain the first candidate category label AD corresponding to E = {AD 1 , A.D. 2 , …, A-D r , …, A-D s}; It can be understood that the Q in step S300 i Replaced by AC r And execute steps S300-S500 to obtain E r The first candidate category label AD of the corresponding intermediate APP r , I will not go into details here.

[0085] S230, set β = γ and adopt the steps S300-S500 according to Q i , get A i The same way as the target category label of the corresponding target APP, according to AC r Get E r The corresponding second candidate category label AD of the intermediate APP r , to obtain the second candidate category label AF corresponding to E = {AF 1 , A.F. 2 , …, AF r , …, AF s}.

[0086] S240, obtain the target category label list AE corresponding to E = {AE 1 , A.E. 2 ,…,AE r ,…,AE s}, where AE r For E r The target category label of the corresponding target APP.

[0087] S250 , obtain H according to AD, AF and AE.

[0088] Specifically, step S250 also includes the following steps S251-S253:

[0089] S251. Obtain the accuracy score AG corresponding to θ θ , A.G. θ Meet the following conditions:

[0090] AG θ =∑ s r＝1 AH r / s,AH r For E r The corresponding first precision weight, where AD r =AE r When AH r =1, when ADr ≠AE r When AH r =0.

[0091] S252. Obtain the accuracy score AG corresponding to γ γ , A.G. γ Meet the following conditions:

[0092] AG γ =∑ s r＝1 AR r / s,AR r For E r The corresponding second accuracy weight, where AF r =AE r When r =1, when AF r ≠AE r When r =0.

[0093] S253, being AG θ >AJ 0 And|AG γ -AG θ |<AJ 1 When H=θ, otherwise, θ=θ+1 is set to update θ and enter step S210, where AJ 0 is the preset accuracy score, AJ 1 AJ is a preset accuracy difference, and those skilled in the art know that they can set AJ according to actual needs. 0 and A.J. 1 The specific value of is not described here.

[0094] Through the above steps, a set of candidate device ID lists corresponding to the intermediate APP name list is obtained, the candidate device ID in the candidate device ID list is set to a first preset quantity value, the first candidate category label corresponding to the intermediate APP is obtained, the candidate device ID in the candidate device ID list is set to a second preset quantity value, the second candidate category label corresponding to the intermediate APP is obtained, and based on the first candidate category label, the second candidate category label and the target category label of the intermediate APP, the accuracy score corresponding to the first preset quantity value and the accuracy score corresponding to the second preset quantity value are obtained. The preset device quantity threshold is obtained based on the accuracy score corresponding to the first preset quantity value and the accuracy score corresponding to the second preset quantity value, which is conducive to improving the accuracy of obtaining the preset device quantity threshold.

[0095] An embodiment of the present invention also provides a non-transitory computer-readable storage medium, which can be set in an electronic device to store a computer program related to a method in a method embodiment, and the computer program is loaded and executed by the processor to implement the method provided in the above embodiment.

[0096] An embodiment of the present invention further provides an electronic device, comprising: a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method provided in the above embodiment when executing the computer program.

[0097] An embodiment of the present invention further provides a computer program product, which includes program code. When the program product is run on an electronic device, the program code is used to enable the electronic device to execute the steps of the method according to various exemplary embodiments of the present invention described above in this specification.

[0098] The present invention provides a method for obtaining a target category label, an electronic device and a storage medium. The method can obtain a first key label corresponding to a target APP name according to a third-party category label corresponding to a first key APP name, wherein the first key APP is an APP in a preset third-party application download platform, and the third-party category label is a category label of the first key APP in the preset third-party application download platform. A second key APP name list corresponding to the first key label is further obtained, and a second key label list and a third key label list obtained from the second key APP name list are obtained based on the target category label of an intermediate APP name, wherein the intermediate APP is an APP whose target category label is not NULL in a target database, and a target category label of the target APP is determined according to the number of second key labels in the second key label list that is the same as the third key label. It can be seen that the above method obtains the target category label of the target APP based on the category label of the first key APP in the preset third-party application download platform and the target category label corresponding to the intermediate APP name, and reduces the impact of the download volume and popularity of the target APP in the process of obtaining the target category label, which is conducive to improving the accuracy of obtaining the target category label.

[0099] Although some specific embodiments of the present invention have been described in detail by way of example, it should be understood by those skilled in the art that the above examples are only for illustration, not for limiting the scope of the present invention. It should also be understood by those skilled in the art that various modifications may be made to the embodiments without departing from the scope and spirit of the present invention.

Claims

1. A method for obtaining a target category label, characterized in that: The target category label is the category label of the APP in the target database, and the method comprises the following steps: S1. Get the target APP name list A = {A1, A2, ..., A i , …, A m }, A i is the name of the i-th target APP, the value of i ranges from 1 to m, m is the number of target APP names, the target APP name is the name of the target APP, and the target APP is the APP whose target category label is NULL in the target database; S2, according to the first key APP name list B = {B1, B2, ..., B j , …, B n }, get the first key tag list C corresponding to A = {C1, C2, ..., C i , …, C m }, where A i =B j When B j The corresponding third-party category label is C i , B j is the jth first key APP name, j ranges from 1 to n, n is the number of first key APP names, C i A i The corresponding first key tag, the first key APP name is the name of the first key APP, the first key APP is an APP in the preset third-party application download platform, and the third-party category tag is the category tag of the first key APP in the preset third-party application download platform; S3, traverse B, when B j The corresponding third-party category label and C i If the same, j As C i The corresponding second key APP name to obtain C i Corresponding second key APP name list D i ={D i1 , D i2 , …, D ie , …, D if(i) }, D ie C i The corresponding e-th second key APP name, the value of e is 1 to f(i), f(i) is C i The number of corresponding second key APP names; S4, according to the intermediate APP name list E = {E1, E2, ..., E r ,…,E s }, get D i The corresponding second key tag list F i ={F i1 , F i2 , …, F ie , …, F if(i) }, and for F i1 , F i2 , …, F ie , …, F if(i) Perform deduplication to obtain D i The corresponding third key tag list G i = {G i1 , G i2 , …, G ik , …, G it(i) }, where D ie =E r When E r The corresponding target category label is F ie , E r is the name of the rth intermediate APP, r ranges from 1 to s, s is the number of intermediate APP names, the intermediate APP name is the name of the intermediate APP, and the intermediate APP is the APP whose target category label is not NULL in the target database. ie D ie The corresponding second key tag, G ik D i The corresponding kth third key tag, k ranges from 1 to t(i), t(i) is D i The number of corresponding third key tags; S5, when G 0 ik =max(G 0 i1 , G 0 i2 , …, G 0 ik , …, G 0 it(i) ),G ik As A i The corresponding target category label of the target APP, G 0 ik F i1 , F i2 , …, F ie , …, F if(i) Middle and G ik The number of identical second key tags. max() is the maximum value acquisition function.

2. The method for obtaining a target category label according to claim 1, characterized in that: The target database includes several APPs and APP information of each APP, and the APP information at least includes the name of the APP, the installation package name of the installation package corresponding to the APP, and the target category label of the APP.

3. The method for obtaining a target category label according to claim 1, characterized in that: If D ie With E1, E2, …, E r ,…,E s If they are not the same, then determine F ie is NULL.

4. The method for obtaining a target category label according to claim 2, characterized in that: After step S2, the following steps S10-S50 are also included: S10, when B1, B2, ..., B j , …, B n With A i If they are not the same, A i In the corresponding target installation package name string, the substring after the first preset delimiter from right to left is used as A i The corresponding first string R i , wherein the target installation package name string is a string representing the installation package name of the installation package corresponding to the target APP, including multiple substrings connected by preset separators; S20, according to the preset string list set J = {J1, J2, ..., J g , …, J h }, get R i The corresponding second string list, where when K i ≤max(J 0 1. J 0 2, …, J 0 g , …, J 0 h ) and K i =J 0 g When J g As R i The corresponding second string list, J g is the g-th preset string list, the value of g ranges from 1 to h, h is the number of preset string lists, each preset string list includes a number of preset strings, K i For R i The string length, J 0 g For J g The corresponding preset string length, J g The lengths of all preset strings in J 0 g Similarly, the second string list includes a plurality of second strings, and the preset string is a string that can extract information; S30, obtain a third string list L corresponding to E = {L1, L2, ..., L r , …, L s }, L r For E r The corresponding third string, E r The corresponding third string is E r The substring after the first preset delimiter in the corresponding intermediate installation package name string from right to left. The intermediate installation package name string is a string representing the installation package name of the installation package corresponding to the intermediate APP, which contains multiple substrings connected by preset delimiters; S40, when R i With R i If any second string in the corresponding second string list is the same, get R i Corresponding third key APP name list M i ={M i1 , M i2 , …, M ix , …, M ip(i) } and M i The corresponding fourth key tag list N i = {N i1 , N i2 ,…,N ix ,…,N ip(i) }, which will be the same as R i The same L r The corresponding E r As R i The corresponding third key APP name, the E r The corresponding target category label is used as the fourth key label corresponding to the third key APP name, M ix For R i The corresponding xth third key APP name, x ranges from 1 to p(i), p(i) is R i The number of corresponding third key APP names, N ix M ix The corresponding fourth key tag; S50, for N i1 , N i2 ,…,N ix ,…,N ip(i) Perform deduplication processing to obtain R i The corresponding first intermediate label list P i = {P i1 , P i2 ,…,P iy ,…,P iq(i) } and based on P i Get A i The corresponding target category label of the target APP, where P iy For R i The corresponding y-th first intermediate label, y ranges from 1 to q(i), q(i) is R i The number of first intermediate labels corresponding to P 0 iy =max(P 0 i1 , P 0 i2 ,…,P 0 iy ,…,P 0 iq(i) ), P iy As A i The corresponding target category label of the target APP, P 0 iy N i1 , N i2 ,…,N ix ,…,N ip(i) Zhong and P iy The number of identical fourth key tags.

5. The method for obtaining target category labels according to claim 4, characterized in that: After step S40, the following steps S100-S500 are also included: S100, when K i >max(J 0 1. J 0 2, …, J 0 g , …, J 0 h ) or R i With R i If all second character strings in the corresponding second character string list are different, proceed to step S200; S200, when c(i)≥H, obtain A i Corresponding specified device ID list Q i = {Q i1 , Q i2 , …, Q ia , …, Q ic(i) }, where c(i) is A i The number of corresponding specified device IDs, H is the preset device quantity threshold, Q ia A i The corresponding a-th specified device ID, a value ranges from 1 to c(i), A i The corresponding specified device is installed with A i The device of the corresponding target APP; S300, according to Q i , get Q i The corresponding specified APP name list set S i ={S i1 , S i2 , …, S ia , …, S ic(i) }, where S ia Q ia A corresponding specified APP name list, the specified APP name list includes several specified APP names, the specified APP name is the APP name of the specified APP, and the specified APP is the APP currently installed in the specified device; S400, taking the target category label corresponding to the intermediate APP name that is the same as the specified APP name as the second intermediate label corresponding to the specified APP name, to obtain S i The corresponding second intermediate label list set S 0 i ={S 0 i1 , S 0 i2 , …, S 0 ia , …, S 0 ic(i) },S 0 ia For S ia The corresponding second intermediate label list, S 0 ia Including S ia The second middle label corresponding to each specified APP name in; S500, S 0 i1 , S 0 i2 , …, S 0 ia , …, S 0 ic(i) All second intermediate labels in are deduplicated to obtain S 0 i The corresponding third intermediate label list T i ={T i1 , T i2 ,…,T ib ,…,T id(i) }, and according to S 0 i and T i Get A i The target category label of the corresponding target APP, where T ib For S 0 i The corresponding b-th third middle label, b ranges from 1 to d(i), d(i) is S 0 i The number of corresponding third middle labels.

6. The method for obtaining a target category label according to claim 5, characterized in that: If all the intermediate APP names in the intermediate APP name list are different from the specified APP name, it is determined that the second intermediate tag corresponding to the specified APP name is NULL.

7. The method for obtaining target category labels according to claim 5, characterized in that: Steps according to S 0 i and T i Get A i The target category tag of the corresponding target APP also includes the following steps S501-S504: S501, obtain S 0 ia Medium T ib The corresponding TGI value U aib , U aib Meet the following conditions: U aib =V aib / V 0 ia / (∑ c(i) a＝1 V aib / ∑ c(i) a＝1 V 0 ia )×100, where V aib For S 0 ia Medium and T ib The number of the same second middle label, V 0 ia For S 0 ia The number of second middle labels in ; S502, obtain S 0 ia Medium T ib The corresponding target weight W aib , W aib Meet the following conditions: W aib =V aib / V 0 ia ; S503, according to U aib and W aib Get T ib The corresponding weighted average TGI value Z ib , Z ib Meet the following conditions: WITH ib =∑ c(i) a＝1 (IN aib ×U aib ) / ∑ c(i) a＝1 IN aib ; S504, when Z ib =max(Z i1 , Z i2 , …, Z ib , …, Z id(i) ),T ib As A i The target category label of the corresponding target APP.

8. The method for obtaining target category labels according to claim 5, characterized in that: The specified device ID is the identity of the specified device.

9. A non-transitory computer-readable storage medium, characterized in that: The storage medium stores a computer program, which is loaded and executed by a processor to implement the method for obtaining a target category label as described in any one of claims 1 to 8.

10. An electronic device comprising: A processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method for obtaining a target category label as described in any one of claims 1 to 8 when executing the computer program.

Images