CN112579661A

CN112579661A - Method and device for determining specific target pair, computer equipment and storage medium

Info

Publication number: CN112579661A
Application number: CN201910935872.XA
Authority: CN
Inventors: 邢金彪; 王辉
Original assignee: Hangzhou Hikvision Digital Technology Co Ltd
Current assignee: Hangzhou Hikvision Digital Technology Co Ltd
Priority date: 2019-09-29
Filing date: 2019-09-29
Publication date: 2021-03-30
Anticipated expiration: 2039-09-29
Also published as: CN112579661B

Abstract

The invention discloses a method and a device for determining a specific target pair, computer equipment and a storage medium, wherein the method comprises the following steps: acquiring a plurality of behavior time sequences based on the behavior data sequences of a plurality of targets; acquiring a plurality of subset sequences of a first behavior time sequence based on the first behavior time sequence in the plurality of behavior time sequences; determining a subset sequence having the same elements as any second action time sequence in the plurality of action time sequences from the plurality of subset sequences of the first action time sequence, wherein the sequence length of the second action time sequence is equal to the target sequence length; and determining a specific target pair based on the similarity between the determined subset sequence and the target to which the second action time sequence belongs. The invention filters the behavior time sequence with the length larger than that of the target sequence based on the behavior time sequence with the length of the target sequence under the condition of ensuring the integrity of the calculation result, thereby reducing the data amount required to be calculated and reducing the complexity of the specific target to the determination process.

Description

Method and device for determining specific target pair, computer equipment and storage medium

Technical Field

The invention relates to the field of data mining technology processing, in particular to a method and a device for determining a specific target pair, computer equipment and a storage medium.

Background

The specific target pair mining refers to a process of finding a specific target which is obviously different from most targets in a target set, and the specific target pair mining has important application value in the fields of securities finance, medical insurance, intelligent transportation, social network, life science research and the like, for example, in the securities market, the specific target pair mining is often expressed as collusion manipulation (multi-account joint manipulation), fund 'rat box' and the like. These accounts are aimed at gaining illicit benefits, centralizing capital advantages or utilizing information advantages, manipulating transaction amounts, transaction prices, and disrupting market order. The algorithm for determining the specific target pair usually calculates the similarity or common characteristic between any two targets, and takes any two targets satisfying a certain similarity threshold as the specific target pair. Therefore, the algorithm for determining the specific target pairs plays a crucial role in the specific target pair mining.

At present, the specific target pairs are usually calculated by means of cartesian product, that is, all possible combinations among the targets are listed, and then the similarity between the targets in each combination is determined, however, the complexity of this calculation method is very large, for example, for a set consisting of 1000 targets, the similarity between 1000 × 1000 — 1000000 groups of targets needs to be calculated, the calculation amount is very large, and this calculation method of cartesian product may result in that the specific target pairs cannot be accurately determined. Therefore, the above-described conventional calculation method may result in inefficient calculation of the specific target pair in the case of a large data amount.

Disclosure of Invention

The embodiment of the invention provides a method, a device, a computer device and a storage medium for determining a specific target pair, which can solve the problem of low calculation efficiency of the specific target pair in the related technology. The technical scheme is as follows:

in one aspect, a method for determining a specific target pair is provided, the method comprising:

acquiring a plurality of behavior time sequences based on the behavior data sequences of a plurality of targets, wherein each element of one behavior time sequence corresponds to the occurrence time of each behavior in the behavior data sequence;

acquiring a plurality of subset sequences of the first behavior time sequence based on the first behavior time sequence in the plurality of behavior time sequences, wherein the sequence length of the first behavior time sequence is greater than the length of the target sequence, and the sequence length of each subset sequence is the length of the target sequence;

determining a subset sequence having the same elements as any second action time sequence in the plurality of action time sequences from the plurality of subset sequences of the first action time sequence, wherein the sequence length of the second action time sequence is equal to the target sequence length;

and determining a specific target pair based on the similarity between the determined subset sequence and the target to which the second action time sequence belongs.

In an embodiment of the present invention, before the obtaining the plurality of behavior time series based on the behavior data series of the plurality of targets, the method further includes:

acquiring identity information corresponding to a plurality of targets;

acquiring a plurality of behavior data corresponding to the identity information within a preset time length;

and sequencing the behavior data based on the occurrence time of the behavior data to obtain a behavior data sequence corresponding to a plurality of targets.

In an embodiment of the present invention, the obtaining a plurality of behavior time series based on the behavior data series of the plurality of targets, where each element of one behavior time series corresponds to an occurrence time of each behavior in the behavior data series, includes:

converting the occurrence time of each behavior in the behavior data sequence of the multiple targets to obtain the behavior time in the target format;

and integrating the behavior time of the target format to obtain behavior time sequences corresponding to the behavior data sequences of the multiple targets.

In an embodiment of the invention, the obtaining a plurality of subset sequences of the first behavior time sequence based on the first behavior time sequence in the plurality of behavior time sequences includes:

determining a sequence length of each behavior time series;

determining a behavior time sequence with a sequence length larger than the target sequence length as a first behavior time sequence;

all subset sequences that fit the length of the target sequence are listed from the first action time sequence.

In an embodiment of the present invention, the determining, from the plurality of subset sequences of the first action time sequence, a subset sequence having the same element as any second action time sequence of the plurality of action time sequences includes:

and matching the element value of each subset sequence with the element value of the second behavior time sequence to determine the subset sequence with the element value equal to that of the second behavior time sequence.

In an embodiment of the present invention, the determining a specific target pair based on the similarity between the determined subset sequence and the target to which the second behavior time sequence belongs includes:

respectively determining behavior data sequences of corresponding targets based on the determined subset sequences and the second behavior time sequence;

and calculating the similarity between the behavior data sequences in the determined targets, and determining two targets with the similarity larger than a preset threshold value as a specific target pair.

In one aspect, a specific target pair determining apparatus is provided, the apparatus comprising:

the acquisition module is used for acquiring a plurality of behavior time sequences based on the behavior data sequences of a plurality of targets, wherein each element of one behavior time sequence corresponds to the occurrence time of each behavior in the behavior data sequence;

the subset sequence acquisition module is used for acquiring a plurality of subset sequences of the first behavior time sequence based on the first behavior time sequence in the plurality of behavior time sequences, wherein the sequence length of the first behavior time sequence is greater than the length of the target sequence, and the sequence length of each subset sequence is the length of the target sequence;

the determining module is used for determining a subset sequence which has the same elements with any second action time sequence in the action time sequences from the subset sequences of the first action time sequence, and the sequence length of the second action time sequence is equal to the length of the target sequence;

and the specific target pair determining module is used for determining a specific target pair based on the similarity between the determined subset sequence and the target to which the second behavior time sequence belongs.

In an embodiment of the present invention, the determining module is specifically configured to:

and matching the element value of each subset sequence with the element value of the second behavior time sequence, and determining the subset sequence with the element value equal to that of the second behavior time sequence.

In one aspect, a computer device is provided that includes one or more processors and one or more memories having stored therein at least one instruction that is loaded and executed by the one or more processors to perform an operation performed by a specific objective on a determination method.

In one aspect, a computer-readable storage medium having at least one instruction stored therein, the instruction being loaded and executed by a processor to implement an operation performed by a specific target pair determination method is provided.

The technical scheme provided by the embodiment of the invention has the following beneficial effects:

the invalid behavior time sequence in the behavior time sequence larger than the length of the target sequence is filtered based on the behavior time sequence of the length of the target sequence, so that the calculation of the similarity between target behavior data is limited within the length of the target sequence, the calculation complexity of a specific target pair determination algorithm is effectively reduced, the specific target pair is rapidly determined on the premise of not losing precision, and the efficiency is improved.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

FIG. 1 is a schematic diagram of a specific target determination method provided in an embodiment of the present invention;

FIG. 2 is a schematic flow chart of acquiring a plurality of behavior time sequences based on a behavior data sequence of a plurality of targets according to an embodiment of the present invention;

FIG. 3 is a schematic flow chart of acquiring a plurality of behavior time sequences according to an embodiment of the present invention;

FIG. 4 is a schematic flow chart of obtaining a plurality of behavior time sequences based on a behavior data sequence of a plurality of targets according to an embodiment of the present invention;

FIG. 5 is a flow chart illustrating a process for determining a subset sequence according to an embodiment of the present invention;

FIG. 6 schematically shows a schematic diagram of a filtering of a sequence of subsets;

FIG. 7 is a schematic flow chart of determining specific target pairs according to an embodiment of the present invention;

FIG. 8 is a schematic flow chart of determining specific target pairs according to an embodiment of the present invention;

FIG. 9 is a schematic diagram of a specific target pair determining apparatus according to an embodiment of the present invention;

fig. 10 is a block diagram of a terminal 1000 according to an embodiment of the present invention;

fig. 11 is a schematic structural diagram of a computer device according to an embodiment of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

FIG. 1 is a schematic diagram of a specific target determination method according to an embodiment of the present invention. The method can be applied to any computer device, which can be a terminal or a server, and referring to fig. 1, the embodiment includes:

101. and acquiring a plurality of behavior time sequences based on the behavior data sequences of the targets, wherein each element of one behavior time sequence corresponds to the occurrence time of each behavior in the behavior data sequence.

In an embodiment of the present invention, the target may specifically be a person, a vehicle, a bank account, or other targets, the behavior of the target is monitored and recorded by a monitoring device or system, so as to collect behavior data and occurrence time of the behavior, and after the collected behavior data of the target in a period is integrated, a behavior data sequence of the target is generated.

Because the data volume contained in the behavior data sequence of the target is too large, the specific target pair is determined directly based on the behavior data sequence, which may cause low calculation efficiency, so that the specific target pair determination method provided by the embodiment of the invention provides a method for determining the behavior time sequence corresponding to the behavior data sequence of the target, and the subsequent specific target pair determination is performed based on the behavior time sequence, thereby improving the calculation efficiency of the specific target pair determination.

102. Based on a first behavior time sequence in the behavior time sequences, acquiring a plurality of subset sequences of the first behavior time sequence, wherein the sequence length of the first behavior time sequence is greater than the target sequence length, and the sequence length of each subset sequence is the target sequence length.

In one embodiment of the present invention, based on the characteristic that two targets in a specific target pair behave similarly but not similar to most other targets, a specific target pair is most likely to be between two targets having the same behavior time series length or between two targets having the behavior time series length in an inclusion relationship, and therefore, the specific target pair in the embodiment of the present invention is determined by performing correlation calculation on any two targets having the same behavior time series length.

In practical application, a fixed target sequence length is set according to actual requirements, a behavior time sequence which is in accordance with the target sequence length is determined from a plurality of behavior time sequences with different sequence lengths, because the behavior time sequence which is smaller than the target sequence length has no value, the behavior time sequence which is smaller than the target sequence length can be directly filtered through the step, but the behavior time sequence which is larger than the target sequence length possibly contains a valuable behavior time sequence, therefore, all subset sequences of the target sequence length are determined from the behavior time sequences which are larger than the target sequence length, and the valuable behavior time sequence is obtained after all the subset sequences are filtered through subsequent steps.

103. From the plurality of subset sequences of the first action time sequence, a subset sequence having the same element as any second action time sequence of the plurality of action time sequences is determined, and the sequence length of the second action time sequence is equal to the target sequence length.

In an embodiment of the present invention, the second behavior time sequence with the sequence length of the plurality of behavior time sequences as the length of the target sequence is used as a reference, the plurality of subset sequences in step 102 are filtered, and the subset sequence with the same elements as those in the second behavior time sequence is determined.

104. And determining a specific target pair based on the similarity between the determined subset sequence and the target to which the second action time sequence belongs.

In an embodiment of the present invention, based on the determined subset sequence and the second behavior time sequence, the behavior data sequences of all corresponding targets are determined, similarity calculation is performed on the behavior data sequences of any two targets, and two objects with a similarity greater than a preset target threshold are determined as a specific target pair, specifically, similarity calculation methods such as a cosine similarity calculation method, a Jaccard similarity calculation method, a maximum common subset similarity calculation method, and the like may be used for the similarity calculation, which is not limited in the embodiment of the present invention.

The method filters the invalid behavior time sequence in the behavior time sequence with the length larger than that of the target sequence based on the behavior time sequence with the length of the target sequence, so that the calculation of the similarity between target behavior data is limited within the length of the target sequence, the calculation complexity of a specific target pair determination algorithm is effectively reduced, the specific target pair is rapidly determined on the premise of not losing precision, and the efficiency is improved.

Based on the above embodiment shown in fig. 1, the step 101 "obtaining a plurality of behavior time sequences based on behavior data sequences of a plurality of targets" may be implemented in the following manner, and fig. 2 is a schematic flow chart of obtaining a plurality of behavior time sequences based on behavior data sequences of a plurality of targets according to an embodiment of the present invention. Referring to fig. 2, the embodiment includes:

201. and acquiring identity information corresponding to a plurality of targets.

The identity information corresponding to the target may be an identity number (ID) assigned to the target, where the identity number may be a unique serial number or code for identifying the identity of the target, and in the computer device, for a specific target, the ID is not changed, and all data associated with the ID, such as behavior data of the target, may be obtained in the computer device through the ID.

202. And acquiring a plurality of behavior data corresponding to the identity information within a preset time length.

In an embodiment of the present invention, the behavior data of the target is usually recorded in a behavior data set of day-by-day, which is an ordered behavior data list with a length n, where n represents consecutive days, i.e. a preset duration, and the behavior data set may be specifically represented as S, S ═ [ (1, B ═ B { (m {)₁)，(2，B₂)，……(n，B_n)]Wherein (n, B)_n) Set of behavioral data representing the target on day n, B_nBehavioral data representing an object, B_nThe target can be null, and the behavior data of the target in the preset time length can be obtained based on the ID of the target.

203. And sequencing the behavior data based on the occurrence time of the behavior data to obtain a behavior data sequence corresponding to a plurality of targets.

In one embodiment of the present invention, for a subsequent specific target pair algorithm, the data structure of the behavior data is defined as an input data structure of the specific target pair algorithm, and the behavior data may be defined according to the following data structure: [ id, Array [ Set [ String ] ] (width), count ], wherein id represents identification information of the target, Array [ Set [ String ] ] (width) represents a behavior data Array with a preset time length of width, and count represents a behavior data sequence length, i.e., the number of days in which there is behavior data in a preset time length of width days.

For example, the behavior data sequence with the target id 231 in the preset time period of 30 days can be expressed as:

[231, Array ([ ], [02], [ ], [03,02], …, [05], [02,05], [01,02]), 5], that is, the behavior data sequence of the target 231 is Array ([ ], [02], [ ], [03,02], …, [05], [02,05], [01,02]), and the length of the behavior data sequence is 5, that is, there is 5 days of behavior data in 30 spots.

Based on the above embodiment shown in fig. 2, after "obtaining behavior data sequences corresponding to a plurality of targets" in step 203, a plurality of behavior time sequences corresponding to the behavior data sequences are obtained, and obtaining the behavior time sequences may be implemented in the following manner, and fig. 3 is a schematic flow diagram for obtaining a plurality of behavior time sequences according to an embodiment of the present invention. Referring to fig. 3, the embodiment includes:

301. and converting the occurrence time of each behavior in the behavior data sequences of the multiple targets to obtain the behavior time in the target format.

In an embodiment of the present invention, in order to reduce the computational complexity of the following specific target to the algorithm, a behavior time sequence of the target may be obtained, where the behavior time sequence is used to represent the occurrence time of the behavior of the target, and the occurrence time of the target behavior is recorded in time units such as time, calendar, month calendar, etc. when the behavior occurs, therefore, the occurrence time of the target behavior needs to be converted in the following steps, and the behavior time needs to be converted into a format that can facilitate the following computation.

302. And integrating the behavior time of the target format to obtain behavior time sequences corresponding to the behavior data sequences of the multiple targets.

In one embodiment of the invention, behavior time of the target data format is integrated to generate a corresponding behavior time sequence.

For example: the row data sequence for the target is:

[231，Array([],[02],[],[03,02],…,[05],[02,05],[01,02])，5]，

after integrating Array ([ ], [02], [ ], [03,02], …, [05], [02,05], [01,02]), determining that the time corresponding to 5 behavior data of the target 231 is day 1, day 3, day 28, day 29 and day 30 within 30 days, converting the time of the behavior occurrence to obtain a character string (0,2,27,28,29), and obtaining the corresponding behavior time sequence: string (0,2,27,28,29), with a sequence length of 5.

Based on the above embodiment shown in fig. 1, the step 102 "obtaining a plurality of subset sequences of the first behavior time sequence based on the first behavior time sequence in the plurality of behavior time sequences" may be implemented in the following manner, and fig. 4 is a schematic flow chart illustrating obtaining a plurality of behavior time sequences based on a behavior data sequence of a plurality of targets according to an embodiment of the present invention. Referring to fig. 4, the embodiment includes:

401. the sequence length of each behavior time series is determined.

402. And determining the action time sequence with the sequence length larger than the target sequence length as a first action time sequence.

In one embodiment of the present invention, since behavior time series with a sequence length greater than the target sequence length may have value, behavior time series with a sequence length greater than the target sequence length are determined based on the sequence length of each behavior time series.

403. All subset sequences that fit the length of the target sequence are listed from the first action time sequence.

In one embodiment of the invention, all the subset sequences of the target sequence length are generated from the behavior time sequence with the sequence length larger than the target sequence length, and are used as the basis for carrying out specific target pair analysis on the targets subsequently, so that the targets with or capable of generating the same sequence length are classified into one class, and the similarity between the behavior data sequences of any two targets is calculated.

Based on the above embodiment shown in fig. 1, step 103 "determining a subset sequence having the same element as any second behavior time sequence in the plurality of behavior time sequences from the plurality of subset sequences in the first behavior time sequence" may be implemented in the following manner, and fig. 5 is a flowchart for determining the subset sequence according to an embodiment of the present invention. Referring to fig. 5, the embodiment includes:

501. and determining the action time sequence with the sequence length equal to the target sequence length as a second action time sequence.

In one embodiment of the present invention, since the behavior time series with the sequence length equal to the target sequence length is a valuable series among the plurality of behavior time series, before filtering the subset series, a second behavior time series with the sequence length equal to the target sequence length among the behavior time series is filtered, and the subset series is filtered with the second behavior time series as a standard.

502. And counting each element in the second behavior time sequence to obtain the value of the element in the second behavior time sequence.

In an embodiment of the present invention, the filtering criterion for the subset sequence is to determine whether a value of each element in the subset sequence is equal to a value of each element in the second action time sequence, so that the value of each element is obtained from the second action time sequence, and the repeatedly appearing elements are recorded only once, and based on this, values of all elements included in the second action time sequence are obtained.

503. And carrying out statistics on elements in the plurality of subset sequences to obtain the value of the element of each subset sequence.

In an embodiment of the present invention, similar to the values of the elements in the second behavior time sequence obtained in

steps

501 and 502, in the subsequent filtering process of the subset sequences, the value of each element in each subset sequence needs to be obtained, and based on the value of each element in the subset sequence and the value of the element in the second behavior time sequence, the subset sequences are filtered, and the subset sequences without value are filtered, so as to improve the calculation efficiency of the specific target pair.

504. And matching the element value of each subset sequence with the element value of the second behavior time sequence to determine the subset sequence with the element value equal to that of the second behavior time sequence.

In an embodiment of the present invention, whether the values of the elements of each subset sequence are completely the same is determined based on the values of the elements of the second behavior time series, for example, the values of the elements of the second behavior time series are (0,1,2,3,4,5,6), and the values of the elements of any one subset sequence are (0,1,2,4, 6), it may be determined that each element of the subset sequence is the same as the element of the second behavior time series, that is, the subset sequence is a valuable sequence.

For example, fig. 6 schematically shows a schematic diagram of filtering a subset sequence, as shown in fig. 6, the subset sequence includes a plurality of sequences with different sequence lengths, the values of elements of the second behavior time sequence are now set to (2,4,18,23,37,41), and the target sequence length is 5, then, after filtering the subset sequence shown in fig. 6, all subset sequences with sequence lengths of 5 are obtained: (4,18,23,37, 41); (2,18,23,37, 41); (2,4,23,37, 41); (2,4,18,37, 41); (2,4,18,23, 41); (2,4,18,23,37). A large number of worthless subset sequences in the subset sequences are filtered through the filtering process, complexity of a calculation process for determining the specific target pairs is reduced, and accuracy of determining the specific target pairs is guaranteed.

Based on the above embodiment shown in fig. 1, step 104 "determining the specific target pair based on the similarity between the determined subset sequence and the target to which the second behavior time sequence belongs" may be implemented in the following manner, and fig. 7 is a schematic flow chart of determining the specific target pair according to an embodiment of the present invention. Referring to fig. 7, the embodiment includes:

701. and respectively determining the behavior data sequence of the corresponding target based on the determined subset sequence and the second behavior time sequence.

And respectively determining the behavior data sequence of the target corresponding to each subset sequence and the behavior data sequence of the target corresponding to the second behavior time sequence.

702. And calculating the similarity of the behavior data sequences of any two targets in the determined targets, and determining the two targets with the similarity larger than a preset threshold value as a specific target pair.

In one embodiment of the invention, the similarity between behavior data sequences corresponding to any two targets in each subset sequence or in the second behavior time sequence is calculated.

In an embodiment of the present invention, similarity calculation is performed on behavior data sequences of any two corresponding targets in the determined subset sequence and the second behavior time sequence, a similarity threshold is preset at the same time, two targets with similarities larger than the similarity threshold are determined as specific target pairs, finally, the obtained specific target pairs are used as a final specific target pair set, and the specific target pair set is applied to a related security protection scene to send out corresponding early warning information.

In one embodiment of the invention, not all targets need to calculate the similarity between two targets, and the difference between the time or days involved in the behavior data of different targets is very large. Therefore, filtering is needed for targets, and only targets with similar behavior sequence length need to calculate the similarity between each two targets. For example: the behavior records of three persons A, B and C9 days before 1 month are shown in the following table 1:

TABLE 1

Time

Number 1

Number 2

No. 3

Number 4

Number 5

Number 6

No. 7

Number 8

Number 9

Record of nail behaviour

A

A、B

C

A

D

B、C

Record of second behavior

C

A

B

A、B

Third action record

C

D

A

Now, assume that the similarity threshold is 3, that is, there are 3-day records with the same behavior in the behavior sequence between two targets to combine into a specific target pair. Then, as shown in Table 1 above, both A and B can produce specific target pairs, and neither C nor A nor B can produce specific target pairs. In this way, a simple determination of the target can be made by its behavioral time-series to determine whether a specific target pair can be generated. Therefore, a behavior time series corresponding to the behavior data series is introduced, and the targets are classified according to the behavior time series. Such as: in the above table 1, the behaviors A, B and C are (1,2,3,6,7,8), (1,2,5,6,8), (3,4,5,9) in sequence. If the intersection of the behavior time sequences of A and B is (1,2,6 and 8) and the length is more than 3, a specific target pair can be generated. However, the length of the intersection of the behavior time sequences of the third and the second is less than 3, the similarity threshold value is not met, and the generation of a specific target pair cannot be seen, so that the specific target pair can be directly filtered out without comparison. Through setting the behavior time sequence of the target, when the length of the sequence is fixed, the number of times of comparison between every two targets can be greatly reduced by filtering the targets with different behavior time sequences, so that the algorithm time complexity is reduced, and practice shows that the step can reduce the calculation amount of tens of millions to tens of thousands or thousands, for example from 593335159 to 1680, and the Shuffle calculation amount of data is reduced from one billion bytes to one million bytes or less.

The specific target pair determination method disclosed by the invention is explained in detail below by taking an example of implementing specific target pair determination through a specific algorithm.

Fig. 8 is a schematic flow chart of determining specific target pairs according to an embodiment of the present invention. Referring to fig. 8, the embodiment includes:

801. inputting a behavior data sequence of a target, inputting a target duration and a similarity threshold;

802. calculating the action time sequence and the corresponding sequence length of each target;

803. setting the length of a target sequence;

804. comparing the sequence length of the behavior time sequence of the target based on the target sequence length, and if the sequence length of the behavior time sequence of the target is greater than the target sequence length, executing step 805; otherwise, go to step 810;

805. generating a second behavior time sequence with the sequence length being the target sequence length;

806. acquiring a first behavior time sequence with the sequence length larger than the target sequence length, determining all subset sequences with the sequence length being the target sequence length, and filtering the subset sequences based on a second behavior time sequence;

807. aggregating the filtered subset sequence and the second behavior time sequence to complete grouping of the corresponding targets;

808. calculating the similarity between the targets in each target group, and determining a specific target pair by using two targets with the similarity meeting a preset similarity threshold;

809. adding the determined specific target pairs into a specific target pair set, and returning to the step 804;

810. and outputting the specific target pair set.

The invention discloses a specific target pair determining method, which comprises the following steps: acquiring a plurality of behavior time sequences based on the behavior data sequences of a plurality of targets, wherein each element of one behavior time sequence corresponds to the occurrence time of each behavior in the behavior data sequence; acquiring a plurality of subset sequences of the first behavior time sequence based on the first behavior time sequence in the plurality of behavior time sequences, wherein the sequence length of the first behavior time sequence is greater than the length of the target sequence, and the sequence length of each subset sequence is the length of the target sequence; determining a subset sequence having the same elements as any second action time sequence in the plurality of action time sequences from the plurality of subset sequences of the first action time sequence, wherein the sequence length of the second action time sequence is equal to the target sequence length; and determining a specific target pair based on the similarity between the determined subset sequence and the target to which the second action time sequence belongs. The invention filters the behavior time sequence with the length larger than that of the target sequence based on the behavior time sequence with the length of the target sequence, thereby reducing the data amount required to be calculated and reducing the complexity of the specific target to the determination process.

All the above-mentioned optional technical solutions can be combined arbitrarily to form the optional embodiments of the present invention, and are not described herein again.

The following are embodiments of the apparatus of the present invention that may be used to perform embodiments of the method of the present invention. For details which are not disclosed in the embodiments of the apparatus of the present invention, reference is made to the embodiments of the method of the present invention. Fig. 9 is a schematic diagram of a specific target pair determining apparatus according to an embodiment of the present invention. Referring to fig. 9, the apparatus includes:

an obtaining module 901, configured to obtain multiple behavior time sequences based on behavior data sequences of multiple targets, where each element of a behavior time sequence corresponds to an occurrence time of each behavior in the behavior data sequence;

a subset sequence obtaining module 902, configured to obtain, based on a first behavior time sequence in the plurality of behavior time sequences, a plurality of subset sequences of the first behavior time sequence, where a sequence length of the first behavior time sequence is greater than a target sequence length, and a sequence length of each subset sequence is the target sequence length;

a determining module 903, configured to determine, from the plurality of subset sequences of the first action time sequence, a subset sequence having the same element as any second action time sequence in the plurality of action time sequences, where a sequence length of the second action time sequence is equal to a target sequence length;

a specific target pair determining module 904, configured to determine a specific target pair based on a similarity between the determined subset sequence and the target to which the second behavior time sequence belongs.

In an embodiment of the present invention, the obtaining module 901 is further specifically configured to:

acquiring identity information corresponding to a plurality of targets;

and sequencing the behavior data based on the occurrence time of the behavior data to obtain behavior data sequences corresponding to the multiple targets.

In an embodiment of the present invention, the obtaining module 901 is specifically configured to:

performing character conversion on the occurrence time of each behavior in the behavior data sequences of the targets to obtain the behavior time in the target format;

and integrating the behavior time of the target format to obtain behavior time sequences corresponding to the behavior data sequences of the targets.

In an embodiment of the present invention, the subset sequence obtaining module 902 is specifically configured to:

determining a sequence length of each behavior time series;

and listing all subset sequences which accord with the length of the target sequence from the first action time sequence.

In an embodiment of the present invention, the determining module 903 is specifically configured to:

In an embodiment of the present invention, the specific target pair determining module 904 is specifically configured to:

and calculating the similarity between the behavior data sequences of any two targets in the determined targets, and determining the two targets with the similarity larger than a preset threshold value as a specific target pair.

It should be noted that: the specific object pair determining apparatus provided in the above embodiments is only illustrated by the division of the above functional modules when determining the specific object pair, and in practical applications, the above function distribution may be completed by different functional modules according to needs, that is, the internal structure of the apparatus is divided into different functional modules to complete all or part of the above described functions. In addition, the specific target pair determining device and the specific target pair determining method provided by the above embodiments belong to the same concept, and specific implementation processes thereof are detailed in the method embodiments and are not described herein again.

Fig. 10 is a block diagram of a terminal 1000 according to an embodiment of the present invention. The terminal 1000 can be: a smart phone, a tablet computer, an MP3 player (Moving Picture Experts Group Audio Layer III, motion video Experts compression standard Audio Layer 3), an MP4 player (Moving Picture Experts Group Audio Layer IV, motion video Experts compression standard Audio Layer 4), a notebook computer, or a desktop computer. Terminal 1000 can also be referred to as user equipment, portable terminal, laptop terminal, desktop terminal, or the like by other names.

In general, terminal 1000 can include: a processor 1001 and a memory 1002.

Processor 1001 may include one or more processing cores, such as a 4-core processor, an 8-core processor, and so forth. The processor 1001 may be implemented in at least one hardware form of a DSP (Digital Signal Processing), an FPGA (Field-Programmable Gate Array), and a PLA (Programmable Logic Array). The processor 1001 may also include a main processor and a coprocessor, where the main processor is a processor for Processing data in an awake state, and is also referred to as a Central Processing Unit (CPU); a coprocessor is a low power processor for processing data in a standby state. In some embodiments, the processor 1001 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content required to be displayed on the display screen. In some embodiments, the processor 1001 may further include an AI (Artificial Intelligence) processor for processing a computing operation related to machine learning.

Memory 1002 may include one or more computer-readable storage media, which may be non-transitory. The memory 1002 may also include high-speed random access memory, as well as non-volatile memory, such as one or more magnetic disk storage devices, flash memory storage devices. In some embodiments, a non-transitory computer readable storage medium in the memory 1002 is configured to store at least one instruction for execution by the processor 1001 to implement the virtual resource determination methods provided by the method embodiments herein.

In some embodiments, terminal 1000 can also optionally include: a peripheral interface 1003 and at least one peripheral. The processor 1001, memory 1002 and peripheral interface 1003 may be connected by a bus or signal line. Various peripheral devices may be connected to peripheral interface 1003 via a bus, signal line, or circuit board. Specifically, the peripheral device includes: at least one of radio frequency circuitry 1004, touch screen display 1005, camera 1006, audio circuitry 1007, positioning components 1008, and power supply 1009.

The peripheral interface 1003 may be used to connect at least one peripheral related to I/O (Input/Output) to the processor 1001 and the memory 1002. In some embodiments, processor 1001, memory 1002, and peripheral interface 1003 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 1001, the memory 1002, and the peripheral interface 1003 may be implemented on separate chips or circuit boards, which are not limited by this embodiment.

The Radio Frequency circuit 1004 is used for receiving and transmitting RF (Radio Frequency) signals, also called electromagnetic signals. The radio frequency circuitry 1004 communicates with communication networks and other communication devices via electromagnetic signals. The radio frequency circuit 1004 converts an electrical signal into an electromagnetic signal to transmit, or converts a received electromagnetic signal into an electrical signal. Optionally, the radio frequency circuit 1004 comprises: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a subscriber identity module card, and so forth. The radio frequency circuit 1004 may communicate with other terminals via at least one wireless communication protocol. The wireless communication protocols include, but are not limited to: metropolitan area networks, various generation mobile communication networks (2G, 3G, 4G, and 5G), Wireless local area networks, and/or WiFi (Wireless Fidelity) networks. In some embodiments, the rf circuit 1004 may further include NFC (Near Field Communication) related circuits, which are not limited in this application.

The display screen 1005 is used to display a UI (User Interface). The UI may include graphics, text, icons, video, and any combination thereof. When the display screen 1005 is a touch display screen, the display screen 1005 also has the ability to capture touch signals on or over the surface of the display screen 1005. The touch signal may be input to the processor 1001 as a control signal for processing. At this point, the display screen 1005 may also be used to provide virtual buttons and/or a virtual keyboard, also referred to as soft buttons and/or a soft keyboard. In some embodiments, display screen 1005 can be one, providing a front panel of terminal 1000; in other embodiments, display 1005 can be at least two, respectively disposed on different surfaces of terminal 1000 or in a folded design; in still other embodiments, display 1005 can be a flexible display disposed on a curved surface or on a folded surface of terminal 1000. Even more, the display screen 1005 may be arranged in a non-rectangular irregular figure, i.e., a shaped screen. The Display screen 1005 may be made of LCD (Liquid Crystal Display), OLED (Organic Light-Emitting Diode), and the like.

The camera assembly 1006 is used to capture images or video. Optionally, the camera assembly 1006 includes a front camera and a rear camera. Generally, a front camera is disposed at a front panel of the terminal, and a rear camera is disposed at a rear surface of the terminal. In some embodiments, the number of the rear cameras is at least two, and each rear camera is any one of a main camera, a depth-of-field camera, a wide-angle camera and a telephoto camera, so that the main camera and the depth-of-field camera are fused to realize a background blurring function, and the main camera and the wide-angle camera are fused to realize panoramic shooting and VR (Virtual Reality) shooting functions or other fusion shooting functions. In some embodiments, camera assembly 1006 may also include a flash. The flash lamp can be a monochrome temperature flash lamp or a bicolor temperature flash lamp. The double-color-temperature flash lamp is a combination of a warm-light flash lamp and a cold-light flash lamp, and can be used for light compensation at different color temperatures.

The audio circuit 1007 may include a microphone and a speaker. The microphone is used for collecting sound waves of a user and the environment, converting the sound waves into electric signals, and inputting the electric signals to the processor 1001 for processing or inputting the electric signals to the radio frequency circuit 1004 for realizing voice communication. For stereo sound collection or noise reduction purposes, multiple microphones can be provided, each at a different location of terminal 1000. The microphone may also be an array microphone or an omni-directional pick-up microphone. The speaker is used to convert electrical signals from the processor 1001 or the radio frequency circuit 1004 into sound waves. The loudspeaker can be a traditional film loudspeaker or a piezoelectric ceramic loudspeaker. When the speaker is a piezoelectric ceramic speaker, the speaker can be used for purposes such as converting an electric signal into a sound wave audible to a human being, or converting an electric signal into a sound wave inaudible to a human being to measure a distance. In some embodiments, the audio circuit 1007 may also include a headphone jack.

A Location component 1008 is employed to locate a current geographic Location of terminal 1000 for purposes of navigation or LBS (Location Based Service). The Positioning component 1008 may be a Positioning component based on the Global Positioning System (GPS) in the united states, the beidou System in china, the graves System in russia, or the galileo System in the european union.

Power supply 1009 is used to supply power to various components in terminal 1000. The power source 1009 may be alternating current, direct current, disposable batteries, or rechargeable batteries. When the power source 1009 includes a rechargeable battery, the rechargeable battery may support wired charging or wireless charging. The rechargeable battery may also be used to support fast charge technology.

In some embodiments, terminal 1000 can also include one or more sensors 1100. The one or more sensors 1100 include, but are not limited to: acceleration sensor 1101, gyro sensor 1102, pressure sensor 1103, fingerprint sensor 1104, optical sensor 1105, and proximity sensor 1106.

Acceleration sensor 1101 can detect acceleration magnitudes on three coordinate axes of a coordinate system established with terminal 1000. For example, the acceleration sensor 1101 may be used to detect components of the gravitational acceleration in three coordinate axes. The processor 1001 may control the touch display screen 1005 to display the user interface in a landscape view or a portrait view according to the gravitational acceleration signal collected by the acceleration sensor 1101. The acceleration sensor 1101 may also be used for acquisition of motion data of a game or a user.

The gyro sensor 1102 can detect the body direction and the rotation angle of the terminal 1000, and the gyro sensor 1101 can cooperate with the acceleration sensor 1101 to acquire the 3D motion of the user on the terminal 1000. The processor 1001 may implement the following functions according to the data collected by the gyro sensor 1102: motion sensing (such as changing the UI according to a user's tilting operation), image stabilization at the time of photographing, game control, and inertial navigation.

Pressure sensor 1103 can be disposed on a side bezel of terminal 1000 and/or on a lower layer of touch display 1005. When pressure sensor 1103 is disposed on a side frame of terminal 1000, a user's grip signal on terminal 1000 can be detected, and processor 1001 performs left-right hand recognition or shortcut operation according to the grip signal collected by pressure sensor 1103. When the pressure sensor 1103 is disposed at a lower layer of the touch display screen 1005, the processor 1001 controls the operability control on the UI interface according to the pressure operation of the user on the touch display screen 1005. The operability control comprises at least one of a button control, a scroll bar control, an icon control and a menu control.

The fingerprint sensor 1104 is used for collecting a fingerprint of the user, and the processor 1001 identifies the user according to the fingerprint collected by the fingerprint sensor 1104, or the fingerprint sensor 1104 identifies the user according to the collected fingerprint. Upon identifying that the user's identity is a trusted identity, the processor 1001 authorizes the user to perform relevant sensitive operations including unlocking a screen, viewing encrypted information, downloading software, paying, and changing settings, etc. Fingerprint sensor 1104 can be disposed on the front, back, or side of terminal 1000. When a physical button or vendor Logo is provided on terminal 1000, fingerprint sensor 1104 can be integrated with the physical button or vendor Logo.

The optical sensor 1105 is used to collect the ambient light intensity. In one embodiment, the processor 1001 may control the display brightness of the touch display screen 1005 according to the ambient light intensity collected by the optical sensor 1105. Specifically, when the ambient light intensity is high, the display brightness of the touch display screen 1005 is increased; when the ambient light intensity is low, the display brightness of the touch display screen 1005 is turned down. In another embodiment, the processor 1001 may also dynamically adjust the shooting parameters of the camera assembly 1006 according to the ambient light intensity collected by the optical sensor 1105.

Proximity sensor 1106, also referred to as a distance sensor, is typically provided on the front panel of terminal 1000. Proximity sensor 1106 is used to capture the distance between a user and the front face of terminal 1000. In one embodiment, when proximity sensor 1106 detects that the distance between the user and the front face of terminal 1000 is gradually reduced, processor 1001 controls touch display 1005 to switch from a bright screen state to a dark screen state; when proximity sensor 1106 detects that the distance between the user and the front face of terminal 1000 is gradually increased, touch display 1005 is controlled by processor 1001 to switch from a breath-screen state to a bright-screen state.

Those skilled in the art will appreciate that the configuration shown in FIG. 10 is not intended to be limiting and that terminal 1000 can include more or fewer components than shown, or some components can be combined, or a different arrangement of components can be employed.

Fig. 11 is a schematic structural diagram of a computer device according to an embodiment of the present invention, where the computer device 1100 may generate a relatively large difference due to different configurations or performances, and may include one or more processors (CPUs) 1101 and one or more memories 1102, where the memory 1202 stores at least one instruction, and the at least one instruction is loaded and executed by the processors 1101 to implement the operation control display method provided by each method embodiment. Certainly, the computer device may further have components such as a wired or wireless network interface, a keyboard, and an input/output interface, so as to perform input and output, and the computer device may further include other components for implementing the functions of the device, which is not described herein again.

In an exemplary embodiment, a computer-readable storage medium, such as a memory, including instructions executable by a processor in a terminal to perform the method for operating control display in the above-described embodiments is also provided. For example, the computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.

The present invention is not limited to the above preferred embodiments, and any modifications, equivalent replacements, improvements, etc. within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for determining a specific target pair, comprising:

acquiring a plurality of subset sequences of the first behavior time sequence based on the first behavior time sequence in the plurality of behavior time sequences, wherein the sequence length of the first behavior time sequence is greater than the length of a target sequence, and the sequence length of each subset sequence is the length of the target sequence;

determining a subset sequence having the same elements as any second behavior time sequence in the plurality of behavior time sequences from among the plurality of subset sequences of the first behavior time sequence, wherein the sequence length of the second behavior time sequence is equal to the target sequence length;

2. The method of claim 1, wherein before obtaining the plurality of behavior time series based on the behavior data series of the plurality of targets, the method further comprises:

acquiring identity information corresponding to a plurality of targets;

3. The method of claim 1, wherein obtaining a plurality of behavior time series based on the behavior data series of the plurality of targets, each element of one behavior time series corresponding to an occurrence time of each behavior in the behavior data series comprises:

converting the occurrence time of each behavior in the behavior data sequences of the targets to obtain the behavior time in the target format;

4. The method of claim 1, wherein obtaining a plurality of subset sequences of the first behavior time sequence based on the first behavior time sequence of the plurality of behavior time sequences comprises:

determining a sequence length of each behavior time series;

5. The method of claim 1, wherein determining, from among the plurality of sequences of subsets of the first sequence of behavior time sequences, a sequence of subsets having a same element as any second sequence of behavior time sequences of the plurality of sequences of behavior time sequences comprises:

6. The method of claim 1, wherein determining a specific target pair based on the similarity between the determined subset sequence and the target to which the second behavior time sequence belongs comprises:

7. A specific target pair determining apparatus, comprising:

a subset sequence obtaining module, configured to obtain, based on a first behavior time sequence in the plurality of behavior time sequences, a plurality of subset sequences of the first behavior time sequence, where a sequence length of the first behavior time sequence is greater than a target sequence length, and a sequence length of each subset sequence is the target sequence length;

a determining module, configured to determine, from a plurality of subset sequences of the first behavior time sequence, a subset sequence having a same element as any second behavior time sequence of the plurality of behavior time sequences, where a sequence length of the second behavior time sequence is equal to the target sequence length;

8. The apparatus of claim 7, wherein the determining module is specifically configured to:

9. A computer device comprising one or more processors and one or more memories having stored therein at least one instruction that is loaded and executed by the one or more processors to perform operations performed by the specific-target pair determination method of any one of claims 1 to 6.

10. A computer-readable storage medium having stored therein at least one instruction, which is loaded and executed by a processor to perform operations performed by the specific target pair determination method according to any one of claims 1 to 6.