Behavior event sequence generation method, device, equipment and storage medium

Abstract

The present application relates to the field of data processing technology, and provides a method, device, equipment and storage medium for generating a behavior event sequence, the method comprising: obtaining multiple historical behavior event sequences of a user; determining a target co-occurrence matrix of multiple historical behavior event sequences, and determining a support matrix corresponding to the target co-occurrence matrix; determining mutually dependent target behavior events in multiple historical behavior event sequences according to the target co-occurrence matrix and the support matrix; obtaining the co-occurrence element value of each target behavior event in the target co-occurrence matrix and the support element value in the support matrix; generating a target behavior event sequence according to the co-occurrence element value and the support element value of each target behavior event, the target behavior event sequence being used to describe the processing order of the target behavior events. The present solution can accurately determine the processing order of mutually dependent events.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method, device, equipment and storage medium for generating a behavior event sequence. Background Art

[0002] With the development of information technology, people are exposed to more and more information, but much of the information is noise to users. For example, most recommended events are independent events with no temporal relationship, such as the recommendation of goods in shopping applications, the recommendation of music in music applications, and the recommendation of videos in video applications. However, some recommended events are independent and have no temporal relationship. However, in some specific cases, independent events have temporal dependencies. For example, applying for a marriage certificate and applying for a birth permit are both independent events, but applying for a birth permit is generally after applying for a marriage certificate. Therefore, there is a dependency between applying for a marriage certificate and applying for a birth permit. At present, there is no accurate event handling order recommendation strategy for such scenarios with both independent and dependent events. Therefore, the sequence recommendation of the handling order of events that are both independent and dependent is a problem that needs to be solved urgently. Summary of the invention

[0003] The main purpose of the present application is to provide a method, device, equipment and storage medium for generating a behavior event sequence, aiming to accurately and quickly generate a processing order of interdependent events.

[0004] In a first aspect, the present application provides a method for generating a behavior event sequence, comprising:

[0005] Acquire multiple historical behavior event sequences of the user, wherein the historical behavior event sequences are used to describe the order in which the historical behavior events are handled;

[0006] Determine a target co-occurrence matrix of the plurality of historical behavior event sequences, and determine a support matrix corresponding to the target co-occurrence matrix;

[0007] Determining mutually dependent target behavior events in the plurality of historical behavior event sequences according to the target co-occurrence matrix and the support matrix;

[0008] Obtaining the co-occurrence element value in the target co-occurrence matrix and the support element value in the support matrix for each target behavior event;

[0009] A target behavior event sequence is generated according to the co-occurrence element value and the support element value of each target behavior event, and the target behavior event sequence is used to describe the processing order of the target behavior events.

[0010] In a second aspect, the present application further provides a behavior event sequence generation device, the behavior event sequence generation device comprising an acquisition module, a first determination module, a second determination module and a generation module, wherein:

[0011] The acquisition module is used to acquire multiple historical behavior event sequences;

[0012] The first determination module is used to determine a target co-occurrence matrix of the plurality of historical behavior event sequences, and determine a support matrix corresponding to the target co-occurrence matrix;

[0013] The second determination module is used to determine the mutually dependent target behavior events in the plurality of historical behavior event sequences according to the target co-occurrence matrix and the support matrix;

[0014] The acquisition module is further used to acquire the co-occurrence element value in the target co-occurrence matrix and the support element value in the support matrix for each target behavior event;

[0015] The generating module is used to generate a target behavior event sequence according to the co-occurrence element value and the support element value of each target behavior event, and the target behavior event sequence is used to describe the processing order of the target behavior events.

[0016] In a third aspect, the present application also provides a computer device, comprising a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, the steps of the behavior event sequence generation method as described above are implemented.

[0017] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps of the behavior event sequence generation method as described above are implemented.

[0018] The present application provides a method, device, equipment and storage medium for generating a behavior event sequence. The present application obtains multiple historical behavior event sequences of a user; then determines the target co-occurrence matrix of the multiple historical behavior event sequences, and determines the support matrix corresponding to the target co-occurrence matrix; then determines the interdependent target behavior events in the multiple historical behavior event sequences based on the target co-occurrence matrix and the support matrix; obtains the co-occurrence element values ​​of each target behavior event in the target co-occurrence matrix and the support element values ​​in the support matrix; and then generates a target behavior event sequence based on the co-occurrence element values ​​and the support element values ​​of each target behavior event. This solution determines the target co-occurrence matrix and the support matrix of multiple historical behavior event sequences, and accurately and quickly determines the processing order of interdependent events based on the target co-occurrence matrix and the support matrix. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0020] Figure 1 A schematic diagram of the steps of a method for generating a behavior event sequence provided in an embodiment of the present application;

[0021] Figure 2 for Figure 1 A flowchart of the sub-steps of the method for generating a sequence of behavioral events in FIG.

[0022] Figure 3 A schematic block diagram of a behavior event sequence generating device provided in an embodiment of the present application;

[0023] Figure 4 for Figure 3 A schematic block diagram of submodules of a behavior event sequence generating device in;

[0024] Figure 5 A schematic block diagram of the structure of a computer device provided in an embodiment of the present application.

[0025] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0026] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0027] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0028] The embodiments of the present application provide a method, apparatus, device and storage medium for generating a behavior event sequence. The method for generating a behavior event sequence can be applied to a terminal device, which can be a mobile phone, a tablet computer, a laptop computer, a desktop computer, a personal digital assistant and a wearable device.

[0029] In conjunction with the accompanying drawings, some embodiments of the present application are described in detail below. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0030] Please refer to Figure 1 , Figure 1 A schematic diagram of the steps of a method for generating a behavior event sequence provided in an embodiment of the present application.

[0031] like Figure 1 As shown, the behavior event sequence generation method includes steps S101 to S105.

[0032] Step S101: Acquire multiple historical behavior event sequences of a user, wherein the historical behavior event sequences are used to describe the processing order of historical behavior events.

[0033] Among them, historical behavior events are events that the user has handled before, including user behavior events such as the user opening an application event, the user selecting a product in the application event, the user clicking to play music in the application event, and the user going to a government agency to handle registration events. For example, the user opens application A event, the user opens application B event, the user selects clothes in a shopping application event, the user goes to the Civil Affairs Bureau to register for marriage, and the user goes to the Civil Affairs Bureau to apply for a birth certificate.

[0034] Among them, the historical behavior event sequence is used to describe the processing order of historical behavior events. For example, the user's historical behavior events are: the user watched news A at 12:10, the user watched news B at 12:15, and the user watched news C at 12:17. The historical behavior event sequence can be [A, B, C].

[0035] In one embodiment, the order of handling historical behavior events is obtained, and a sequence of multiple historical behavior events of the user is obtained according to the order in which the user handles the historical behavior events. The order of handling can be the timestamp corresponding to the handling of each behavior event.

[0036] Step S102: determining a target co-occurrence matrix of the plurality of historical behavior event sequences, and determining a support matrix corresponding to the target co-occurrence matrix.

[0037] In one embodiment, the co-occurrence matrix of each historical behavior event sequence is determined; and the target co-occurrence matrix is ​​determined based on the co-occurrence matrix of each historical behavior event sequence. By determining the co-occurrence matrix of each historical behavior event sequence, and based on the co-occurrence matrix of each historical behavior event sequence, the target co-occurrence matrix can be accurately determined.

[0038] In one embodiment, the method for determining the co-occurrence matrix of each historical behavior event sequence can be: according to the order in which users handle events, the number of historical behavior events handled after each historical behavior event and the number of historical behavior events handled after that event are counted to obtain the co-occurrence element values ​​of the co-occurrence matrix, and each co-occurrence element value is arranged in sequence according to the order in which the historical behavior events are handled to obtain the co-occurrence matrix of the historical behavior event sequence.

[0039] For example, a user's historical behavior event sequence is [4, 1, 3, 5, 4, A, 3, A, 3, 5, 2, 5, B, C, 2, 4], where 1 represents historical behavior event 1, 2 represents historical behavior event 2, 3 represents historical behavior event 3, 4 represents historical behavior event 4, 5 represents historical behavior event 5, A represents historical behavior event A, B represents historical behavior event B, C represents historical behavior event C, and the number of times historical behavior event 1 is handled after historical behavior event 1 is counted is 0, and the number of times historical behavior event 1 is handled after historical behavior event 1 is counted is The number of historical behavior event 2 is 2 times, the number of historical behavior event 3 handled after historical behavior event 1 is 3 times, the number of historical behavior event 4 handled after historical behavior event 1 is 2 times, the number of historical behavior event 5 handled after historical behavior event 1 is 3 times, the number of historical behavior event A handled after historical behavior event 1 is 2 times, the number of historical behavior event B handled after historical behavior event 1 is 1 time, and the number of historical behavior event C handled after historical behavior event 1 is 1 time.

[0040] Similarly, after handling historical behavior event 2, the numbers of historical behavior event 1, historical behavior event 2, historical behavior event 3, historical behavior event 4, historical behavior event 5, historical behavior event A, historical behavior event B, and historical behavior event C were 0, 1, 0, 2, 1, 0, 1, and 1 respectively; similarly, after handling historical behavior event 3, the numbers of historical behavior event 1, historical behavior event 2, historical behavior event 3, historical behavior event 4, historical behavior event 5, historical behavior event A, historical behavior event B, and historical behavior event C were 0, 6, 3, 4, 7, 3, 3, and 3 respectively.

[0041] Similarly, after handling historical behavior event 4, the numbers of historical behavior event 1, historical behavior event 2, historical behavior event 3, historical behavior event 4, historical behavior event 5, historical behavior event A, historical behavior event B, and historical behavior event C were 1, 4, 5, 3, 5, 4, 2, and 2 times respectively; similarly, after handling historical behavior event 5, the numbers of historical behavior event 1, historical behavior event 2, historical behavior event 3, historical behavior event 4, historical behavior event 5, historical behavior event A, historical behavior event B, and historical behavior event C were 0, 5, 2, 4, 3, 2, 3, and 3 times respectively.

[0042] Similarly, the number of times historical behavior event 1, historical behavior event 2, historical behavior event 3, historical behavior event 4, historical behavior event 5, historical behavior event A, historical behavior event B, and historical behavior event C were handled after historical behavior event A was 0, 4, 3, 2, 4, 1, 2, and 2 times respectively; similarly, the number of times historical behavior event 1, historical behavior event 2, historical behavior event 3, historical behavior event 4, historical behavior event 5, historical behavior event A, historical behavior event B, and historical behavior event C were handled after historical behavior event B was 0, 1, 0, 1, 0, 0, 0, and 1 time respectively.

[0043] Similarly, the number of times historical behavior event 1, historical behavior event 2, historical behavior event 3, historical behavior event 4, historical behavior event 5, historical behavior event A, historical behavior event B, and historical behavior event C were handled after historical behavior event C was handled were 0 times, 1 time, 0 times, 1 time, 0 times, 0 times, 0 times, and 0 times respectively. The value of each co-occurrence element is arranged in sequence according to the order of handling historical behavior events to obtain the co-occurrence matrix of the historical behavior event sequence, which is the co-occurrence matrix shown in Matrix 1.

[0044] Matrix 1

[0045]

[0046] In one embodiment, according to the co-occurrence matrix of each historical behavior event sequence, the target co-occurrence matrix can be determined by performing a matrix addition operation on the co-occurrence matrix of each historical behavior event sequence to obtain the target co-occurrence matrix. By performing a matrix addition operation on the co-occurrence matrix of each historical behavior event sequence, the target co-occurrence matrix can be accurately and quickly determined.

[0047] For example, the user's historical behavior event sequence one is [4, 1, 3, 5, 4, A, 3, A, 3, 5, 2, 5, B, C, 2, 4], the historical behavior event sequence two is [1, 1, 3, 4, 5, 1, 3, 4, 3, 5, 2], the historical behavior event sequence three is [4, 5, 3, 1, 5, 1, 1, 4, 1, 5, 4, A, 3, 2, 3, B, 1, 2, C, 5], the historical behavior event sequence four is [5, 3, 5, 2, A, B, C, 5], and the historical behavior event sequence five is [1 , 5,3,4,1,1,2,A,B], historical behavior event sequence six is ​​[3,5,2,2,A,5,4,5,3,4,B,4,3,1,3,A,1,4,5,3], historical behavior event sequence seven is [3,4,A,1,1,2,2,B,1], historical behavior event sequence eight is [4,1,3,1,A,B,1], historical behavior event sequence nine is [5,4,A,B], historical behavior event sequence ten is [5,4,1,A,B], historical behavior event sequence eleven is [1,2,2,3,5,3,1,A,5], historical behavior event sequence twelve is [3,3,4,3,2,5,1,4,1,3,1,5,3,A,2,2,4,3,5,B], historical behavior event sequence thirteen is [1,5,2,3,A,B,C], historical behavior event sequence fourteen is [4,1,3,A,B,2,4,5,4], historical behavior event sequence fifteen is [2,5,1,A,2,1,4,4,3,1,B,C,2,1,1,5,5,1 ], historical behavior event sequence sixteen is [4, 1, 3, 2, 5, 3, A, 1, 2, 3, 1], historical behavior event sequence seventeen is [5, 4, 4, A, B], historical behavior event sequence eighteen is [3, 3, A, 3, 3, 1, 3], historical behavior event sequence nineteen is [3, 4, 5, 2, 3, 1, A, B, 4, 2, 1, C, 3, 2], historical behavior event sequence twenty is [3, 3, 1, 4, A, 1, 4, 4, 1, 3, 3, 2, 2, B, 5, 4, 1, 1, 1],

[0048] Determine the co-occurrence matrix corresponding to the historical behavior event sequence one: one, the co-occurrence matrix corresponding to the historical behavior event sequence two: two, the co-occurrence matrix corresponding to the historical behavior event sequence three: three, the co-occurrence matrix corresponding to the historical behavior event sequence four: four, the co-occurrence matrix corresponding to the historical behavior event sequence five: five, the co-occurrence matrix corresponding to the historical behavior event sequence six: six, the co-occurrence matrix corresponding to the historical behavior event sequence seven: seven, the co-occurrence matrix corresponding to the historical behavior event sequence eight: eight, the co-occurrence matrix corresponding to the historical behavior event sequence nine: nine, the co-occurrence matrix corresponding to the historical behavior event sequence ten: ten, the co-occurrence matrix corresponding to the historical behavior event sequence eleven: eleven, the co-occurrence matrix corresponding to the historical behavior event sequence twelve: twelve, the co-occurrence matrix corresponding to the historical behavior event sequence thirteen: thirteen, the co-occurrence matrix corresponding to the historical behavior event sequence fourteen: fourteen, the co-occurrence matrix corresponding to the historical behavior event sequence Column 15 corresponds to the co-occurrence matrix 15, the co-occurrence matrix 16 corresponding to the historical behavior event sequence 16, the co-occurrence matrix 17 corresponding to the historical behavior event sequence 17, the co-occurrence matrix 18 corresponding to the historical behavior event sequence 18, the co-occurrence matrix 19 corresponding to the historical behavior event sequence 19, and the co-occurrence matrix 20 corresponding to the historical behavior event sequence 20, add the co-occurrence matrix 1, co-occurrence matrix 2, co-occurrence matrix 3, co-occurrence matrix 4, co-occurrence matrix 5, co-occurrence matrix 6, co-occurrence matrix 7, co-occurrence matrix 8, co-occurrence matrix 9, co-occurrence matrix 10, co-occurrence matrix 11, co-occurrence matrix 12, co-occurrence matrix 13, co-occurrence matrix 14, co-occurrence matrix 15, co-occurrence matrix 16, co-occurrence matrix 17, co-occurrence matrix 18, co-occurrence matrix 19, and co-occurrence matrix 20 to obtain the target co-occurrence matrix as shown in Matrix 2.

[0049] Matrix 2

[0050]

[0051] It should be noted that the historical behavior event sequence can be processed by a sparse matrix to reduce the complexity of the calculation and improve the accuracy and efficiency of the target co-occurrence matrix calculation. Among them, the sparse matrix method for processing the behavior event sequence can be selected according to the actual situation and is not specifically limited here.

[0052] In one embodiment, the inverse matrix of the target co-occurrence matrix is ​​determined, and a matrix subtraction operation is performed on the target co-occurrence matrix and the inverse matrix to obtain a first matrix; a matrix addition operation is performed on the target co-occurrence matrix and the inverse matrix to obtain a second matrix; and a matrix division operation is performed on the first matrix and the second matrix to obtain a support matrix. The value range of each support element value in the support matrix is ​​[-1, 1], and the closer the support element value is to 1, the higher the degree of dependence of the target behavior events that are mutually dependent events.

[0053] Exemplarily, the target co-occurrence matrix is ​​the co-occurrence matrix shown in Matrix 2, the target co-occurrence matrix is ​​subjected to an inverse transformation to obtain an inverse matrix, the target co-occurrence matrix and the inverse matrix are subjected to a matrix subtraction operation to obtain a first matrix, the target co-occurrence matrix and the inverse matrix are subjected to a matrix addition operation to obtain a second matrix, and the first matrix is ​​divided by the second matrix to obtain a support matrix as shown in Matrix 3.

[0054] Matrix 3

[0055]

[0056] Step S103: Determine mutually dependent target behavior events in the plurality of historical behavior event sequences according to the target co-occurrence matrix and the support matrix.

[0057] Among them, the target behavior event is an event whose event processing sequence is mutually dependent, for example, shopping, selecting goods and paying, the processing sequence is first selecting goods and then paying, so selecting goods and paying are mutually dependent target events. The co-occurrence element value of the target behavior event is greater than the preset co-occurrence element value, and the support element value is greater than the preset support element value.

[0058] In one embodiment, a preset co-occurrence element value and a preset support element value are obtained, and the behavior events with a co-occurrence element value greater than the preset co-occurrence element value and a support element value greater than the preset support element value are screened to obtain mutually dependent target behavior events in multiple historical behavior event sequences. Among them, the preset co-occurrence element value and the preset support element value can be set according to actual conditions, and this application does not make specific restrictions on this. For example, the preset co-occurrence element value and the preset support element value can be set to 5 and 0.85 respectively. By screening the behavior events, the mutually dependent target behavior events in the historical behavior event sequence can be accurately determined.

[0059] Exemplarily, a preset co-occurrence element value of 5 and a preset support element value of 0.85 are obtained, and behavioral events whose co-occurrence element values ​​are greater than 5 and whose support element values ​​are greater than 0.85 are queried from matrix 2 and support matrix 3 of the target co-occurrence matrix, and the target behavioral events are obtained as behavioral event A, behavioral event B, and behavioral event C.

[0060] Step S104: Obtain the co-occurrence element value in the target co-occurrence matrix and the support element value in the support matrix for each target behavior event.

[0061] After the target behavior event is determined, the co-occurrence element value of the target behavior event is obtained from the target co-occurrence matrix and the support element value of the target behavior event is obtained from the support matrix.

[0062] Exemplarily, the target behavior events include behavior event A, behavior event B and behavior event C. The co-occurrence element value of behavior event B depending on behavior event A is 17, the co-occurrence element value of behavior event C depending on behavior event A is 7, and the co-occurrence element value of behavior event C depending on behavior event B is 6 from the target co-occurrence matrix of matrix 2. The support element value of behavior event B depending on behavior event A is 0.89, the support element value of behavior event C depending on behavior event A is 1.00, and the support element value of behavior event C depending on behavior event B is 1.00.

[0063] Step S105 : generating a target behavior event sequence according to the co-occurrence element value and the support element value of each target behavior event, wherein the target behavior event sequence is used to describe the processing order of the target behavior events.

[0064] The target behavior event sequence is used to describe the order of handling the target behavior events. For example, if the target behavior event sequence is [C, A, D, B], then the order of handling the behavior events by the user is behavior event C, behavior event A, behavior event D, and behavior event B.

[0065] In one embodiment, if Figure 2 As shown, step S105 includes sub-steps S1051 and S1052.

[0066] Sub-step S1051: determining a forward event sequence and a reverse event sequence of each target behavior event according to the co-occurrence element value and the support element value of each target behavior event.

[0067] According to the support element value of each target behavior event, the positive behavior event of each behavior event and the reverse behavior event of each behavior event are determined, the positive event sequence of each behavior event is determined according to the positive behavior event of each behavior event, and the reverse behavior event sequence of each behavior event is determined according to the reverse behavior event of each behavior event.

[0068] In one embodiment, based on the support element value of each target behavior event, the method for determining the positive behavior event of each behavior event and the reverse behavior event of each behavior event can be: the target behavior event with a support element value greater than or equal to 0 is regarded as a positive behavior event, and the target behavior event with a support element value less than 0 is regarded as a reverse behavior event.

[0069] Exemplarily, the support element value from behavior event A to behavior event B is 0.89, the support element value from behavior event A to behavior event C is 1.00, the support element value from behavior event B to behavior event A is -0.89, the support element value from behavior event B to behavior event C is 1.00, the support element value from behavior event C to behavior event A is -1.00, and the support element value from behavior event C to behavior event B is -1.00. The target behavior events with support element values ​​greater than or equal to 0 are taken as positive behavior events, and the target behavior events with support element values ​​less than 0 are taken as reverse behavior events. The positive behavior event sequence of behavior event A is [B, 17; C, 7], the positive behavior event sequence of behavior event B is [C, 6], the reverse behavior event sequence of behavior event B is [A, 17], and the reverse behavior event sequence of behavior event C is [A, 7; B, 6].

[0070] Sub-step S1052: generating a target behavior event sequence according to the forward event sequence and the reverse event sequence of each target behavior event.

[0071] In one embodiment, according to the forward event sequence and the reverse event sequence of each target behavior event, the intermediate behavior event sequence between each target behavior event is determined; according to the forward event sequence of each target behavior event and the intermediate behavior event sequence between each target behavior event, the target behavior event sequence is generated. By subtracting the intermediate behavior event sequence between the target behavior events from the forward behavior event sequence of the target behavior event, the target behavior event sequence can be accurately determined.

[0072] Exemplarily, the forward event sequence of behavior event A is [B, 17; C, 7], the forward behavior event sequence of behavior event B is [C, 6], the reverse behavior event sequence of behavior event B is [A, 17], and the reverse behavior event sequence of behavior event C is [A, 7; B, 6]. The intermediate event between the forward event sequence of behavior event A [B, 17; C, 7] and the reverse behavior event sequence of behavior event C [A, 7; B, 6] is behavior event B. Therefore, the forward event sequence of behavior event A is [B, 17; C, 7] minus the forward behavior event sequence of behavior event B is [C, 6], and the behavior event sequence of behavior event A is [B, 17; C, 1]. The forward behavior event sequence of each behavior event is connected to obtain the target behavior event sequence [A, B, C]. Therefore, the processing order of user behavior events is behavior event A, behavior event B, and behavior event C.

[0073] The behavior event sequence generation method provided in the above embodiment obtains multiple historical behavior event sequences of the user; then determines the target co-occurrence matrix of the multiple historical behavior event sequences, and determines the support matrix corresponding to the target co-occurrence matrix; then determines the interdependent target behavior events in the multiple historical behavior event sequences based on the target co-occurrence matrix and the support matrix; obtains the co-occurrence element values ​​of each target behavior event in the target co-occurrence matrix and the support element values ​​in the support matrix; then generates a target behavior event sequence based on the co-occurrence element values ​​and the support element values ​​of each target behavior event, and the target behavior event sequence is used to describe the processing order of the target behavior events. This scheme can accurately determine the processing order of interdependent events by determining the target co-occurrence matrix and the support matrix of multiple historical behavior event sequences, and based on the target co-occurrence matrix and the support matrix.

[0074] See also Figure 3 , Figure 3 A schematic block diagram of a behavior event sequence generation provided in an embodiment of the present application.

[0075] like Figure 3 As shown, the behavior event sequence generating device 200 includes an acquisition module 210, a first determination module 220, a second determination module 230 and a generation module 240, wherein:

[0076] The acquisition module 210 is used to acquire multiple historical behavior event sequences;

[0077] The first determination module 220 is used to determine a target co-occurrence matrix of the plurality of historical behavior event sequences, and determine a support matrix corresponding to the target co-occurrence matrix;

[0078] The second determination module 230 is used to determine the mutually dependent target behavior events in the plurality of historical behavior event sequences according to the target co-occurrence matrix and the support matrix;

[0079] The acquisition module 210 is further used to acquire the co-occurrence element value in the target co-occurrence matrix and the support element value in the support matrix for each target behavior event;

[0080] The generating module 240 is used to generate a target behavior event sequence according to the co-occurrence element value and the support element value of each target behavior event, and the target behavior event sequence is used to describe the processing order of the target behavior events.

[0081] In one embodiment, the first determining module 220 is further configured to:

[0082] determining a co-occurrence matrix for each of said historical behavioral event sequences;

[0083] The target co-occurrence matrix is ​​determined according to the co-occurrence matrix of each of the historical behavior event sequences.

[0084] In one embodiment, the first determining module 220 is further configured to:

[0085] A matrix addition operation is performed on the co-occurrence matrix of each of the historical behavior event sequences to obtain the target co-occurrence matrix.

[0086] In one embodiment, the first determining module 220 is further configured to:

[0087] Determine an inverse matrix of the target co-occurrence matrix, and perform a matrix subtraction operation on the target co-occurrence matrix and the inverse matrix to obtain a first matrix;

[0088] Performing a matrix addition operation on the target co-occurrence matrix and the inverse matrix to obtain a second matrix;

[0089] Perform a matrix division operation on the first matrix and the second matrix to obtain the support matrix.

[0090] In one embodiment, if Figure 4 As shown, the generating module 240 includes:

[0091] A determination submodule 241, configured to determine a forward event sequence and a reverse event sequence of each of the target behavior events according to the co-occurrence element value and the support element value of each of the target behavior events;

[0092] The generating submodule 242 is used to generate a target behavior event sequence according to the forward event sequence and the reverse event sequence of each target behavior event.

[0093] In one embodiment, the generating submodule 242 is further used for:

[0094] Determining an intermediate behavior event sequence between each of the target behavior events according to the forward event sequence and the reverse event sequence of each of the target behavior events;

[0095] A target behavior event sequence is generated according to the forward event sequence of each target behavior event and the intermediate behavior event sequence between each target behavior event.

[0096] It should be noted that those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and modules and units can refer to the corresponding processes in the aforementioned behavior event sequence generation method embodiment, and will not be repeated here.

[0097] The apparatus provided in the above embodiment may be implemented in the form of a computer program. The computer program may be Figure 5 Runs on the computer device shown.

[0098] See also Figure 5 , Figure 5 A schematic block diagram of the structure of a computer device provided in an embodiment of the present application. The computer device may be a server or a terminal.

[0099] like Figure 5 As shown, the computer device includes a processor, a memory, and a network interface connected via a system bus, wherein the memory may include a non-volatile storage medium and an internal memory.

[0100] The non-volatile storage medium can store an operating system and a computer program. The computer program includes program instructions, and when the program instructions are executed, the processor can execute any one of the behavior event sequence generation methods.

[0101] The processor is used to provide computing and control capabilities and support the operation of the entire computer equipment.

[0102] The internal memory provides an environment for the operation of the computer program in the non-volatile storage medium. When the computer program is executed by the processor, the processor can execute any behavior event sequence generation method.

[0103] The network interface is used for network communication. Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0104] It should be understood that the bus is, for example, an I2C (Inter-integrated Circuit) bus, the memory may be a Flash chip, a read-only memory (ROM) disk, an optical disk, a USB flash drive or a mobile hard disk, etc., the processor may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0105] In one embodiment, the processor is used to run a computer program stored in the memory to implement the following steps:

[0106] Acquire multiple historical behavior event sequences of the user, wherein the historical behavior event sequences are used to describe the order in which the historical behavior events are handled;

[0107] Determine a target co-occurrence matrix of the plurality of historical behavior event sequences, and determine a support matrix corresponding to the target co-occurrence matrix;

[0108] Determining mutually dependent target behavior events in the plurality of historical behavior event sequences according to the target co-occurrence matrix and the support matrix;

[0109] Obtaining the co-occurrence element value in the target co-occurrence matrix and the support element value in the support matrix for each target behavior event;

[0110] A target behavior event sequence is generated according to the co-occurrence element value and the support element value of each target behavior event, and the target behavior event sequence is used to describe the processing order of the target behavior events.

[0111] In one embodiment, the processor, when implementing the step of determining the target co-occurrence matrix of the plurality of historical behavior event sequences, is configured to implement:

[0112] determining a co-occurrence matrix for each of said historical behavioral event sequences;

[0113] The target co-occurrence matrix is ​​determined according to the co-occurrence matrix of each of the historical behavior event sequences.

[0114] In one embodiment, when the processor determines the target co-occurrence matrix according to the co-occurrence matrix of each of the historical behavior event sequences, it is configured to implement:

[0115] A matrix addition operation is performed on the co-occurrence matrix of each of the historical behavior event sequences to obtain the target co-occurrence matrix.

[0116] In one embodiment, the processor, when implementing the determining of the support matrix corresponding to the target co-occurrence matrix, is used to implement:

[0117] Determine an inverse matrix of the target co-occurrence matrix, and perform a matrix subtraction operation on the target co-occurrence matrix and the inverse matrix to obtain a first matrix;

[0118] Performing a matrix addition operation on the target co-occurrence matrix and the inverse matrix to obtain a second matrix;

[0119] Perform a matrix division operation on the first matrix and the second matrix to obtain the support matrix.

[0120] In one embodiment, the co-occurrence element value of the target behavior event is greater than a preset co-occurrence element value, and the support element value is greater than a preset support element value.

[0121] In one embodiment, when the processor generates the target behavior event sequence according to the co-occurrence element value and the support element value of each target behavior event, it is configured to implement:

[0122] Determine a forward event sequence and a reverse event sequence of each target behavior event according to the co-occurrence element value and the support element value of each target behavior event;

[0123] A target behavior event sequence is generated according to the forward event sequence and the reverse event sequence of each target behavior event.

[0124] In one embodiment, when the processor generates the target behavior event sequence according to the forward event sequence and the reverse event sequence of each target behavior event, it is configured to implement:

[0125] Determining an intermediate behavior event sequence between each of the target behavior events according to the forward event sequence and the reverse event sequence of each of the target behavior events;

[0126] A target behavior event sequence is generated according to the forward event sequence of each target behavior event and the intermediate behavior event sequence between each target behavior event.

[0127] It should be noted that those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the computer device described above can refer to the corresponding process in the aforementioned behavior event sequence generation method embodiment, which will not be repeated here.

[0128] An embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored. The computer program includes program instructions. The method implemented when the program instructions are executed can refer to the various embodiments of the behavior event sequence generation method of the present application.

[0129] The computer-readable storage medium may be an internal storage unit of the computer device described in the foregoing embodiment, such as a hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc., equipped on the computer device.

[0130] It should be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in this application specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0131] It should also be understood that the term "and / or" used in the specification of this application and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, including these combinations. It should be noted that, in this article, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "including a..." does not exclude the presence of other identical elements in the process, method, article or system including the element.

[0132] The serial numbers of the embodiments of the present application are for description only and do not represent the advantages and disadvantages of the embodiments. The above description is only a specific implementation mode of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A method for generating a behavioral event sequence, characterized in that: include: Acquire multiple historical behavior event sequences of the user, wherein the historical behavior event sequences are used to describe the order in which the historical behavior events are handled; Determine a co-occurrence matrix of each of the historical behavior event sequences, perform matrix addition operation on the co-occurrence matrix of each of the historical behavior event sequences, and obtain a target co-occurrence matrix, wherein the co-occurrence matrix is ​​determined based on the historical behavior events handled after each historical behavior event and the number of the historical behavior events handled after the historical behavior event; Determine an inverse matrix of the target co-occurrence matrix, and perform a matrix subtraction operation on the target co-occurrence matrix and the inverse matrix to obtain a first matrix; Performing a matrix addition operation on the target co-occurrence matrix and the inverse matrix to obtain a second matrix, and performing a matrix division operation on the first matrix and the second matrix to obtain a support matrix; Determining mutually dependent target behavior events in the plurality of historical behavior event sequences according to the target co-occurrence matrix and the support matrix; Obtaining the co-occurrence element value in the target co-occurrence matrix and the support element value in the support matrix for each target behavior event; A target behavior event sequence is generated according to the co-occurrence element value and the support element value of each target behavior event, and the target behavior event sequence is used to describe the processing order of the target behavior events.

2. The method for generating a behavioral event sequence according to claim 1, characterized in that: The co-occurrence element value of the target behavior event is greater than a preset co-occurrence element value, and the support element value is greater than a preset support element value.

3. The method for generating a behavioral event sequence according to any one of claims 1 to 2, characterized in that: Generating a target behavior event sequence according to the co-occurrence element value and the support element value of each target behavior event includes: Determine a forward event sequence and a reverse event sequence of each target behavior event according to the co-occurrence element value and the support element value of each target behavior event; A target behavior event sequence is generated according to the forward event sequence and the reverse event sequence of each target behavior event.

4. The method for generating a behavioral event sequence according to claim 3, characterized in that: The step of generating a target behavior event sequence according to the forward event sequence and the reverse event sequence of each target behavior event comprises: Determining an intermediate behavior event sequence between each of the target behavior events according to the forward event sequence and the reverse event sequence of each of the target behavior events; A target behavior event sequence is generated according to the forward event sequence of each target behavior event and the intermediate behavior event sequence between each target behavior event.

5. A behavior event sequence generating device, characterized in that: The behavior event sequence generating device comprises an acquisition module, a first determination module, a second determination module and a generation module, wherein: The acquisition module is used to acquire multiple historical behavior event sequences; The first determination module is used to determine the co-occurrence matrix of each of the historical behavior event sequences, perform matrix addition operations on the co-occurrence matrices of each of the historical behavior event sequences to obtain a target co-occurrence matrix, wherein the co-occurrence matrix is ​​determined based on the historical behavior events handled after each historical behavior event and the number of historical behavior events handled after the historical behavior event; determine the inverse matrix of the target co-occurrence matrix, and perform matrix subtraction operations on the target co-occurrence matrix and the inverse matrix to obtain a first matrix; perform matrix addition operations on the target co-occurrence matrix and the inverse matrix to obtain a second matrix, and perform matrix division operations on the first matrix and the second matrix to obtain a support matrix; The second determination module is used to determine the mutually dependent target behavior events in the plurality of historical behavior event sequences according to the target co-occurrence matrix and the support matrix; The acquisition module is further used to acquire the co-occurrence element value in the target co-occurrence matrix and the support element value in the support matrix for each target behavior event; The generating module is used to generate a target behavior event sequence according to the co-occurrence element value and the support element value of each target behavior event, and the target behavior event sequence is used to describe the processing order of the target behavior events.

6. A computer device, characterized in that: The computer device includes a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, the steps of the behavior event sequence generation method according to any one of claims 1 to 5 are implemented.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, the steps of the behavior event sequence generation method according to any one of claims 1 to 5 are implemented.

Images