A service feature processing method, device and electronic device based on length integration

Abstract

The embodiment of this specification provides a service feature processing method based on length integration, which obtains multiple features of the same attribute of the user in the service, generates a multidimensional feature sequence according to a preset density parameter, extracts a local feature sequence in the multidimensional feature sequence, determines multiple mapping paths between the multidimensional feature sequence and the local feature sequence, determines the cumulative distance of each mapping path, selects the mapping path with the shortest cumulative distance as the optimal path, integrates the multidimensional feature sequence and the local feature sequence to the same length according to the feature correspondence in the optimal path, determines the distance similarity between the multidimensional feature sequence after the integration length and the multidimensional feature sequence, and determines the user's feature change attribute information according to the distance similarity. The feature change attribute information is determined so as to provide services quickly, reduce the risk of data query failure, and improve service security.

Description

Technical Field

[0001] The present application relates to the field of computers, and in particular to a service feature processing method, device and electronic device based on length integration. Background Art

[0002] When conducting business, some business information will be generated over time. This business information can reflect changes in users or the environment to a certain extent. Therefore, the industry needs to pay attention to its changes so as to adopt response strategies in a timely manner and improve business levels.

[0003] At present, when calculating the change attribute information in the industry, most of them divide a large time period into multiple non-overlapping equal-length time periods. Since the divided time periods are of equal length, the number of features is the same, and the features between different time periods can correspond one to one, so the change attributes can be directly compared and calculated.

[0004] However, this approach cannot take into account the integrity of features over a large period of time, resulting in low accuracy of the final change attributes, a high risk of data query failures, and poor service security.

[0005] However, if multiple overall features within a long period of time are used as one of the comparison objects, the industry currently lacks a comparison object and processing method for comparing and calculating the change attributes.

[0006] In this case, it is necessary to provide a new method to take into account the temporal integrity and improve the calculation accuracy of the attributes of business feature changes in order to provide services quickly, reduce the risk of data query failures, and improve service security. Summary of the invention

[0007] The embodiments of this specification provide a service feature processing method, device and electronic device based on length integration, which are used to reduce the risk of data query failure and improve service security.

[0008] The embodiment of this specification provides a service feature processing method based on length integration, including:

[0009] Acquire multiple features of the same attribute of the user in the business, generate a multidimensional feature sequence according to a preset density parameter, and extract a local feature sequence in the multidimensional feature sequence;

[0010] Determining a plurality of mapping paths between the multidimensional feature sequence and the local feature sequence;

[0011] Determine the cumulative distance of each mapping path, and select the mapping path with the shortest cumulative distance as the optimal path;

[0012] Integrate the multidimensional feature sequence and the local feature sequence to the same length according to the feature correspondence in the optimal path, and determine the distance similarity between the multidimensional feature sequence and the multidimensional feature sequence after the integration length;

[0013] According to the distance similarity, characteristic change attribute information of the user is determined.

[0014] Optionally, the acquiring of multiple features of the same attribute of the user in the business and generating a multi-dimensional feature sequence according to a preset density parameter includes:

[0015] According to the length of the time interval from the current moment, the features of multiple time periods are collected, a feature container is created according to the preset time density parameter, and the corresponding features are stored in the feature container in the order of each time period. The feature container has a multi-dimensional feature sequence.

[0016] Optionally, the determining a plurality of mapping paths between the multidimensional feature sequence and the local feature sequence comprises:

[0017] The features in the multidimensional time series features and the local time series features are traversed in the order of features in the sequence, at least one feature in another queue is assigned to the traversed features, a corresponding relationship is established, and the corresponding relationship generated in the traversal process is recorded as a mapping path between sequences.

[0018] Optionally, the integrating the multidimensional feature sequence and the local feature sequence to the same length according to the feature correspondence in the optimal path, and determining the distance similarity between the multidimensional feature sequence and the multidimensional feature sequence after the integrated length, comprises:

[0019] Merging multiple features corresponding to the same feature in the multidimensional feature sequence to obtain a multidimensional feature sequence with the same length as the local feature sequence;

[0020] Feature vectors are constructed for the local feature sequence and the merged multidimensional feature sequence respectively, and the similarity between the feature vectors is calculated as the distance similarity between the multidimensional feature sequence and the local feature sequence.

[0021] Optionally, merging multiple features corresponding to the same feature in the multidimensional feature sequence includes:

[0022] Multiple features corresponding to the same feature are converted into a single feature according to the conversion rule.

[0023] Optionally, converting multiple features corresponding to the same feature into a single feature according to the conversion rule includes:

[0024] The mean of the multiple features is calculated as a single feature after merging.

[0025] Optionally, determining the feature change attribute information of the user according to the distance similarity includes:

[0026] Determine feature change amplitude information according to the distance similarity;

[0027] The multidimensional feature sequence is compared with feature values ​​of the multidimensional feature sequence, and change direction data is added to the change amplitude information according to the comparison result.

[0028] Optionally, extracting a local feature sequence from the multidimensional feature sequence includes:

[0029] Starting from the last feature of the multi-dimensional feature sequence, a sequence consisting of a plurality of continuous features is extracted in the direction of the first feature as a local feature sequence.

[0030] The embodiment of this specification also provides a service feature processing method based on density integration, including:

[0031] A sequence generation module, which obtains multiple features of the same attribute of the user in the business, generates a multi-dimensional feature sequence according to a preset density parameter, and extracts a local feature sequence in the multi-dimensional feature sequence;

[0032] A mapping module, determining a plurality of mapping paths between the multidimensional feature sequence and the local feature sequence;

[0033] A screening module determines the cumulative distance of each mapping path, and screens the mapping path with the shortest cumulative distance as the optimal path;

[0034] An integration module, integrating the multidimensional feature sequence and the local feature sequence to the same length according to the feature correspondence in the optimal path, and determining the distance similarity between the multidimensional feature sequence and the multidimensional feature sequence after the integration length;

[0035] The feature change attribute module determines the feature change attribute information of the user according to the distance similarity.

[0036] The embodiment of the present specification also provides an electronic device, wherein the electronic device includes:

[0037] processor; and,

[0038] A memory storing a computer executable program, wherein when the executable program is executed, the processor performs any one of the above methods.

[0039] An embodiment of the present specification also provides a computer-readable storage medium, wherein the computer-readable storage medium stores one or more programs, and when the one or more programs are executed by a processor, any of the above methods is implemented.

[0040] The various technical solutions provided in the embodiments of this specification obtain multiple features of the same attribute of the user in the business, generate a multidimensional feature sequence according to the preset density parameter, extract the local feature sequence in the multidimensional feature sequence, determine multiple mapping paths between the multidimensional feature sequence and the local feature sequence, determine the cumulative distance of each mapping path, select the mapping path with the shortest cumulative distance as the optimal path, integrate the multidimensional feature sequence and the local feature sequence to the same length according to the feature correspondence in the optimal path, determine the distance similarity between the multidimensional feature sequence after the integrated length and the multidimensional feature sequence, and determine the user's feature change attribute information according to the distance similarity. The feature change attribute information is determined to provide services quickly, reduce the risk of data query failures, and improve service security. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0042] Figure 1 A schematic diagram of the principle of a service feature processing method based on length integration provided in an embodiment of this specification;

[0043] Figure 2 A matrix schematic diagram provided for an embodiment of this specification;

[0044] Figure 3 A schematic diagram of the structure of a service feature processing device based on length integration provided in an embodiment of this specification;

[0045] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of this specification;

[0046] Figure 5 A schematic diagram of a computer-readable medium provided for an embodiment of this specification. DETAILED DESCRIPTION

[0047] Exemplary embodiments of the present invention will now be described more fully with reference to the accompanying drawings. However, exemplary embodiments can be implemented in a variety of forms, and should not be construed as limiting the present invention to the embodiments set forth herein. On the contrary, providing these exemplary embodiments enables the present invention to be more comprehensive and complete, and is more convenient for fully conveying the inventive concept to those skilled in the art. The same reference numerals in the figures represent the same or similar elements, components or parts, and thus their repeated description will be omitted.

[0048] Under the premise of being consistent with the technical concept of the present invention, the features, structures, characteristics or other details described in a specific embodiment do not exclude that they can be combined in one or more other embodiments in a suitable manner.

[0049] In the description of specific embodiments, the features, structures, characteristics or other details described in the present invention are intended to enable those skilled in the art to fully understand the embodiments. However, it does not exclude that those skilled in the art can practice the technical solutions of the present invention without one or more of the specific features, structures, characteristics or other details.

[0050] The flowcharts shown in the accompanying drawings are only exemplary 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 can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.

[0051] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0052] The term "and / or" or "and / or" includes all combinations of any one or more of the associated listed items.

[0053] Figure 1 A schematic diagram of a service feature processing method based on length integration provided in an embodiment of this specification, the method may include:

[0054] S101: Acquire multiple features of the same attribute of a user in business, generate a multidimensional feature sequence according to a preset density parameter, and extract a local feature sequence in the multidimensional feature sequence.

[0055] In the embodiment of the present specification, the multiple features of the user with the same business attribute may be the number of times the user browses a certain page.

[0056] In the embodiment of the present specification, the multiple features of the same attribute of the user in the business may be the time consumption of the user's behavior.

[0057] Of course, there may be other features, which will not be specifically elaborated or limited here.

[0058] The density parameter may refer to time density. By using the preset density, a feature sequence may be generated according to a time series, for example, how long it takes to output a feature.

[0059] Of course, the density parameter can also be the storage space density, for example, how many storage units are needed to store a feature.

[0060] By setting the density, an adjustable number of features can be obtained within a time period or a storage space, so that the density can be adjusted. By adjusting the density, the length of the sequence can be adjusted, so that two sequences that were originally uncomparable due to unequal lengths can be integrated into two sequences of equal length, so that feature comparison can be performed to calculate the change attribute information.

[0061] Among them, the multidimensional feature sequence is a plurality of features with time sequence.

[0062] In an embodiment of the present specification, the multiple characteristics of the user with the same business attributes may be counting results calculated by the business system based on user behavior data collected in multiple time periods, such as the number, quantity and type of a certain type of application installed by the user within one year, six months or one month.

[0063] Here, within one year, within half a year, and within one month refer to multiple time periods.

[0064] Therefore, multiple time periods can have an inclusive relationship with each other.

[0065] Specifically, in the embodiment of this specification, the step of obtaining multiple features of the same attribute of the user in the business and generating a multi-dimensional feature sequence according to a preset density parameter may include:

[0066] According to the length of the time interval from the current moment, the features of multiple time periods are collected, a feature container is created according to the preset time density parameter, and the corresponding features are stored in the feature container in the order of each time period. The feature container has a multi-dimensional feature sequence.

[0067] The feature container here can be a queue or a storage space for storing data such as a data table.

[0068] In order to take into account the integrity, we take the multi-dimensional feature sequence as one side of the comparison and extract a part of the sequence from it as the other side of the comparison.

[0069] Therefore, in the embodiment of this specification, extracting the local feature sequence from the multidimensional feature sequence may include:

[0070] Starting from the last feature of the multi-dimensional feature sequence, a sequence consisting of a plurality of continuous features is extracted in the direction of the first feature as a local feature sequence.

[0071] In practical application, this can mean that the multidimensional feature sequence has count results (45, 22, 13) within one year, six months, and one month, while the local feature sequence has count results (22, 13) within six months and one month.

[0072] Since the lengths of the local feature sequence and the multidimensional feature sequence are different, they need to be integrated in order to calculate their changes.

[0073] S102: Determine a plurality of mapping paths between the multidimensional feature sequence and the local feature sequence.

[0074] Since the multidimensional feature sequence has multiple features, denoted as p, and the local feature sequence also has multiple features, denoted as q, p>q, there are many feature correspondences between the two sequences. If the correspondence is performed according to the order of the features in the sequence so that the correspondence does not cross, and for each feature in one of the sequences, there is a corresponding feature in the other sequence, then this correspondence can be called a mapping path.

[0075] Since there are multiple mapping paths, we can find them all and then select the optimal path.

[0076] Therefore, in the embodiment of this specification, the determining of multiple mapping paths between the multidimensional feature sequence and the local feature sequence may include:

[0077] The features in the multidimensional time series features and the local time series features are traversed in the order of features in the sequence, at least one feature in another queue is assigned to the traversed features, a corresponding relationship is established, and the corresponding relationship generated in the traversal process is recorded as a mapping path between sequences.

[0078] In specific implementation, constraint rules can be constructed, including: traversing the features in the multidimensional time series features and the local time series features and allocating them in order; for each allocated feature, no further allocation is made; when multiple features are allocated to one feature, these multiple features should be continuous features to achieve non-intersection.

[0079] S103: Determine the cumulative distance of each mapping path, and select the mapping path with the shortest cumulative distance as the optimal path.

[0080] After obtaining the mapping path, the cumulative distance can be calculated according to the feature correspondence in the mapping path.

[0081] Specifically, the absolute value of the difference may be calculated according to the corresponding features, and the calculated multiple absolute values ​​may be summed up as the cumulative distance.

[0082] Of course, it is also possible to calculate the ratio according to the corresponding features, and sum up the calculated multiple ratios as the cumulative distance.

[0083] In this way, the mapping path with the smallest cumulative distance can reflect the best corresponding relationship, so it is taken as the optimal path.

[0084] S104: Integrate the multidimensional feature sequence and the local feature sequence to the same length according to the feature correspondence in the optimal path, and determine the distance similarity between the multidimensional feature sequence and the multidimensional feature sequence after the integration length.

[0085] In the embodiment of the present specification, the multidimensional feature sequence and the local feature sequence are integrated to the same length by adjusting the density of compression corresponding to multiple features of the same feature, or by merging multiple features corresponding to the same feature, so that the multidimensional feature sequence and the local feature sequence have the same length.

[0086] In the embodiment of the present specification, the step of integrating the multidimensional feature sequence and the local feature sequence to the same length according to the feature correspondence in the optimal path, and determining the distance similarity between the multidimensional feature sequence and the multidimensional feature sequence after the integrated length may include:

[0087] Merging multiple features corresponding to the same feature in the multidimensional feature sequence to obtain a multidimensional feature sequence with the same length as the local feature sequence;

[0088] Feature vectors are constructed for the local feature sequence and the merged multidimensional feature sequence respectively, and the similarity between the feature vectors is calculated as the distance similarity between the multidimensional feature sequence and the local feature sequence.

[0089] The similarity between the feature vectors here may be the cosine similarity between the feature vectors.

[0090] Of course, the Euclidean distance similarity may also be calculated, which will not be specifically described or limited here.

[0091] In the embodiment of this specification, merging multiple features corresponding to the same feature in the multidimensional feature sequence may include:

[0092] Multiple features corresponding to the same feature are converted into a single feature according to the conversion rule.

[0093] Of course, you can also directly retain one of the multiple features and eliminate the rest.

[0094] In the embodiment of this specification, converting multiple features corresponding to the same feature into a single feature according to the conversion rule includes:

[0095] The mean of the multiple features is calculated as a single feature after merging.

[0096] Of course, you can also configure weights for each feature and calculate the weighted average as a single feature after merging, which will not be elaborated in detail here.

[0097] S105: Determine the feature change attribute information of the user according to the distance similarity.

[0098] This embodiment obtains multiple features of the same attribute of the user in the business, generates a multidimensional feature sequence according to a preset density parameter, extracts a local feature sequence in the multidimensional feature sequence, determines multiple mapping paths between the multidimensional feature sequence and the local feature sequence, determines the cumulative distance of each mapping path, selects the mapping path with the shortest cumulative distance as the optimal path, integrates the multidimensional feature sequence and the local feature sequence to the same length according to the feature correspondence in the optimal path, determines the distance similarity between the multidimensional feature sequence after the integrated length and the multidimensional feature sequence, and determines the feature change attribute information of the user according to the distance similarity. The feature change attribute information is determined so as to provide services quickly, reduce the risk of data query failure, and improve service security.

[0099] In the embodiment of this specification, determining the feature change attribute information of the user according to the distance similarity includes:

[0100] Determine feature change amplitude information according to the distance similarity;

[0101] The multidimensional feature sequence is compared with feature values ​​of the multidimensional feature sequence, and change direction data is added to the change amplitude information according to the comparison result.

[0102] The direction of change refers to increasing or decreasing, which can be expressed as positive or negative, and the magnitude of the change is a numerical value. For example, the feature change attribute information can be -0.2, which means a decrease of 20%.

[0103] By determining the characteristic change attribute information of the user, the Internet service strategy can be adjusted according to the characteristic change attribute information. For example, for a certain user, more resources can be allocated to the web pages that have been browsed more times, and even the web page information can be pre-stored in the terminal.

[0104] Of course, it is also possible to adjust Internet service strategies based on the changing attribute information of a large number of users. For example, based on the services that are used more frequently by users, the data that the service depends on can be sorted forward, thereby shortening the data call time, so as to quickly provide services, reduce the risk of data query failures, and improve service security.

[0105] In practical applications, when calculating the optimal path, you can also calculate the distance matrix between the points of the two sequences, search for the mapping path from the lower left corner to the upper right corner of the matrix, and calculate the sum of the distance matrix elements in the mapping path. Filter the elements and the smallest mapping path as the optimal path, and perform length integration based on the correspondence between the features in the optimal path.

[0106] In the specific implementation, assume that we have two sequences Q and C, whose lengths are n and m respectively: one sequence is used as the reference template and the other sequence is used as the test template. Each matrix element (i, j) represents the point q i and c j The search for the optimal path can be reduced to finding a path that passes through several grid points in this grid. The grid points passed by the path are the alignment points of the two sequences for calculation:

[0107] Because the two templates have different lengths, there are many ways to match them. We need to find the matching path with the shortest distance. Now assume that the following constraints are met: from one square (to the diagonal, upward, right) to the next square (i, j), if it is horizontal or vertical, the path distance is d(i, j), if it is diagonal, it is 2d(i, j), as follows: g(i k , j k )=g(i,j)=min(g1,g2,g3), where g1=g(i-1,j)+d(i,j), g2=g(i-1,j-1)+2d(i,j), g3=g(i,j-1)+d(i,j).

[0108] Among them, g(i, j) means that both sequences are matched successively from the starting component, and have been assigned to i in Q and j in C, and the matching to this step is the distance between the two sequences, and both are d(i, j) or 2d(i, j) added to the result of the previous match, and then the minimum value is taken.

[0109] Finally, the cumulative distance is: S(i, j) = d(q i ,c j )+min(S1, S2, S3); where S1 is S(i-1, j-1); S1 is S(i, j-1); S1 is S(i-1, j).

[0110] Figure 2 A matrix diagram provided for an embodiment of this specification.

[0111] Among them, sequence 1 is (1, 3, 3, 2, 2, 4, 4), and sequence 2 is (1, 1, 3, 2, 4). By taking the difference, we get Figure 2From the matrix shown, it can be calculated that the cumulative path pointed by the arrow is 0 and the distance is the smallest. Therefore, the row and column values ​​corresponding to the grids on the path can be associated to establish a corresponding relationship, thereby performing length integration.

[0112] Of course, this is just an example provided for ease of understanding.

[0113] Figure 3 A schematic diagram of the structure of a service feature processing device based on length integration provided in an embodiment of this specification, the device may include:

[0114] The sequence generation module 301 obtains multiple features of the same attribute of the user in the business, generates a multi-dimensional feature sequence according to a preset density parameter, and extracts a local feature sequence in the multi-dimensional feature sequence;

[0115] A mapping module 302 determines a plurality of mapping paths between the multidimensional feature sequence and the local feature sequence;

[0116] A screening module 303 determines the cumulative distance of each mapping path, and screens the mapping path with the shortest cumulative distance as the optimal path;

[0117] An integration module 304 integrates the multidimensional feature sequence and the local feature sequence to the same length according to the feature correspondence in the optimal path, and determines the distance similarity between the multidimensional feature sequence and the multidimensional feature sequence after the integration length;

[0118] The feature change attribute module 305 determines the feature change attribute information of the user according to the distance similarity.

[0119] The device obtains multiple features of the same attribute of the user in the business, generates a multidimensional feature sequence according to a preset density parameter, extracts a local feature sequence in the multidimensional feature sequence, determines multiple mapping paths between the multidimensional feature sequence and the local feature sequence, determines the cumulative distance of each mapping path, selects the mapping path with the shortest cumulative distance as the optimal path, integrates the multidimensional feature sequence and the local feature sequence to the same length according to the feature correspondence in the optimal path, determines the distance similarity between the multidimensional feature sequence after the integration length and the multidimensional feature sequence, and determines the feature change attribute information of the user according to the distance similarity. The feature change attribute information is determined so as to provide services quickly, reduce the risk of data query failure, and improve service security.

[0120] Based on the same inventive concept, an embodiment of this specification also provides an electronic device.

[0121] The following describes an electronic device embodiment of the present invention, which can be regarded as a specific physical implementation of the method and device embodiments of the present invention. The details described in the electronic device embodiment of the present invention should be regarded as a supplement to the above method or device embodiments; details not disclosed in the electronic device embodiment of the present invention can be implemented with reference to the above method or device embodiments.

[0122] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this specification. Figure 4 The electronic device 400 according to this embodiment of the present invention is described. Figure 4 The electronic device 400 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0123] like Figure 4 As shown, the electronic device 400 is in the form of a general computing device. The components of the electronic device 400 may include, but are not limited to: at least one processing unit 410, at least one storage unit 420, a bus 430 connecting different system components (including the storage unit 420 and the processing unit 410), a display unit 440, etc.

[0124] The storage unit stores program codes, which can be executed by the processing unit 410, so that the processing unit 410 performs the steps according to various exemplary embodiments of the present invention described in the above processing method section of this specification. For example, the processing unit 410 can perform the following steps: Figure 1 Steps shown.

[0125] The storage unit 420 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 4201 and / or a cache memory unit 4202 , and may further include a read-only memory unit (ROM) 4203 .

[0126] The storage unit 420 may also include a program / utility 4204 having a set (at least one) of program modules 4205, such program modules 4205 including but not limited to: an operating system, one or more application programs, other program modules and program data, each of which or some combination may include the implementation of a network environment.

[0127] Bus 430 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0128] The electronic device 400 may also communicate with one or more external devices 500 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), one or more devices that enable a user to interact with the electronic device 400, and / or any device that enables the electronic device 400 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed through an input / output (I / O) interface 450. Furthermore, the electronic device 400 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter 460. The network adapter 460 may communicate with other modules of the electronic device 400 through the bus 430. It should be understood that although Figure 4 Not shown, other hardware and / or software modules may be used in conjunction with the electronic device 400, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0129] Through the description of the above implementation methods, it is easy for those skilled in the art to understand that the exemplary embodiments described in the present invention can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation method of the present invention can be embodied in the form of a software product, which can be stored in a computer-readable storage medium (which can be a CD-ROM, USB flash drive, mobile hard disk, etc.) or on a network, including a number of instructions to enable a computing device (which can be a personal computer, server, or network device, etc.) to execute the above method according to the present invention. When the computer program is executed by a data processing device, the computer-readable medium can implement the above method of the present invention, that is: Figure 1 The method shown.

[0130] Figure 5 A schematic diagram of a computer-readable medium provided for an embodiment of this specification.

[0131] accomplish Figure 1The computer program of the method shown can be stored on one or more computer readable media. The computer readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0132] The computer readable storage medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The readable storage medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by an instruction execution system, an apparatus, or a device or used in combination with it. The program code contained on the readable storage medium may be transmitted with any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the above.

[0133] Program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0134] In summary, the present invention can be implemented in hardware, or in a software module running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that general data processing devices such as microprocessors or digital signal processors (DSPs) can be used in practice to implement some or all of the functions of some or all of the components in the embodiments of the present invention. The present invention can also be implemented as a device or apparatus program (e.g., a computer program and a computer program product) for executing part or all of the methods described herein. Such a program implementing the present invention can be stored on a computer-readable medium, or can have the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0135] The specific embodiments described above further describe the purpose, technical solutions and beneficial effects of the present invention in detail. It should be understood that the present invention is not inherently related to any specific computer, virtual device or electronic device, and various general devices can also implement the present invention. The above description is only a specific embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

[0136] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0137] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A service feature processing method based on length integration, characterized in that: include: According to the time interval from the current moment, multiple features of multiple time periods of the user with the same attribute in the business are obtained, a feature container is created according to the preset time density, and the corresponding features are stored in the feature container according to the sequence of each time period, the feature container has a multi-dimensional feature sequence, and starting from the last feature of the multi-dimensional feature sequence, a sequence composed of multiple continuous features is extracted in the direction of the first feature as a local feature sequence; wherein the feature container is a storage space for storing data, and the multi-dimensional feature sequence and the local feature sequence both have multiple features; Establishing the corresponding relationship of features, recording the corresponding relationship generated in the traversal process as multiple mapping paths between the multidimensional feature sequence and the local feature sequence, specifically including: traversing the features in the multidimensional feature sequence and the local feature sequence, and allocating them in order; for each allocated feature, no more allocation is performed; when multiple features are allocated to one feature, the allocated multiple features must be continuous features so that the corresponding relationship of the features does not cross; wherein there are multiple feature corresponding relationships between the multidimensional feature sequence and the local feature sequence, and the corresponding relationship is performed in the order of the features in the sequence so that the corresponding relationship does not cross, and for each feature in one of the sequences, there is a corresponding feature in the other sequence, and this corresponding relationship is called a mapping path; Determine the cumulative distance of each mapping path, select the mapping path with the shortest cumulative distance as the optimal path, specifically including: calculate the distance matrix mapped between the multidimensional feature sequence and each point of the local feature sequence, search for the mapping path from the lower left corner to the upper right corner of the distance matrix, and calculate the sum of the distance matrix elements in the mapping path, and select the mapping path with the smallest sum of elements as the optimal path; Integrating the multidimensional feature sequence and the local feature sequence to the same length according to the feature correspondence in the optimal path, and determining the distance similarity between the multidimensional feature sequence and the local feature sequence after the integration length; According to the distance similarity, the feature change amplitude information is determined; the feature values ​​of the multidimensional feature sequence and the local feature sequence are compared, and the change direction data is added to the change amplitude information according to the comparison result to obtain the feature change attribute information.

2. The method according to claim 1, characterized in that The step of integrating the multidimensional feature sequence and the local feature sequence to the same length according to the feature correspondence in the optimal path, and determining the distance similarity between the multidimensional feature sequence and the local feature sequence after the integration length includes: Merging multiple features corresponding to the same feature in the multidimensional feature sequence to obtain a multidimensional feature sequence with the same length as the local feature sequence; Feature vectors are constructed for the local feature sequence and the merged multidimensional feature sequence respectively, and the similarity between the feature vectors is calculated as the distance similarity between the multidimensional feature sequence and the local feature sequence.

3. The method according to claim 2, characterized in that The merging of multiple features corresponding to the same feature in the multidimensional feature sequence includes: Multiple features corresponding to the same feature are converted into a single feature according to the conversion rule.

4. The method according to claim 3, characterized in that The converting of multiple features corresponding to the same feature into a single feature according to the conversion rule includes: The mean of the multiple features is calculated as a single feature after merging.

5. A service feature processing device based on length integration, characterized in that: include: The sequence generation module obtains the features of multiple time periods of the same attribute of the user in the business according to the time interval from the current moment, creates a feature container according to the preset time density parameter, and stores the corresponding features in the feature container according to the order of each time period, wherein the feature container has a multi-dimensional feature sequence, and extracts a sequence consisting of multiple continuous features from the last feature of the multi-dimensional feature sequence to the first feature direction as a local feature sequence; wherein the feature container is a storage space for storing data, and both the multi-dimensional feature sequence and the local feature sequence have multiple features; A mapping module, establishing a corresponding relationship between features, recording the corresponding relationship generated in the traversal process as multiple mapping paths between the multidimensional feature sequence and the local feature sequence, specifically including: traversing the features in the multidimensional feature sequence and the local feature sequence, and allocating them in order; for each allocated feature, no more allocation is performed; when multiple features are allocated to one feature, the allocated multiple features must be continuous features so that the corresponding relationship of the features does not cross; wherein there are multiple feature corresponding relationships between the multidimensional feature sequence and the local feature sequence, and the corresponding relationship is performed in the order of the features in the sequence so that the corresponding relationship does not cross, and for each feature in one of the sequences, there is a corresponding feature in the other sequence, and this corresponding relationship is called a mapping path; A screening module determines the cumulative distance of each mapping path, and screens the mapping path with the shortest cumulative distance as the optimal path, specifically comprising: calculating the distance matrix mapped between each point of the multidimensional feature sequence and the local feature sequence, searching for the mapping path from the lower left corner to the upper right corner of the distance matrix, and calculating the sum of the distance matrix elements in the mapping path, and screening the mapping path with the smallest sum of elements as the optimal path; An integration module, integrating the multidimensional feature sequence and the local feature sequence to the same length according to the feature correspondence in the optimal path, and determining the distance similarity between the multidimensional feature sequence and the local feature sequence after the integration length; The feature change attribute module determines the feature change amplitude information according to the distance similarity; compares the feature values ​​of the multidimensional feature sequence and the local feature sequence, and adds change direction data to the change amplitude information according to the comparison result to obtain change attribute information.

6. An electronic device, wherein: The electronic device includes: processor; and, A memory storing a computer executable program which, when executed, causes the processor to perform a method according to any one of claims 1 to 4.

7. A computer-readable storage medium, wherein: The computer-readable storage medium stores one or more programs, and when the one or more programs are executed by a processor, the method of any one of claims 1 to 4 is implemented.

Images