Text character string sorting method and device, medium and electronic equipment

Abstract

The invention provides a text character string sorting method and device, a medium and electronic equipment, and relates to the field of data processing.The text character string sorting method comprises the steps that user features of a target user are obtained to obtain an initial feature vector T; determining a target historical feature vector in the plurality of historical feature vectors according to the T and necessary user features in the user features of the missing feature values included in the T; according to the target historical feature vector, supplementing user features with missing feature values in T to obtain a target feature vector T '; and inputting the T'into a sorting model to sort the a to-be-sorted character strings corresponding to the target user. According to the method, the target historical feature vector is determined through the necessary user features of the missing feature values, user feature supplementation is performed on the initial feature vector, the obtained target feature vector is closer to each user feature of the target user, and thus the obtained sorting result of the to-be-sorted character string is more accurate.

Description

Background Art

[0002] In today's era of highly developed digital information, the application scenarios of sorting various text strings according to user characteristics are becoming more and more common. For example, in e-commerce platforms, merchants often need to sort text strings such as product descriptions and recommendation copy according to many user characteristics such as user purchase history, browsing preferences, geographic location and age, so as to accurately push product information that meets their interests and needs to users; for example, in content information platforms, operators will sort text strings such as article titles and content summaries according to user reading habits, subscription topics, occupations and other characteristics, so as to achieve personalized content recommendations and improve user experience and user stickiness of the platform.

[0003] In the process of implementing text string sorting based on user features, it is usually necessary to obtain complete and accurate user feature-related data as the basis for sorting. However, in actual operation, there is a prominent problem that needs to be solved urgently. That is, there are often missing user feature data.

[0004] Missing user feature data may be caused by a variety of reasons. When user feature data is missing, it will have a serious adverse impact on the sorting results of the text strings, directly leading to inaccurate sorting results. Summary of the invention

[0005] In response to the above technical problems, the present application provides a text string sorting method, device, medium and electronic device, which at least partially solve the problems existing in the prior art.

[0006] In a first aspect of the present application, a method for sorting text strings is provided, the method comprising:

[0007] S100, obtaining the user characteristics of the target user to obtain an initial characteristic vector T = (T1, T2, ..., T i ,…,T n ), i = 1, 2, ..., n, where n is the number of user features of the target user; T i is the i-th user feature of the target user; the target user has a corresponding string to be sorted; each string to be sorted has a corresponding target object; each string to be sorted has at least one corresponding necessary user feature; each necessary user feature belongs to T; there is at least one user feature with a missing feature value in T.

[0008] S200, determining a target historical feature vector from a number of historical feature vectors based on necessary user features among user features with missing feature values ​​included in T and T; wherein each historical feature vector does not contain user features with missing feature values; and each historical feature vector contains the same feature dimension as T.

[0009] S300 , supplementing the user features with missing feature values ​​in T according to the target historical feature vector to obtain a target feature vector T′.

[0010] S400: Input T' into a sorting model to sort the a character strings to be sorted corresponding to the target user.

[0011] In a second aspect of the present application, a text string sorting device is provided, the device comprising:

[0012] The initial vector acquisition unit is used to acquire the user characteristics of the target user to obtain an initial characteristic vector T = (T1, T2, ..., T i , …, T n ), i = 1, 2, ..., n, where n is the number of user features of the target user; T i is the i-th user feature of the target user; the target user has a corresponding string to be sorted; each string to be sorted has a corresponding target object; each string to be sorted has at least one corresponding necessary user feature; each necessary user feature belongs to T; there is at least one user feature with a missing feature value in T;

[0013] A target vector determination unit, configured to determine a target historical feature vector from a plurality of historical feature vectors according to necessary user features among user features with missing feature values ​​included in T and T; wherein each historical feature vector does not contain user features with missing feature values; and each historical feature vector contains the same feature dimension as T;

[0014] A supplementing unit, used to supplement the user features with missing feature values ​​in T according to the target historical feature vector, so as to obtain a target feature vector T';

[0015] The sorting unit is used to input T' into the sorting model to sort the a strings to be sorted corresponding to the target user.

[0016] In a third aspect of the present application, a non-transitory computer-readable storage medium is provided, in which at least one instruction or at least one program is stored, and the at least one instruction or at least one program is loaded and executed by a processor to implement the aforementioned text string sorting method.

[0017] In a fourth aspect of the present application, an electronic device is provided, comprising a processor and the above-mentioned non-transitory computer-readable storage medium.

[0018] This application has at least the following beneficial effects:

[0019] The text string sorting method provided in the present application first obtains an initial feature vector according to the user features of the target user, and due to various reasons, the initial feature vector contains at least one user feature with missing feature values, that is, the user has some missing user features, and then, the user feature values ​​with missing feature values ​​may also include some necessary user features. According to the initial feature vector and the necessary user features, the target historical vector is determined in several historical feature vectors. Here, the role of the target historical feature vector is to supplement the user vector with the actual feature value in the initial feature vector. After supplementation, the updated target feature vector is obtained. Finally, the target feature vector is input into the sorting model to sort the a strings to be sorted corresponding to the target user. In the present application, when determining the target historical vector, the necessary user features in the user features with missing feature values ​​included in T are also referred to. The necessary user features are more important user features. The target historical feature vector obtained thereby has the highest matching degree with the initial feature vector, that is, the target historical feature vector is most similar to the initial feature vector. Therefore, the user features with missing feature values ​​in T are supplemented according to the target historical feature vector, and the target feature vector obtained is more accurate. Then, the sorting result obtained is more accurate. The present application determines the target historical feature vector through the necessary user features of the missing feature values ​​to supplement the user features of the initial feature vector, and the obtained target feature vector is closer to each user feature of the target user, so that the sorting result of the string to be sorted is more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in 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 only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 A flow chart of a method for sorting text strings provided in an embodiment of the present application;

[0022] Figure 2 A structural block diagram of a text string sorting device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0023] 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 only 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 those skilled in the art without creative work are within the scope of protection of this application.

[0024] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0025] It should be noted that various aspects of the embodiments within the scope of the appended claims are described below. It should be apparent that the aspects described herein may be embodied in a wide variety of forms, and any specific structure and / or function described herein is merely illustrative. Based on the present application, it should be understood by those skilled in the art that an aspect described herein may be implemented independently of any other aspect, and two or more of these aspects may be combined in various ways. For example, any number of aspects described herein may be used to implement the device and / or practice the method. In addition, other structures and / or functionalities other than one or more of the aspects described herein may be used to implement this device and / or practice this method.

[0026] Please refer to Figure 1 As shown, an embodiment of the present application provides a method for sorting text strings, the method comprising:

[0027] Step S100, obtaining the user characteristics of the target user to obtain an initial characteristic vector T = (T1, T2, ..., T i , …, T n ), i = 1, 2, ..., n, where n is the number of user features of the target user; T i is the i-th user feature of the target user; the target user has a corresponding string to be sorted; each string to be sorted has a corresponding target object; each string to be sorted has at least one corresponding necessary user feature; each necessary user feature belongs to T; there is at least one user feature with a missing feature value in T.

[0028] Specifically, the a strings to be sorted corresponding to the target user are sorted according to the user features and the characteristics of the target object corresponding to each string to be sorted. The higher the ranking, the higher the compatibility of the string to be sorted with the target user. The initial feature vector currently obtained has a user feature with at least one missing feature value. Due to the missing user feature, the initial feature vector is incomplete and cannot fully represent the user's features. The sorting result of the string to be sorted is less accurate than the completed initial feature vector. Therefore, the current initial feature vector needs to be completed.

[0029] Step S200, determining a target historical feature vector from a number of historical feature vectors based on necessary user features among user features with missing feature values ​​included in T and T; wherein each historical feature vector does not contain user features with missing feature values; and each historical feature vector contains the same feature dimension as T.

[0030] Specifically, the target historical feature vector is determined from among several historical feature vectors according to the necessary user features in the user features with missing feature values ​​included in T and T. In this embodiment, when determining the target historical vector, the necessary user features in the user features with missing feature values ​​included in T are also referred to, and the necessary user features are more important user features, so that the target historical feature vector obtained has the highest matching degree with the initial feature vector, that is, the target historical feature vector is most similar to the initial feature vector.

[0031] Step S300: supplement the user features with missing feature values ​​in T according to the target historical feature vector to obtain a target feature vector T'.

[0032] Specifically, according to the target historical feature vector, the user features with missing feature values ​​in T are supplemented. Here, the user features with missing feature values ​​in T are supplemented according to the historical user features in the target historical feature vector corresponding to the missing feature values ​​in T, so that the initial feature vector becomes complete. There is no missing feature value.

[0033] Step S400: input T' into a sorting model to sort a character strings to be sorted corresponding to the target user.

[0034] Specifically, the supplemented complete target feature vector is input into the sorting model to sort the a character strings to be sorted corresponding to the target user.

[0035] In the present application, when determining the target historical vector, the necessary user features in the user features of the missing feature values ​​included in T are also referenced. The necessary user features are more important user features, and the target historical feature vector thus obtained has the highest matching degree with the initial feature vector, that is, the target historical feature vector and the initial feature vector are most similar. Therefore, the user features of the missing feature values ​​in T are supplemented according to the target historical feature vector, and the obtained target feature vector is more accurate. Furthermore, the obtained sorting result is more accurate. The present application determines the target historical feature vector through the necessary user features of the missing feature values ​​to supplement the initial feature vector with user features, and the obtained target feature vector is closer to each user feature of the target user, and the obtained sorting result for the string to be sorted is more accurate.

[0036] In some embodiments, the above text string sorting method can be implemented by the following code:

[0037]

[0038]

[0039]

[0040] In an exemplary embodiment of the present application, step S200 includes:

[0041] S210, according to T, obtain the missing necessary feature vector Q = (Q1, Q2, ..., Q j , …, Q m );j=1,2,…,m;where m is the number of missing necessary features; Q j is the i-th missing necessary feature; the missing necessary feature is the necessary user feature with missing feature value in T; each missing necessary feature has at least one associated necessary user feature; each associated necessary user feature belongs to T.

[0042] Specifically, the missing necessary feature vector includes each necessary user feature in the user features with missing feature values ​​in T. Each missing necessary feature has at least one associated necessary user feature, which is a necessary user feature that affects the missing necessary feature. A necessary user feature is a feature that is more important than a user feature.

[0043] It should be noted that each necessary associated user feature belongs to T. T contains n-dimensional user features.

[0044] S220, according to each associated necessary user feature corresponding to each missing necessary feature, obtain an associated necessary feature vector B=(B1, B2, ..., B x , …, B y);x=1,2,…,y;where y is the number of all the necessary associated user features after deduplication;B x is the xth associated necessary user feature after deduplication; each associated necessary user feature after deduplication has a corresponding associated number; the associated number is the number of associated missing necessary features.

[0045] Specifically, all associated necessary user features corresponding to all missing necessary features are deduplicated to obtain an associated necessary feature vector B.

[0046] S230, according to T, obtain the non-missing feature vector F = (F1, F2, ..., F c , …, F d );c=1,2,…,d;wherein d is the number of user features with no missing feature values ​​in T;F c is the user feature with the cth non-missing feature value in T.

[0047] S240, according to a number of historical non-missing feature vectors and F, obtain a matching degree list P = (P1, P2, ..., P g ,…,P h );P g is F and the g-th historical non-missing feature vector L g The historical non-missing feature vector is obtained by deleting the user features in the corresponding historical feature vector that are the same as the user features of each missing feature value in T.

[0048] Specifically, P g Meet the following conditions:

[0049]

[0050] Among them, x c F c The corresponding weight; L g , c For L g Medium and F c The corresponding user characteristics.

[0051] x c Follow these steps to determine:

[0052] x c =1 / (1+MAX(GX)-GX c );

[0053] Where GX is a list of non-missing feature vector association numbers; GX = (GX1, GX2, ..., GX c , …, GX d ); GX c F cThe corresponding correlation number; if F c If the GX is the same as any of the necessary user characteristics, c is the number of missing necessary features associated with the corresponding associated necessary user features; if F c The necessary user characteristics for each association are different, then GX c is 0.

[0054] Here, several historical feature vectors are obtained, each of which does not contain user features with missing feature values; and the feature dimensions contained in each historical feature vector are the same as T. According to each user feature dimension corresponding to F in each historical feature vector, the corresponding historical non-missing feature vector is obtained. Then, the target historical feature vector is determined according to the matching degree between each historical non-missing feature vector and the non-missing feature vector.

[0055] It should be noted that, in this embodiment, when obtaining the matching degree between each historical non-missing feature vector and the non-missing feature vector, an optimized Euclidean distance formula is used, wherein a corresponding weight is assigned to each distance because some of the user features of the non-missing feature values ​​contained in F are the associated necessary technical features corresponding to the necessary user features of the missing feature values, and the rest are conventional user features; then when obtaining the matching degree between F and each historical non-missing feature vector, a corresponding weight is assigned to each dimensional difference, so that the corresponding weight of the associated necessary technical features corresponding to the necessary user features of the missing feature values ​​when making the dimensional difference, that is, the importance is higher, and the corresponding weight of the conventional user features when making the dimensional difference, that is, the importance is lower. In summary, the associated necessary technical features corresponding to the necessary user features of the missing feature values ​​have a large impact on the matching degree, and the conventional user features have a small impact on the matching degree. The obtained matching degree is more in line with the requirements of sorting the strings to be sorted with necessary user features in this embodiment, and the obtained sorting result is more accurate.

[0056] Furthermore, for the weights corresponding to the associated necessary technical features corresponding to the necessary user features of the missing feature values, the more the number of associated missing necessary features is, the greater the relevance to the necessary user features of the missing feature values ​​is, and the greater the corresponding weight is; conversely, the fewer the number of associated missing necessary features is, the smaller the relevance to the necessary user features of the missing feature values ​​is, and the smaller the corresponding weight is; and for conventional user features, the corresponding weight is even smaller. In this way, the associated necessary technical features corresponding to the necessary user features of the missing feature values ​​have a great influence on the matching degree, and the more the number of associated missing necessary features is, the greater the corresponding weight is, and the influence of conventional user features on the matching degree is small, which is less than the influence of the associated necessary technical features corresponding to the necessary user features of each missing feature value on the matching degree.

[0057] S250, if Pg =MAX(P), then P g Determined as the target historical feature vector.

[0058] The historical feature vector with the largest matching degree is determined as the target historical feature vector, and the target historical feature vector is the one that is closest to the initial feature vector among several historical feature vectors.

[0059] In an exemplary embodiment of the present application, step S300 includes:

[0060] S310, if P g =MAX(P), and P g ≥preset matching degree threshold, then according to the target historical feature vector, the user feature of each missing feature value in T is supplemented to obtain the target feature vector T'.

[0061] In this embodiment, if the target historical feature vector has a large match with F (equal to or greater than the preset match threshold), it means that the target historical feature vector has a high degree of fit and similarity with the initial feature vector. At this time, the user features of each missing feature value in T are supplemented.

[0062] In an exemplary embodiment of the present application, step S300 includes:

[0063] S320, if P g =MAX(P), and P g <preset matching degree threshold, then according to the target historical feature vector, the necessary user features of the missing feature values ​​in T are supplemented to obtain the target feature vector T'.

[0064] In this embodiment, if the target historical feature vector does not match F very well, it means that the target historical feature vector does not match the initial feature vector very well. In this case, only the necessary user features with missing feature values ​​in T are supplemented. For user features with missing feature values, the feature value can be set to null.

[0065] In this embodiment, when the target historical feature vector does not match F very well, only necessary user features are supplemented, while other conventional user features are not supplemented. This is because necessary user features are necessary features for sorting text strings, and other user features with real feature values ​​have little effect on the sorting of text strings. However, since the target historical feature vector does not match F very well, if all of them are supplemented and replaced, it may have a negative impact on the sorting results, thereby reducing the objectivity and adaptability of the sorting results.

[0066] The following two specific scenarios illustrate the text string sorting method of this application:

[0067] In one embodiment, the user characteristics of the target user may be physical sign data such as blood type, blood oxygen saturation, blood pressure, heart rate, etc., and the character string to be sorted may be a character string composed of drug information such as the characteristics corresponding to the biological agent (such as the name of the biological agent), and the target object corresponding to the character string to be sorted may be the biological agent. At this time, after sorting the character string to be sorted, it can be understood as the name sorting of each biological agent. The higher the ranking, the more it matches the target user, so as to achieve the recommendation of biological agents for the target user.

[0068] In another embodiment, the user characteristics of the target user may be preference information such as video length preference, video type preference, etc., and the string to be sorted may be a jump link corresponding to the video, and its corresponding target object may be a video. At this time, the string to be sorted is sorted to achieve the preferred video recommendation for the target user.

[0069] Please refer to Figure 2 As shown, an embodiment of the present application provides a text string sorting device 100, the device comprising:

[0070] The initial vector acquisition unit 110 is used to acquire the user characteristics of the target user to obtain an initial characteristic vector T=(T1, T2, ..., T i ,…,T n ), i = 1, 2, ..., n, where n is the number of user features of the target user; T i is the i-th user feature of the target user; the target user has a corresponding string to be sorted; each string to be sorted has a corresponding target object; each string to be sorted has at least one corresponding necessary user feature; each necessary user feature belongs to T; there is at least one user feature with a missing feature value in T.

[0071] The target vector determination unit 120 is used to determine a target historical feature vector from a plurality of historical feature vectors according to necessary user features among user features with missing feature values ​​included in T and T; wherein each historical feature vector does not contain user features with missing feature values; and each historical feature vector contains the same feature dimension as T.

[0072] The supplementing unit 130 is used to supplement the user features with missing feature values ​​in T according to the target historical feature vector to obtain a target feature vector T'.

[0073] The sorting unit 140 is used to input T' into the sorting model to sort the a character strings to be sorted corresponding to the target user.

[0074] An embodiment of the present application further provides a computer program product, which includes program code. When the program product is run on an electronic device, the program code is used to enable the electronic device to execute the steps of the method according to various exemplary embodiments of the present application described above in this specification.

[0075] In addition, although the steps of the method in the present application are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc.

[0076] Through the description of the above implementation methods, it is easy for those skilled in the art to understand that the example implementation methods described here can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the implementation methods of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the implementation methods of the present application.

[0077] In an exemplary embodiment of the present application, an electronic device capable of implementing the above method is also provided.

[0078] Those skilled in the art will appreciate that various aspects of the present application may be implemented as a system, method or program product. Therefore, various aspects of the present application may be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which may be collectively referred to as "circuit", "module" or "system" herein.

[0079] The electronic device according to this embodiment of the present application is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0080] The electronic device is presented in the form of a general-purpose computing device. The components of the electronic device may include, but are not limited to: the at least one processor mentioned above, the at least one storage device mentioned above, and a bus connecting different system components (including storage devices and processors).

[0081] The storage stores program codes, which can be executed by the processor, so that the processor executes the steps described in the above “Exemplary Method” section of this specification according to various exemplary embodiments of the present application.

[0082] The memory may include readable media in the form of volatile memory, such as random access memory (RAM) and / or cache memory, and may further include read only memory (ROM).

[0083] The storage may also include a program / utility having a set (at least one) of program modules, such program modules 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.

[0084] The bus may represent one or more of several types of bus structures including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures.

[0085] The electronic device can also communicate with one or more external devices (such as keyboards, pointing devices, Bluetooth devices, etc.), and can also communicate with one or more devices that enable users to interact with the electronic device, and / or communicate with any device (such as routers, modems, etc.) that enables the electronic device to communicate with one or more other computing devices. This communication can be carried out through an input / output (I / O) interface. In addition, the electronic device can also communicate with one or more networks (such as local area networks (LANs), wide area networks (WANs) and / or public networks, such as the Internet) through a network adapter. As shown in the figure, the network adapter communicates with other modules of the electronic device through a bus. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with the electronic device, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0086] Through the description of the above implementation methods, it is easy for those skilled in the art to understand that the example implementation methods described here can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the implementation methods of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation methods of the present application.

[0087] In an exemplary embodiment of the present application, a computer-readable storage medium is also provided, on which a program product capable of implementing the above method of the present specification is stored. In some possible implementations, various aspects of the present application can also be implemented in the form of a program product, which includes a program code. When the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps according to various exemplary implementations of the present application described in the above "Exemplary Method" section of the present specification.

[0088] The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of readable storage media (a non-exhaustive list) 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.

[0089] Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, in which readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Readable signal media may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0090] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0091] Program code for performing the operations of the present application 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 the case of 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., via the Internet using an Internet service provider).

[0092] In addition, the above-mentioned figures are only schematic illustrations of the processes included in the method according to the exemplary embodiments of the present application, and are not intended to be limiting. It is easy to understand that the processes shown in the above-mentioned figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0093] It should be noted that, although several modules or units of the equipment for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into being embodied by multiple modules or units.

[0094] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application 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 sorting text strings, characterized in that: The method comprises: S100, obtaining the user characteristics of the target user to obtain an initial characteristic vector T = (T1, T2, ..., T i ,…,T n ), i = 1, 2, ..., n, where n is the number of user features of the target user; T i is the i-th user feature of the target user; the target user has a corresponding string to be sorted; each string to be sorted has a corresponding target object; each string to be sorted has at least one corresponding necessary user feature; each necessary user feature belongs to T; there is at least one user feature with a missing feature value in T; S200, determining a target historical feature vector from a plurality of historical feature vectors according to necessary user features among user features with missing feature values ​​included in T and T; wherein each historical feature vector does not contain user features with missing feature values; and each historical feature vector contains the same feature dimension as T; S300, supplementing the user features with missing feature values ​​in T according to the target historical feature vector to obtain a target feature vector T'; S400: Input T' into a sorting model to sort the a character strings to be sorted corresponding to the target user.

2. The text string sorting method according to claim 1, characterized in that: Step S200 includes: S210, according to T, obtain the missing necessary feature vector Q = (Q1, Q2, ..., Q j , …, Q m );j=1,2,…,m;where m is the number of missing necessary features; Q j is the i-th missing necessary feature; the missing necessary feature is the necessary user feature with missing feature value in T; each missing necessary feature has at least one associated necessary user feature; each associated necessary user feature belongs to T; S220, according to each associated necessary user feature corresponding to each missing necessary feature, obtain an associated necessary feature vector B=(B1, B2, ..., B x , …, B y ); x = 1, 2, ..., y; where y is the number of all associated necessary user features after deduplication; B x is the xth necessary associated user feature after deduplication; each necessary associated user feature after deduplication has a corresponding associated number; the associated number is the number of missing necessary features of the association; S230, according to T, obtain the non-missing feature vector F = (F1, F2, ..., F c , …, F d );c=1,2,…,d;wherein d is the number of user features with no missing feature values ​​in T;F c is the user feature with the cth non-missing feature value in T; S240, according to a number of historical non-missing feature vectors and F, obtain a matching degree list P = (P1, P2, ..., P g ,…,P h );P g is F and the g-th historical non-missing feature vector L g The historical non-missing feature vector is obtained by deleting the user features in the corresponding historical feature vector that are the same as the user features of each missing feature value in T; S250, if P g =MAX(P), then P g Determined as the target historical feature vector.

3. The text string sorting method according to claim 2, characterized in that: P g Meet the following conditions: Among them, x c F c The corresponding weight; L g，c For L g Medium and F c The corresponding user characteristics.

4. The text string sorting method according to claim 3, characterized in that: x c Follow these steps to determine: x c =1 / (1+MAX(GX)-GX c ); Where GX is a list of non-missing feature vector association numbers; GX = (GX1, GX2, ..., GX c , …, GX d ); GX c F c The corresponding correlation number; if F c If the GX is the same as any of the necessary user characteristics, c is the number of missing necessary features associated with the corresponding associated necessary user features; if F c The necessary user characteristics for each association are different, then GX c is 0.

5. The text string sorting method according to claim 4, characterized in that: Step S300 includes: S310, if P g =MAX(P), and P g ≥preset matching degree threshold, then according to the target historical feature vector, the user feature of each missing feature value in T is supplemented to obtain the target feature vector T'.

6. The text string sorting method according to claim 4, characterized in that: Step S300 includes: S320, if P g =MAX(P), and P g <preset matching degree threshold, then according to the target historical feature vector, the necessary user features of the missing feature values ​​in T are supplemented to obtain the target feature vector T'.

7. A text string sorting device, characterized in that: The device comprises: The initial vector acquisition unit is used to acquire the user characteristics of the target user to obtain an initial characteristic vector T = (T1, T2, ..., T i ,…,T n ), i = 1, 2, ..., n, where n is the number of user features of the target user; T i is the i-th user feature of the target user; the target user has a corresponding string to be sorted; each string to be sorted has a corresponding target object; each string to be sorted has at least one corresponding necessary user feature; each necessary user feature belongs to T; there is at least one user feature with a missing feature value in T; A target vector determination unit, configured to determine a target historical feature vector from a plurality of historical feature vectors according to necessary user features among user features with missing feature values ​​included in T and T; wherein each historical feature vector does not contain user features with missing feature values; and each historical feature vector contains the same feature dimension as T; A supplementing unit, used to supplement the user features with missing feature values ​​in T according to the target historical feature vector, so as to obtain a target feature vector T'; The sorting unit is used to input T' into the sorting model to sort the a strings to be sorted corresponding to the target user.

8. A non-transitory computer-readable storage medium, characterized in that: The storage medium stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the method as claimed in any one of claims 1 to 6.

9. An electronic device, characterized in that: The invention comprises a processor and the non-transitory computer-readable storage medium as claimed in claim 8.

Images