Text label determination method, apparatus, medium, and electronic device

Abstract

The application provides a text label determination method and device, a medium and an electronic equipment, and relates to the field of data processing. The method comprises the following steps: obtaining non-structured text information input by a user and a first candidate label corresponding to the non-structured text information; obtaining a second candidate label according to the non-structured text information, preset structured text information and a label determination model; if the first candidate label is different from the second candidate label, obtaining a non-structured weight of the non-structured text information and a structured weight of the preset structured text information; and obtaining a target label of the non-structured text information input by the user according to the non-structured text information, the preset structured text information, the non-structured weight, the structured weight and the label determination model. The application makes the target label obtained finally more suitable for the non-structured text input by the user.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of data processing, and in particular to a text label determination method and device, a medium and an electronic device. BACKGROUND

[0002] In today's era of digital information explosion, a large amount of unstructured text information emerges. Unstructured text information, such as user comments on social media, email content, and online forum posts, is difficult to analyze efficiently using traditional structured data processing methods because it does not follow a specific data format.

[0003] Currently, when classifying unstructured text information, there is a significant problem, that is, a high dependence on human subjective judgment of the category of the unstructured text information input by the human. In the judgment process, the human is easily disturbed by various factors. On the one hand, the human's knowledge reserve has limitations, and when facing some professional domain or obscure theme text, the human may make a wrong judgment of the category due to lack of relevant knowledge. On the other hand, the human's subjective emotion and cognitive bias also affect the judgment result. If an individual has inherent preferences or negative views on a certain topic, the classification label of the related text may deviate from the objective standard when determining the classification label. SUMMARY

[0004] To solve the above technical problems, the present application provides a text label determination method, device, medium and electronic device, which at least partially solves the problems in the prior art.

[0005] In a first aspect of the present application, a text label determination method is provided, the method comprising:

[0006] S100, obtaining unstructured text information input by a user and a first candidate label corresponding to the unstructured text information; wherein the first candidate label is one of a plurality of preset candidate labels;

[0007] S200, obtaining a second candidate label according to the unstructured text information, a preset structured text information, and a label determination model; wherein the second candidate label is one of a plurality of preset candidate labels; and the preset structured text information is used to describe attribute information of the user;

[0008] S300, if the first candidate label is different from the second candidate label, obtaining a non-structured weight of the unstructured text information and a structured weight of the preset structured text information;

[0009] S400, obtaining a target label of the unstructured text information input by the user according to the unstructured text information, the preset structured text information, the non-structured weight, the structured weight, and the label determination model.

[0010] In a second aspect of the present application, a text label determination device is provided, the device comprising:

[0011] The first label obtaining unit is configured to obtain non-structured text information input by a user and first candidate labels corresponding to the non-structured text information, wherein the first candidate labels are one of a plurality of preset candidate labels;

[0012] The second label obtaining unit is configured to obtain second candidate labels according to the non-structured text information, preset structured text information and a label determination model, wherein the second candidate labels are one of a plurality of preset candidate labels, and the preset structured text information is used to describe attribute information of the user;

[0013] The weight determining unit is configured to obtain a non-structured weight of the non-structured text information and a structured weight of the preset structured text information if the first candidate labels are different from the second candidate labels.

[0014] The label determining unit is configured to obtain target labels of the non-structured text information input by the user according to the non-structured text information, the preset structured text information, the non-structured weight, the structured weight and the label determination model.

[0015] In a third aspect of the present application, a non-transitory computer readable storage medium is provided, and the storage medium stores at least one instruction or at least one program. The at least one instruction or at least one program is loaded and executed by a processor to implement the above-mentioned text label determination method.

[0016] In a fourth aspect of the present application, an electronic device is provided, which comprises a processor and the above-mentioned non-transitory computer readable storage medium.

[0017] The present application has at least the following beneficial effects:

[0018] The text label determination method provided in the application first acquires non-structured text information input by a user and a first candidate label corresponding to the non-structured text information, that is, the user first determines the label of the input non-structured text information by himself / herself; then, according to the non-structured text information, preset structured text information and a label determination model, a second candidate label is obtained. Here, the second candidate label is determined according to the label determination model, and here, when the second candidate label is obtained by using the label determination model, the preset structured text information is also used to assist in determination, wherein the preset structured text information is used to describe attribute information of the user, and can provide more abundant information for the model when the second candidate label is determined. If the first candidate label is different from the second candidate label, it is possible that the first candidate label input by the user is inaccurate, or it is possible that the second candidate label obtained by the label determination model is inaccurate, at this time, a non-structured weight of the non-structured text information and a structured weight of the preset structured text information are acquired, that is, the input vector of the label determination model is adjusted. Then, the final target label is obtained by using the adjusted input vector. The inaccuracy of the label caused by the subjectivity of pure manual input is avoided. Whether the input vector of the label determination model needs to be adjusted is determined according to the similarity between the manually input label and the label obtained by the model for the first time, so that the target label obtained finally is more consistent with the non-structured text input by the user, and is not simply dependent on the manual input or the output of the model. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0020] Figure 1 The text label determination method flowchart provided in the embodiment of the present application;

[0021] Figure 2 The structural block diagram of the text label determination device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0022] The technical solutions in the embodiments of the present application will be described clearly and completely in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0023] It should be noted that the terms "first", "second", and the like in the description and in the claims of the present application and the above-described accompanying drawings are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product, or server including a series of steps or units does not have to be limited to only those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products, or devices.

[0024] It should be noted that various aspects of embodiments within the scope of the appended claims are described below. It should be apparent that the aspects described herein can be embodied in a wide variety of forms and that any specific structure and / or function described herein is merely illustrative. Based on the teachings herein one skilled in the art should appreciate that an aspect described herein can be implemented independently of any other aspects and that an aspect described herein can be implemented both as any number of software and / or hardware structures and as any number of processes and / or operations.

[0025] Reference is made to Figure 1 As shown in the drawings, the embodiments of the present application provide a text label determination method, the method comprising:

[0026] Step S100, obtaining non-structured text information input by a user and a first candidate label corresponding to the non-structured text information; wherein the first candidate label is one of a plurality of preset candidate labels.

[0027] Specifically, the non-structured text information refers to text data that has no fixed format or organizational form and cannot be directly represented and stored by traditional database table structure or fixed pattern. In this embodiment, the non-structured text information is input by the user, and here, the non-structured text information can be evaluation information, message information, feedback information, etc., and the first candidate label corresponding to the non-structured text information is a label selected by the user from the plurality of preset candidate labels. It should be noted that the purpose of the text label determination method in the present application for determining a suitable label for the non-structured text information input by the user is to enable the non-structured text information input by the user to be handled in a timely and proper manner. As an example: if the non-structured text information input by the user is a certain feedback information, the label corresponding thereto can be a processing object determined for the feedback information to process the feedback information.

[0028] In step S200, a second candidate label is obtained according to the unstructured text information, the preset structured text information, and the label determination model; the second candidate label is one of a plurality of preset candidate labels; and the preset structured text information is used to describe attribute information of the user.

[0029] Specifically, the preset structured text information can be some personal information of the user or other user information related to the unstructured text information. As an example, if the current unstructured text information is a message left by the user on a message system of a hospital, the preset structured text information is medical record information of the user, the first candidate label is a label selected by the user from a plurality of preset candidate labels according to the message left by the user, the preset candidate labels can be medical service labels, medical process labels, etc., and the second candidate label is any one of the plurality of preset candidate labels output by the label determination model. Or, as an example, if the current unstructured text information is an introduction to a software published by the user, the first candidate label is a selected software category; the software category can be used to classify and manage the software. The preset structured text information is parameter information corresponding to the software, etc. The preset candidate labels can be instant messaging software or office software, etc.

[0030] In step S300, if the first candidate label is different from the second candidate label, a non-structure weight of the unstructured text information and a structure weight of the preset structured text information are obtained.

[0031] Specifically, if the first candidate label is different from the second candidate label, it is indicated that the first candidate label input by the user can be inaccurate, or the second candidate label obtained by the label determination model can be inaccurate. In this case, the non-structure weight of the unstructured text information and the structure weight of the preset structured text information are obtained. The weights are used to adjust the influence of the unstructured text information and the preset structured text information on the output second candidate label.

[0032] In step S400, a target label of the unstructured text information input by the user is obtained according to the unstructured text information, the preset structured text information, the non-structure weight, the structure weight, and the label determination model.

[0033] Specifically, after the corresponding weights are obtained, the weight of the unstructured text information in the vector input to the label determination model is adjusted based on the non-structure weight, and the weight of the preset structured text information in the vector input to the label determination model is adjusted based on the structure weight, so that the obtained target label is closer to the unstructured text information input by the user.

[0034] The text label determination method provided in the application first acquires non-structured text information input by a user and a first candidate label corresponding to the non-structured text information, that is, the user first determines the label of the input non-structured text information by himself / herself; then, according to the non-structured text information, preset structured text information and a label determination model, a second candidate label is obtained. Here, the second candidate label is determined according to the label determination model, and here, when the label determination model is used to obtain the second candidate label, the preset structured text information is also used to assist in determination, wherein the preset structured text information is used to describe the attribute information of the user, and can provide more abundant information for the model when the second candidate label is determined. If the first candidate label is different from the second candidate label, it is possible that the first candidate label input by the user is inaccurate, or it is possible that the second candidate label obtained by the label determination model is inaccurate, at this time, a non-structured weight of the non-structured text information and a structured weight of the preset structured text information are acquired, that is, the input vector of the label determination model is adjusted. Then, the final target label is obtained by using the adjusted input vector. The inaccuracy of the label caused by the subjectivity of the pure artificial input is avoided. Whether the input vector of the label determination model needs to be adjusted is determined according to the similarities and differences between the artificial input label and the label obtained by the model for the first time, so that the target label obtained finally is more suitable for the non-structured text input by the user, and is not simply dependent on the artificial input or the output of the model.

[0035] In an exemplary embodiment of the application, after step S200, the method further comprises:

[0036] S500, if the first candidate label is the same as the second candidate label, the first candidate label or the second candidate label is determined as the target label.

[0037] Specifically, if the first candidate label is the same as the second candidate label, it indicates that the first candidate label input by the user is relatively objective and accurate, and at this time, the first candidate label or the second candidate label is determined as the target label.

[0038] In this embodiment, if the first candidate label is the same as the second candidate label, the subsequent step of acquiring the weight is not needed, the computer resource occupation is reduced, and the processing efficiency is improved. Moreover, it is not simply dependent on the artificial input, but the output result of the label determination model and the artificial input label are mutually verified, and the objectivity and accuracy of the finally determined target label are improved.

[0039] In an exemplary embodiment of the application, step S300 comprises:

[0040] S310, if the first candidate label is different from the second candidate label, the correlation degree between the non-structured text information and the preset structured text information is acquired.

[0041] Specifically, if the first candidate label is different from the second candidate label, it indicates that the first candidate label input by the user is inaccurate or the second candidate label obtained by the label determination model is inaccurate. At this time, the association degree between the non-structured text information and the preset structured text information is obtained. If the association degree is high, it indicates that the relevance between the preset structured text information and the non-structured text information is high. The higher the association degree, the higher the accuracy of the target label obtained by using the preset structured text information as the auxiliary input of the non-structured text information. Conversely, if the association degree is low, it indicates that the relevance between the preset structured text information and the non-structured text information is low. The lower the association degree, the lower the accuracy of the target label obtained by using the preset structured text information as the auxiliary input of the non-structured text information. That is, the preset structured text information has a negative effect on the determination of the target label.

[0042] In S320, the non-structured weight and the structured weight are obtained according to the association degree between the non-structured text information and the preset structured text information. The difference between the non-structured weight and the structured weight is inversely proportional to the association degree between the non-structured text information and the preset structured text information.

[0043] Specifically, the difference between the non-structured weight and the structured weight is inversely proportional to the association degree between the non-structured text information and the preset structured text information. The higher the association degree, the higher the accuracy of the target label obtained by using the preset structured text information as the auxiliary input of the non-structured text information. Therefore, the non-structured weight and the structured weight are closer, that is, the difference between the non-structured weight and the structured weight is smaller. Conversely, the lower the association degree, the larger the non-structured weight and the smaller the structured weight, that is, the difference between the non-structured weight and the structured weight is larger.

[0044] In this embodiment, the importance of the preset structured text information for the determination of the target label of the non-structured text information is measured according to the relevance between the non-structured text information and the preset structured text information. The higher the association degree between the preset structured text information and the non-structured text information, the higher the relevance between the content of the preset structured text information and the non-structured text information. At this time, the preset structured text information is used as the supplementary description of the non-structured text information, so that the accuracy of the obtained target label is higher. Conversely, the lower the association degree between the preset structured text information and the non-structured text information, the lower the relevance between the content of the preset structured text information and the non-structured text information. At this time, the preset structured text information is used as the supplementary description of the non-structured text information, which may have a small effect or a negative effect. At this time, the non-structured weight is larger and the structured weight is smaller, that is, the difference between the non-structured weight and the structured weight is larger. The influence of the preset structured text information on the determination of the target label is weakened to avoid reducing the accuracy of the determination of the target label.

[0045] In an example embodiment of the present application, the relevance G between the non-structured text information and the preset structured text information meets the following characteristics:

[0046] G = a / (m + n - a) ;

[0047] wherein m is the number of entities contained in the non-structured text information; n is the number of entities contained in the preset structured text information; and a is the number of identical entities contained in the non-structured text information and the preset structured text information.

[0048] In this embodiment, the entities are extracted from the non-structured text information and the preset structured text information respectively, and the proportion of the same entities in the total number of deduplicated entities is obtained. The greater G is, the more identical entities are contained in the non-structured text information and the structured text information, and the higher the relevance between them is. Conversely, the smaller G is, the fewer identical entities are contained in the non-structured text information and the structured text information, and the lower the relevance between them is.

[0049] It should be noted that the above method of entity extraction can be any method of entity extraction known to those skilled in the art. Herein, no further description is given.

[0050] In addition, the relevance between the non-structured text information and the preset structured text information can also be determined by a semantic analysis model.

[0051] In an example embodiment of the present application, step S400 comprises:

[0052] S410, obtaining a text vector T according to the non-structured text information, the preset structured text information, the non-structured weight and the structured weight; wherein T meets the following characteristics:

[0053] T = (aC, bD) ;

[0054] wherein a is the non-structured weight; C is the feature vector corresponding to the non-structured text information; b is the structured weight; and D is the feature vector corresponding to the preset structured text information.

[0055] S420, inputting the text vector into a label determination model to obtain the target label of the non-structured text information input by the user.

[0056] In this embodiment, after obtaining the non-structured weight and the structured weight, the text vector is obtained according to the non-structured weight and the feature vector corresponding to the non-structured text information, and the structured weight and the feature vector corresponding to the preset structured text information. The non-structured weight and the structured weight determine the importance of the non-structured text information and the preset structured text information in the text vector respectively. The text vector is adjusted based on the weight, which is more flexible, so that the obtained target label is more accurate.

[0057] In an example embodiment of the present application, after step S310, the method further comprises:

[0058] S330, if the correlation degree is less than the preset correlation degree threshold, deleting the preset structured text information to obtain an updated text vector W.

[0059] S340, inputting W into a label determination model to obtain a target label of the user-input non-structured text information.

[0060] In the present embodiment, if the correlation degree is less than the preset correlation degree threshold, i.e., the correlation degree between the preset structured text information and the preset structured text information is very low, at this time, the preset structured text information is likely to have a negative effect on the determination of the target label, therefore, the preset structured text information is deleted, and the feature values corresponding to the preset structured text information part in W can be filled with 0. Finally, W is input into the label determination model to obtain the target label of the user-input non-structured text information. This avoids the accuracy of the determination of the target label by the preset structured text information. As an example: if the current non-structured text information is a message left by a user on a message system in a hospital, and the specific content of the message is feedback that the hospital toilet is not clean, and the preset structured text information is the medical record information of the user, at this time, it can be known that the medical record information basically does not play a role in the process of determining the label of the non-structured text information, and if the feature vector composed of the above message content and the medical record information is input into the label determination model, the target label obtained may also be inaccurate due to the influence of the medical record information.

[0061] Please refer to Figure 2 The embodiment of the present application provides a text label determination device 100, the device comprises:

[0062] A first label acquisition unit 110 is configured to acquire user-input non-structured text information and first candidate labels corresponding to the non-structured text information; wherein the first candidate labels are one of a plurality of preset candidate labels.

[0063] A second label acquisition unit 120 is configured to obtain second candidate labels according to the non-structured text information, preset structured text information, and a label determination model; wherein the second candidate labels are one of a plurality of preset candidate labels; and the preset structured text information is used to describe attribute information of the user.

[0064] A weight determination unit 130 is configured to, if the first candidate labels are different from the second candidate labels, acquire a non-structured weight of the non-structured text information and a structured weight of the preset structured text information.

[0065] The label determination unit 140 is configured to determine a target label of the unstructured text information input by the user according to the unstructured text information, the preset structured text information, the unstructured weight, the structured weight, and a label determination model.

[0066] Embodiments of the present application also provide a computer program product, which comprises program codes for causing an electronic device to perform the steps of the methods according to the various exemplary embodiments of the present application described above when the program product is run on the electronic device.

[0067] In addition, although the various steps of the methods in the present application are described in a specific order in the accompanying 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 result. Additionally or alternatively, some steps can be omitted, a plurality of steps can be combined into one step, and / or one step can be divided into a plurality of steps, etc.

[0068] From the above description of the embodiments, those skilled in the art can easily understand that the example embodiments described herein can be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solutions according to the embodiments 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 U disk, a mobile hard disk, etc.) or a network, and includes a number of instructions to make a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) execute the methods according to the embodiments of the present application.

[0069] In the example embodiments of the present application, an electronic device capable of implementing the above method is also provided.

[0070] Those skilled in the art can understand that each aspect of the present application can be implemented as a system, a method or a program product. Therefore, each aspect of the present application can be embodied in the form of a complete hardware embodiment, a complete software embodiment (including firmware, microcode, etc.), or an embodiment combining hardware and software aspects, which can be collectively referred to as "circuitry", "module" or "system" herein.

[0071] The electronic device according to this embodiment of the present application. The electronic device is merely an example, and should not impose any limitation on the functions and use range of the embodiments of the present application.

[0072] The electronic device is in the form of a general computing device. The components of the electronic device can include, but are not limited to, the at least one processor described above, the at least one memory described above, and a bus connecting different system components, including the memory and the processor.

[0073] The storage stores program codes, which can be executed by the processor, to enable the processor to perform the steps described in the above "Exemplary Method" section according to various exemplary embodiments of the present application.

[0074] The storage can include a readable medium in the form of volatile storage, such as random access memory (RAM) and / or cache storage, and can further include read only memory (ROM).

[0075] The storage can also include program / utility (SW) having a set of at least one program modules that are configured to carry out the processes of the embodiments of the application, including program modules that are:

[0076] The bus can represent one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration bus, a processor or local bus using any of a variety of bus architectures.

[0077] The electronic device can also communicate with one or more external devices (e.g., a keyboard or a pointing device, etc.) that can be coupled thereto and with one or more devices that enable a user to interact with the electronic device (e.g., a display, a remote control device, a mouse, a keypad, etc.). Additionally, the electronic device can communicate with one or more devices that enable the electronic device to communicate with one or more other computing devices. Such communication can occur via an input / output (I / O) interface. Still yet, the electronic device can communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or the Internet) through a network adapter. As depicted, the network adapter can communicate with the other components of the electronic device via the bus. It should be appreciated that the network adapter can also be connected to one or more components of the electronic device in some other fashion or in combination with the bus.

[0078] From the above description of embodiments, it is manifest that the example embodiments described herein can be implemented by software and / or by hardware components. It is further manifest that the embodiments according to the present application can be realized in the form of a software product storing the software program codes on a non-volatile storage medium, such as a CD-ROM, a USB, a mobile hard disk, etc., or on a network, and including a plurality of instructions to enable a computing device (such as a personal computer, a server, a terminal device, or a network device, etc.) to perform the methods according to the embodiments of the present application.

[0079] In the example embodiments of the present application, a computer readable storage medium is also provided, on which a program product capable of implementing the method described above is stored. In some possible implementation manners, various aspects of the present application can also be implemented in the form of a program product, which includes program codes for causing the terminal device to perform the steps described in the "example method" section above according to various example embodiments of the present application when the program product is run on the terminal device.

[0080] The program product can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium may, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination thereof. More specific examples (non-exhaustive list) of the readable storage medium include an electrical connection having one or more wires, a portable disc, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0081] The computer readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, in which readable program codes are borne. Such a propagated data signal can take on many forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination thereof. The readable signal medium can also be any readable medium that is not a readable storage medium and that can send, propagate or transmit the program for use by or in connection with an instruction execution system, apparatus or device.

[0082] The program codes contained on the readable medium can be transmitted by any suitable medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination thereof.

[0083] The program code may be executed by one or more programmable processing devices to perform the operations described herein. The processing devices may include processors, microprocessors, microcontrollers, programmable logic devices, field programmable gate arrays (FPGAs), or other processing devices. The processing devices may be configured to execute program code stored in memory. The memory may include one or more types of memory such as volatile memory (e.g., random access memory (RAM), dynamic random access memory (DRAM), or static random access memory (SRAM)), non-volatile memory (e.g., read only memory (ROM), programmable read only memory (PROM), erasable programmable read only memory (EPROM), electrically erasable programmable read only memory (EEPROM), flash memory, solid state memory, or other non-volatile memory), or other types of memory.

[0084] Furthermore, the above-described diagrams are merely schematic representations 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 readily understood that the processes shown in the above-described diagrams do not indicate or limit the time sequence of the processes. In addition, it is readily understood that the processes can be executed synchronously or asynchronously, for example, in a plurality of modules.

[0085] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, such a division is not mandatory. Indeed, according to the embodiments of the present application, the features and functionalities of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functionalities of one module or unit described above can be further divided into embodied by a plurality of modules or units.

[0086] The above merely describes specific embodiments of the present application, but the protection scope of the present application is not limited thereto, and any changes or replacements easily thought of by those skilled in the art within the technical scope disclosed by the present application should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A text label determination method characterized by, The method comprises: S100, obtaining non-structured text information input by a user and a first candidate label corresponding to the non-structured text information; wherein the first candidate label is one of a plurality of preset candidate labels; S200, obtaining a second candidate label according to the non-structured text information, preset structured text information and a label determination model; wherein the second candidate label is one of the plurality of preset candidate labels; the preset structured text information is used to describe attribute information of the user; S300, if the first candidate label is different from the second candidate label, obtaining a non-structured weight of the non-structured text information and a structured weight of the preset structured text information; S400, obtaining a target label of the non-structured text information input by the user according to the non-structured text information, the preset structured text information, the non-structured weight, the structured weight and the label determination model; Step S300 comprises: S310, if the first candidate label is different from the second candidate label, obtaining a correlation degree between the non-structured text information and the preset structured text information; S320, obtaining the non-structured weight and the structured weight according to the correlation degree between the non-structured text information and the preset structured text information; wherein a difference between the non-structured weight and the structured weight is inversely proportional to the correlation degree between the non-structured text information and the preset structured text information; S330, if the correlation degree is less than a preset correlation degree threshold, deleting the preset structured text information to obtain an updated text vector W; S340, inputting W to the label determination model to obtain the target label of the non-structured text information input by the user; Step S400 comprises: S410, obtaining a text vector T according to the non-structured text information, the preset structured text information, the non-structured weight and the structured weight; wherein T meets the following characteristics: T=(αC, βD); Wherein α is the non-structured weight; C is a feature vector corresponding to the non-structured text information; β is the structured weight; D is a feature vector corresponding to the preset structured text information; S420, inputting the text vector to the label determination model to obtain the target label of the non-structured text information input by the user.

2. The text label determination method of claim 1, wherein, After step S200, the method further comprises: S500, if the first candidate label is the same as the second candidate label, determining the first candidate label or the second candidate label as the target label.

3. The text label determination method of claim 1, wherein, The correlation degree G between the non-structured text information and the preset structured text information meets the following characteristics: G=a / (m+n-a); Wherein m is the number of entities contained in the non-structured text information; n is the number of entities contained in the preset structured text information; a is the number of the same entities contained in the non-structured text information and the preset structured text information.

4. A text label determination apparatus characterized by comprising: The device comprises: A first label obtaining unit is configured to obtain non-structured text information input by a user and a first candidate label corresponding to the non-structured text information; wherein the first candidate label is one of a plurality of preset candidate labels; A second label obtaining unit is configured to obtain a second candidate label according to the non-structured text information, preset structured text information and a label determination model; wherein the second candidate label is one of the plurality of preset candidate labels; the preset structured text information is used to describe attribute information of the user; The weight determination unit is configured to obtain a non-structure weight of the non-structure text information and a structure weight of the preset structure text information if the first candidate label is different from the second candidate label. The label determination unit is configured to obtain a target label of the non-structure text information input by the user according to the non-structure text information, the preset structure text information, the non-structure weight, the structure weight, and a label determination model. The weight determination unit is configured to obtain a non-structure weight of the non-structure text information and a structure weight of the preset structure text information if the first candidate label is different from the second candidate label. S310, if the first candidate label is different from the second candidate label, obtaining a correlation degree between the non-structure text information and the preset structure text information. S320, obtaining the non-structure weight and the structure weight according to the correlation degree between the non-structure text information and the preset structure text information; wherein a difference between the non-structure weight and the structure weight is inversely proportional to the correlation degree between the non-structure text information and the preset structure text information. S330, if the correlation degree is less than a preset correlation degree threshold, deleting the preset structure text information to obtain an updated text vector W. S340, inputting the W to the label determination model to obtain the target label of the non-structure text information input by the user. The label determination unit is configured to obtain a target label of the non-structure text information input by the user according to the non-structure text information, the preset structure text information, the non-structure weight, the structure weight, and a label determination model. S410, obtaining a text vector T according to the non-structure text information, the preset structure text information, the non-structure weight, and the structure weight; wherein T meets the following characteristics: T=(αC, βD); wherein α is the non-structure weight, C is a feature vector corresponding to the non-structure text information, β is the structure weight, and D is a feature vector corresponding to the preset structure text information. S420, inputting the text vector to the label determination model to obtain the target label of the non-structure text information input by the user.

5. A non-transitory computer-readable storage medium, comprising: The storage medium stores at least one instruction or at least one program, which is loaded and executed by the processor to implement the method of any one of claim 3.

6. An electronic device, comprising: The storage medium stores at least one instruction or at least one program, which is loaded and executed by the processor to implement the method of any one of claim 3. The storage medium stores at least one instruction or at least one program, which is loaded and executed by the processor to implement the method of any one of claim 3.

Images