Description text determination method and device, equipment and storage medium

Abstract

The invention discloses a description text determination method, which comprises the following steps: obtaining a to-be-processed text which is a long text with the number of characters greater than a certain threshold value; in order to determine a description text with relatively high quality for a to-be-processed text, the description text corresponding to each dimension in M dimensions can be obtained according to the to-be-processed text, and M is an integer greater than 1. And determining the description text corresponding to each dimension as the description text of the to-be-processed text. In other words, the description text of the to-be-processed text obtained by utilizing the scheme comprises the description text corresponding to each dimension in the M dimensions, so that the description text can contain information of multiple dimensions, and the quality of the determined description text is guaranteed.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, and particularly relates to a description text determination method and device, equipment and a storage medium. BACKGROUND

[0002] In some scenarios, there is a need to extract a description text of a long text. For example, in the field of novels, whether it is a serious published novel or a network novel, there is a need to extract a novel description text. The novel description text can help users quickly determine the main content of the novel, so as to facilitate users to screen novels they want to read. Among them, the description text of the long text is, for example, the synopsis of the long text.

[0003] At present, the artificial extraction method is often used to extract the description text of the long text. For example, for novels, the novel authors are often guided to write corresponding novel description texts for the novels, and other personnel (such as operation and maintenance personnel) are relied on to supplement and perfect the novel description texts written by the authors.

[0004] Using this method, it is impossible to extract high-quality description texts for a large number of novels. Therefore, there is an urgent need for a solution to solve the above problems. SUMMARY

[0005] In order to solve or at least partially solve the above technical problems, the present application provides a description text determination method, device, equipment and storage medium.

[0006] In order to achieve the above purpose, the technical scheme provided by the present application is as follows:

[0007] In a first aspect, the present application provides a description text determination method, which comprises:

[0008] obtaining a to-be-processed text, the to-be-processed text being a long text including a number of characters greater than a certain threshold;

[0009] obtaining a description text corresponding to each dimension in M dimensions respectively according to the to-be-processed text, M being an integer greater than 1;

[0010] determining the description text corresponding to each dimension respectively as the description text of the to-be-processed text.

[0011] In a second aspect, the present application provides a description text determination device, which comprises:

[0012] an obtaining unit, configured to obtain a to-be-processed text, the to-be-processed text being a long text including a number of characters greater than a certain threshold;

[0013] The first determining unit is configured to obtain a description text corresponding to each of M dimensions according to the to-be-processed text, where M is an integer greater than 1.

[0014] The second determining unit is configured to determine the description text corresponding to each of the dimensions as the description text of the to-be-processed text.

[0015] In a third aspect, an electronic device is provided, which includes a processor and a memory.

[0016] The processor is configured to execute instructions stored in the memory, so that the electronic device performs the method according to any one of the first aspect.

[0017] In a fourth aspect, a computer readable storage medium is provided, which includes instructions for instructing a device to perform the method according to any one of the first aspect.

[0018] In a fifth aspect, a computer program product is provided, which, when running on a computer, causes the computer to perform the method according to any one of the first aspect.

[0019] Compared with the related art, the present application has at least the following advantages:

[0020] The present application provides a method for determining a description text, which includes: obtaining a to-be-processed text, the to-be-processed text being a long text including a number of characters greater than a certain threshold. In order to determine a description text with high quality for the to-be-processed text, in the present application, a description text corresponding to each of M dimensions can be obtained according to the to-be-processed text, where M is an integer greater than 1. And the description text corresponding to each of the dimensions is determined as the description text of the to-be-processed text. In other words, the description text of the to-be-processed text obtained by using the present solution includes a description text corresponding to each of the M dimensions, so that the description text can include information of multiple dimensions, and the quality of the determined description text is guaranteed. BRIEF DESCRIPTION OF DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related art, the drawings needed to be used in the embodiments or the related art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments described in the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0022] Figure 1 A flowchart of a method for determining a description text provided by an embodiment of the present application is shown in the figure.

[0023] Figure 2 A schematic diagram of a description text displayed by a client according to an embodiment of the present application;

[0024] Figure 3 A flowchart of a process for determining the M dimensions according to an embodiment of the present application;

[0025] Figure 4 A structural schematic diagram of a description text determining apparatus according to an embodiment of the present application;

[0026] Figure 5 A structural schematic diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0027] In order to make the personnel in the technical field better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of the present application.

[0028] In order to better understand the technical solutions provided by the present application, the description text determining method provided by the present application will be described below in conjunction with some drawings.

[0029] Referring to Figure 1 , the figure is a flowchart of a description text determining method according to an embodiment of the present application.

[0030] Figure 1 The method shown, for example, can be applied to a server. As Figure 1 shown, the description text determining method provided by the present application includes S101-S103.

[0031] S101: Obtain a to-be-processed text, the to-be-processed text being a long text including a number of characters greater than a certain threshold.

[0032] In the present application, the to-be-processed text is a long text including a number of characters greater than a certain threshold. In one specific example, the to-be-processed text is a to-be-processed novel. The characters included in the to-be-processed text include but are not limited to one or more of Chinese characters, English characters, Korean characters, and Japanese characters.

[0033] The present application does not specifically limit the threshold. In one example, the threshold may, for example, be 10,000 or 20,000, etc., which are not listed one by one here.

[0034] S102: Obtain a description text corresponding to each of M dimensions from the to-be-processed text, where M is an integer greater than 1.

[0035] In order to obtain a higher quality description text for the to-be-processed text, so that the user can obtain more content of the to-be-processed text based on the description text, to assist the user in selecting the content (such as a novel) that the user wants to see. In this application, a description text corresponding to each of M dimensions can be obtained from the to-be-processed text, wherein the M dimensions are dimensions of interest to the user, and therefore the description text based on the M dimensions can effectively assist the user in selecting the content that the user wants to see.

[0036] The M dimensions are not specifically limited in the embodiments of the present application. In a specific example, for a novel, when a user selects a novel, the user often pays more attention to the content of dimensions such as character setting, plot outline, emotional pattern, and world setting. Therefore, if the to-be-processed text is a to-be-processed novel, the M dimensions can include at least two of the dimensions of character setting, plot outline, emotional pattern, and world setting.

[0037] Character setting refers to the characteristics of a character in a novel. The setting of a character includes but is not limited to the initial identity (such as a president or a freelancer) and / or special ability of the character. For example, the female protagonist is a cheerful and loving job seeker, and the male protagonist is a cold and domineering tycoon.

[0038] The plot outline includes the core conflict or plot turning point of the novel. For example, the main character obtains an opportunity through the awakening system and leads his companions to become stronger. For example, the female protagonist experiences many setbacks, but becomes more determined and finally achieves happiness.

[0039] The emotional pattern includes the emotional entanglement between the main characters. For example, the male protagonist and the female protagonist meet through a arranged marriage, and the two help each other to make the family stronger. For example, the male protagonist and the female protagonist meet due to a misunderstanding, and gradually resolve the misunderstanding after experiencing a series of things together.

[0040] The world setting is used to describe the era described in the story of the novel. For example, the story takes place in the modern era or across time and space. Or the world setting is used to describe the world in which the story takes place, for example, the story takes place in a specific story background, an imaginary world, a city, or a village.

[0041] In an example, the description text corresponding to each of the M dimensions can be obtained by inputting the to-be-processed text into a text content understanding model. For example, the entire to-be-processed text is input into a text content understanding model to instruct the text content understanding model to analyze the to-be-processed text, thereby obtaining a description text corresponding to each of the M dimensions.

[0042] The text content understanding model mentioned in the present application may be, for example, a machine learning model or a large language model.

[0043] In another example, considering that the number of characters included in the text to be processed may be relatively large, for example, some novels may include hundreds of thousands, millions or even tens of millions of characters. The number of characters that the text content understanding model can understand is limited, for example, the number of characters that the text content understanding model can understand is at most 50,000 characters. Moreover, for the aforementioned description text of different dimensions, it may be embodied through different chapters of the novel. In view of this:

[0044] In one example, in the case where the text to be processed is a novel to be processed, when determining the description text corresponding to the character setting dimension of the novel to be processed, the chapters in which the name of the character appears more than a certain threshold value in the novel to be processed can be input into the text content understanding model to obtain the description text corresponding to the character setting. For example, the name of the character appearing most frequently in the first several chapters (for example, 50 chapters) of the text to be processed can be extracted, and then reference resolution is performed to obtain the main character. Correspondingly, when the content of the chapters in which the main character appears more frequently in the aforementioned 50 chapters is input into the text content understanding model, the text content understanding model can also be input with indication information to indicate that the text content understanding model should pay attention to the character setting of the main character.

[0045] In one example, in the case where the text to be processed is a novel to be processed, when determining the description text corresponding to the plot outline dimension of the novel to be processed, a plurality of core chapters in the novel to be processed can be input into the text content understanding model to obtain the description text corresponding to the plot outline. Since the core chapters generally include relatively important plots, based on the core chapters, the description text corresponding to the plot outline dimension of the novel to be processed can be accurately determined. The core chapters mentioned herein include, but are not limited to, the top P chapters with the most evaluations, or the top P chapters with the highest user continuation rate. P is an integer greater than or equal to 1.

[0046] In one example, in the case where the text to be processed is a novel to be processed, when determining the description text corresponding to the emotional pattern dimension of the novel to be processed, a plurality of chapters in which a plurality of main characters appear in the core chapters of the novel to be processed can be input into the text content understanding model to obtain the description text corresponding to the emotional pattern. Since a plurality of main characters appear in the core chapters, these chapters will describe the emotional entanglement between the main characters, and therefore, inputting the chapters in which a plurality of main characters appear in the core chapters into the text content understanding model can accurately determine the description text corresponding to the emotional pattern dimension of the novel to be processed.

[0047] In one example, in the case that the to-be-processed text is a to-be-processed novel, when determining the description text corresponding to the world setting dimension of the to-be-processed novel, the first N chapters in the to-be-processed novel can be input into the text content understanding model to obtain the description text corresponding to the world setting dimension. Since a novel generally describes the era or world in which it is located in the chapters at the beginning of the novel, inputting the first N chapters into the text content understanding model can accurately obtain the description text corresponding to the world setting dimension of the to-be-processed novel.

[0048] In one particular example, if the to-be-processed novel is a fast travel novel, that is, the main character travels between different worlds or eras, and each world has a different story line. In this case, the to-be-processed novel can be split, and the description text corresponding to the world setting dimension can be determined for each world or era.

[0049] S103: Determine the description text corresponding to each dimension as the description text of the to-be-processed text.

[0050] In this application, after obtaining the description text corresponding to each dimension in the M dimensions according to the to-be-processed text, the description text corresponding to each dimension can be determined as the description text of the to-be-processed text. In other words, the description text of the to-be-processed text includes the description text corresponding to each dimension of the to-be-processed text, so that the description text of the to-be-processed text can include information of multiple dimensions, and the quality of the determined description text is guaranteed.

[0051] In one example, when a user triggers a search operation on a client, the client can send a corresponding search request to the server to request the server to return a corresponding search result. As an example, if the server determines the to-be-processed text as the search result, the server can send the description text of the to-be-processed text to the client. For example, the server can send the cover and description text of the to-be-processed text to the client, and the client can show the cover and description text of the to-be-processed text to the user. Since the description text of the to-be-processed text includes information of the M dimensions that the user is interested in, the user can determine whether the to-be-processed text is the text that the user is interested in through the information of the M dimensions, thereby effectively assisting the user to select the content that the user wants to see.

[0052] Regarding the description text of the to-be-processed text displayed by the client, the following Figure 2 will be described. Figure 2 A schematic diagram of the description text displayed by the client provided by an embodiment of the present application is shown in FIG. 1. As shown in FIG. 1, Figure 2 ​

[0053] The name of the to-be-processed novel is "aaa", and the client displays the name of the to-be-processed novel and corresponding description text, which includes description text corresponding to the three dimensions of the foregoing world setting, character setting and plot outline.

[0054] It should be noted that, Figure 2 Only for the convenience of understanding the description text of the to-be-processed novel mentioned in the present solution, it does not constitute a limitation on the embodiments of the present application, and the page displayed by the client is not limited to the form shown. Figure 2

[0055] As mentioned earlier, the M dimensions are dimensions of interest to users. In one example, the M dimensions can be summarized by the operation and maintenance personnel according to their own experience.

[0056] In another example, the M dimensions can be obtained according to the dimensions involved in the novels historically read by the user. As a specific example, the M dimensions can be determined according to S301-S302 shown. Figure 3 Figure 3 A flowchart for determining the M dimensions provided by the embodiments of the present application.

[0057] S301: For each user in the plurality of users, obtain a plurality of dimensions and description information corresponding to each dimension in the plurality of dimensions according to the dimensions commonly involved in the novels historically read by the user and the description information corresponding to the dimension.

[0058] The plurality of users mentioned here, for example, are users who read texts through a certain client. For example, users who read novels through a certain novel APP.

[0059] In the present application, for each user, the dimensions commonly involved in the novels historically read by the user can be considered as the dimensions of interest to the user. Therefore, performing S301 can obtain the dimensions of interest to the plurality of users, wherein the number of dimensions of interest to each user can be one or more, which is not specifically limited by the present application.

[0060] The dimensions mentioned in S301 have a finer granularity. For example, the dimensions in S301 and the description information corresponding thereto can be understood with reference to Table 1 below.

[0061] Table 1: Dimensions and corresponding description information

[0062] Dimension Description information Core conflict type Conflict caused by different worldviews Emotional development pattern Extreme pain from one-sided sacrifice to the other's realization Time background Seventies Time background Contains the seventies or age background setting Emotional relationship turning type Initiative choice of marriage after experiencing major events Narrative structure Protagonist shuttles between different worlds to perform tasks Emotional relationship pattern Two-way rush after broken mirror is reunited Worldview setting Modern background with surreal elements Emotional interaction pattern High-contrast antagonistic interaction Gold finger type Surreal power tools or abilities drive the plot forward Family relationship reconstruction Protagonist changes the original family predicament Emotional relationship establishment pattern Contract marriage caused by accidental events or interest exchange Fate reversal mechanism Protagonist actively intervenes to reverse the original tragic trajectory Time and space background Time travel to a specific era (such as the seventies)

[0063] ​​The multiple dimensions involved in S301 include but are not limited to the dimensions shown in Table 1, which is only shown for the convenience of understanding the scheme and does not constitute a limitation on the embodiments of the present application. In practice, the multiple dimensions in S301 include, for example, several hundred dimensions.

[0064] S302: Clustering the multiple dimensions based on the description information corresponding to each dimension, to obtain the M dimensions.

[0065] In the present application, considering that the multiple dimensions mentioned in S301 are fine-grained dimensions, and the details involved between different dimensions may overlap. Therefore, in one example, the multiple dimensions can be clustered based on the description information corresponding to each dimension, so that the number of dimensions after clustering is reduced, and the aforementioned multiple dimensions can also be included. In one specific example, the description information of each dimension in the multiple dimensions can be first vectorized to obtain an embedding corresponding to each dimension in the multiple dimensions, and the K-means clustering algorithm is used to cluster the multiple embeddings, gradually reducing the number of clusters obtained by clustering until each cluster does not have a large intersection between the dimensions included in each cluster. In one example, when K=4, the four clusters obtained by clustering are gradually distinguished.

[0066] When K is equal to 4, for each of the four clusters, the fine-grained description information involved in the cluster can be summarized to obtain the following information of the four clusters:

[0067] 1. Role growth and trait setting, including specific dimensions such as female protagonist growth and counterattack, protagonist growth pattern, male character traits, etc.

[0068] 2. Emotion-driven and push mechanism, including specific dimensions such as emotion compensation form, emotion conflict type, emotion turning mode, etc.

[0069] 3. World view and core driving force setting, including specific dimensions such as time background setting, world background setting, event setting, etc.

[0070] 4. Core conflict and special ability system, including specific dimensions such as autonomous destiny reconstruction, accidental plot driving, core conflict type, etc.

[0071] Further, the clustering result is further refined to obtain the aforementioned four dimensions of character setting, plot outline, emotional pattern, and world view setting.

[0072] In the present application, since the aforementioned M dimensions (at least two of the four dimensions of character setting, plot outline, emotional mode and world view setting) are obtained based on dimensions of interest of multiple users, the M dimensions can represent the interests of most users. Accordingly, a user can determine whether the to-be-processed text is a text of interest of the user through the information of the M dimensions, thereby effectively assisting the user in selecting content that the user wants to watch.

[0073] Although in the above example, the M dimensions include at least two of character setting, plot outline, emotional mode and world view setting, this is only one possible implementation of the present application, and in practice, the M dimensions can also include one or more of the following dimensions: ending, highlight, writing style, rhythm, etc.

[0074] Based on the determination method of the description text provided in the embodiments of the present application, the embodiments of the present application further provide a determination apparatus of a description text, which will be explained and described below in combination with Figure 4 the accompanying drawings. Among them, Figure 4 is a structural schematic diagram of a determination apparatus of a description text provided in the embodiments of the present application. It should be noted that the technical details of the determination apparatus of a description text provided in the embodiments of the present application can refer to the related content of the determination method of a description text described above.

[0075] As Figure 4 shown, the determination apparatus 400 of a description text provided in the embodiments of the present application includes:

[0076] The acquisition unit 401 is configured to acquire a to-be-processed text, and the to-be-processed text is a long text including a number of characters greater than a certain threshold.

[0077] The first determination unit 402 is configured to obtain a description text corresponding to each of M dimensions respectively according to the to-be-processed text, and M is an integer greater than 1.

[0078] The second determination unit 403 is configured to determine the description text corresponding to each of the dimensions respectively as a description text of the to-be-processed text.

[0079] Optionally, the apparatus 400 further includes:

[0080] The sending unit is configured to send the description text of the to-be-processed text to a client in response to determining the to-be-processed text as a search result, so that the client displays the description text of the to-be-processed text.

[0081] Optionally, the to-be-processed text is a to-be-processed novel, and the M dimensions include at least two of the following:

[0082] character setting, plot outline, emotional mode and world view setting.

[0083] Optionally, the description text corresponding to the character setting is determined in the following manner:

[0084] The chapter in the to-be-processed novel in which the name appears more than a threshold number of times is input into a text content understanding model to obtain the description text corresponding to the character setting.

[0085] Optionally, the description text corresponding to the plot outline is determined in the following manner:

[0086] The multiple core chapters in the to-be-processed novel are input into a text content understanding model to obtain the description text corresponding to the plot outline.

[0087] Optionally, the description text corresponding to the emotional pattern is determined in the following manner:

[0088] The chapters in which the number of main characters is relatively large in the multiple core chapters in the to-be-processed novel are input into a text content understanding model to obtain the description text corresponding to the emotional pattern.

[0089] Optionally, the description text corresponding to the world setting is determined in the following manner:

[0090] The first N chapters in the to-be-processed novel are input into a text content understanding model to obtain the description text corresponding to the world setting.

[0091] Optionally, the to-be-processed text is a to-be-processed novel, and the M dimensions are determined in the following manner:

[0092] For each user in the multiple users, dimensions that are commonly involved in novels read by the user in the past and description information corresponding to each dimension are obtained.

[0093] The multiple dimensions are clustered based on the description information corresponding to each dimension in the multiple dimensions to obtain the M dimensions.

[0094] In addition, an electronic device is also provided in the embodiments of the present application, and the device includes a processor and a memory: the memory is used to store instructions or computer programs; and the processor is used to execute the instructions or computer programs in the memory, so that the electronic device executes any implementation manner of the method for determining a description text provided in the embodiments of the present application.

[0095] Referring to Figure 5 which shows a structural schematic diagram of an electronic device 500 suitable for being used to implement the embodiments of the present application. Figure 5 The electronic device shown is merely an example, and should not bring any limitation to the functions and use range of the embodiments of the present application.

[0096] As shown in Figure 5 , the electronic device 500 can include a processing device (e.g., a central processor, a graphics processor, etc.) 501 that can perform various appropriate actions and processes according to programs stored in a read-only memory (ROM) 502 or loaded into a random access memory (RAM) 503 from a storage device 508. In the RAM 503, various programs and data required for the operation of the electronic device 500 are also stored. The processing device 501, the ROM 502, and the RAM 503 are connected to each other through a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0097] In general, the following devices can be connected to the I / O interface 505: input devices 506 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 507 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 508 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 509. The communication devices 509 can allow the electronic device 500 to communicate wirelessly or wired with other devices to exchange data. Although Figure 5 The electronic device 500 having various devices is shown, but it is understood that all of the shown devices are not required to be implemented or possessed. More or less devices can be alternatively implemented or possessed.

[0098] In particular, according to embodiments of the present application, the processes described above with reference to the flowcharts can be implemented as a computer software program. For example, embodiments of the present application include a computer program product comprising a computer program carried on a non-transitory computer readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network through the communication devices 509, or installed from the storage devices 508, or installed from the ROM 502. When the computer program is executed by the processing device 501, the above-mentioned functions defined in the methods of embodiments of the present application are performed.

[0099] The electronic device provided by the embodiments of the present application and the method provided by the above-mentioned embodiments belong to the same inventive concept, and the technical details not described in detail in the present embodiment can be referred to the above-mentioned embodiments, and the present embodiment has the same beneficial effects as the above-mentioned embodiments.

[0100] The embodiments of the present application also provide a computer readable medium, the computer readable medium stores instructions or computer programs, when the instructions or computer programs run on the device, make the device execute any embodiment of the method for determining the description text provided by the embodiments of the present application.

[0101] It should be noted that the computer-readable medium described above in this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0102] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0103] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0104] The aforementioned computer-readable medium carries one or more programs, which, when executed by the electronic device, enable the electronic device to perform the aforementioned methods.

[0105] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including but not limited to object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0106] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0107] The units described in the embodiments of this application can be implemented in software or hardware. The names of the units / modules do not necessarily limit the specific unit itself.

[0108] The functions described above in this document can be performed at least in part by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), and so on.

[0109] In the context of this application, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0110] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the systems or apparatus disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple, and relevant parts can be referred to the method section.

[0111] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0112] It should also be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0113] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0114] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method of determining a description of text, characterized by, The method comprises: obtaining a to-be-processed text, the to-be-processed text being a long text including a number of characters greater than a certain threshold; obtaining a description text corresponding to each of M dimensions from the to-be-processed text, M being an integer greater than 1; determining the description text corresponding to each of the dimensions as the description text of the to-be-processed text.

2. The method of claim 1, wherein, The method further comprises: in response to determining the to-be-processed text as a search result, sending the description text of the to-be-processed text to a client to enable the client to display the description text of the to-be-processed text.

3. The method of claim 1, wherein, The to-be-processed text is a to-be-processed novel, and the M dimensions include at least two of the following: character setting, plot outline, emotional pattern, and world view setting.

4. The method of claim 3, wherein, The description text corresponding to the character setting is determined by: inputting chapters in which the name of a character appears more than a certain threshold number of times in the to-be-processed novel into a text content understanding model to obtain the description text corresponding to the character setting.

5. The method of claim 3, wherein, The description text corresponding to the plot outline is determined by: inputting a plurality of core chapters in the to-be-processed novel into a text content understanding model to obtain the description text corresponding to the plot outline.

6. The method of claim 3, wherein, The description text corresponding to the emotional pattern is determined by: inputting a plurality of chapters in which a larger number of main characters appear in the plurality of core chapters in the to-be-processed novel into a text content understanding model to obtain the description text corresponding to the emotional pattern.

7. The method of claim 3, wherein, The description text corresponding to the world view setting is determined by: inputting the first N chapters in the to-be-processed novel into a text content understanding model to obtain the description text corresponding to the world view setting.

8. The method according to any one of claims 1 to 7, characterized in that, The to-be-processed text is a to-be-processed novel, and the M dimensions are determined by: for each user in a plurality of users, obtaining a plurality of dimensions and description information corresponding to each of the plurality of dimensions based on the dimensions involved in novels historically read by the user and the description information corresponding to the dimensions; based on the description information corresponding to each of the plurality of dimensions, clustering the plurality of dimensions to obtain the M dimensions.

9. A determination apparatus for describing a text, characterized in that, The method comprises: an obtaining unit configured to obtain a to-be-processed text, the to-be-processed text being a long text including a number of characters greater than a certain threshold; a first determining unit configured to obtain a description text corresponding to each of M dimensions from the to-be-processed text, M being an integer greater than 1; a second determining unit configured to determine the description text corresponding to each of the dimensions as the description text of the to-be-processed text.

10. An electronic device, comprising: The device comprises a processor and a memory; the memory is configured to store instructions or computer programs; the processor is configured to execute the instructions or computer programs in the memory to enable the electronic device to perform the method of any one of claims 1-8.

11. A computer readable medium characterized by The computer-readable medium stores instructions or computer programs, which, when executed on a device, enable the device to perform the method of any one of claims 1-8.

12. A computer program product, characterised in that, It comprises a computer program carried on a non-transitory computer readable medium, the computer program containing program code for performing the method of any one of claims 1-8.

Images