Text processing method and device and electronic equipment

Abstract

The invention provides a text processing method and device and electronic equipment. The method comprises the following steps: acquiring a plurality of text contents and a preset index corresponding to each text content; according to a plurality of preset indexes, determining quality dimensions corresponding to the plurality of text contents, and determining levels of the quality dimensions corresponding to the plurality of text contents; and determining the text quality of the plurality of text contents according to the levels of the quality dimensions corresponding to the plurality of text contents and the plurality of preset indexes. And the efficiency and accuracy of determining the text quality are improved.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the field of text processing technology, and in particular, to a text processing method, device and electronic device. Background Art

[0002] The large language model can output text content, and the server can distribute the text content. For example, the large language model can create an article, and the server can recommend the article to multiple users.

[0003] Currently, after the large language model outputs text content, the text content can be manually reviewed for quality. Only after the text content passes the quality review can the server distribute the text content. However, manual review is inefficient, resulting in low efficiency in determining text quality. Summary of the invention

[0004] The embodiments of the present disclosure provide a text processing method, device and electronic device, which are used to solve the technical problem of low efficiency in determining text quality in the prior art.

[0005] In a first aspect, an embodiment of the present disclosure provides a text processing method, the text processing method comprising:

[0006] Obtain multiple text contents and preset indicators corresponding to each text content;

[0007] Determining, according to a plurality of preset indicators, quality dimensions corresponding to the plurality of text contents, and determining levels of the quality dimensions corresponding to the plurality of text contents;

[0008] The text qualities of the multiple text contents are determined according to the levels of the quality dimensions corresponding to the multiple text contents and the multiple preset indicators.

[0009] In a second aspect, an embodiment of the present disclosure provides a text processing device, the text processing device comprising an acquisition module, a first determination module, a second determination module and a third determination module, wherein:

[0010] The acquisition module is used to acquire multiple text contents and a preset indicator corresponding to each text content;

[0011] The first determination module is used to determine the quality dimensions corresponding to the multiple text contents according to multiple preset indicators;

[0012] The second determination module is used to determine the levels of the quality dimensions corresponding to the multiple text contents;

[0013] The third determination module is used to determine the text quality of the multiple text contents according to the levels of the quality dimensions corresponding to the multiple text contents and the multiple preset indicators.

[0014] In a third aspect, the present disclosure provides an electronic device comprising: a processor and a memory;

[0015] The memory stores computer-executable instructions;

[0016] The processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the text processing method as described in the first aspect and various possible aspects of the first aspect.

[0017] In a fourth aspect, the present disclosure provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer execution instructions. When a processor executes the computer execution instructions, the text processing method as described in the first aspect and various possible aspects of the first aspect are implemented.

[0018] In a fifth aspect, the present disclosure provides a computer program product, including a computer program, which, when executed by a processor, implements the text processing method as described in the first aspect and various possible aspects of the first aspect.

[0019] The disclosed embodiments provide a text processing method, device, and electronic device, wherein the electronic device can obtain multiple text contents and preset indicators corresponding to each text content, determine the quality dimensions corresponding to the multiple text contents based on the multiple preset indicators, and determine the levels of the quality dimensions corresponding to the multiple text contents, wherein the levels of the quality dimensions can be used to indicate the performance level of the text content on the quality dimension, and the electronic device can determine the text quality of the multiple text contents based on the levels of the quality dimensions corresponding to the multiple text contents and the multiple preset indicators. In the above method, since the electronic device can determine the quality dimensions related to the preset indicators in combination with the preset indicators of the text content, the accuracy of the quality dimensions is improved, and since the electronic device can determine the text quality of the text content based on the levels of the quality dimensions and the preset indicators without manual review, the accuracy and efficiency of determining the text quality can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0021] Figure 1 A schematic diagram of an application scenario provided by an embodiment of the present disclosure;

[0022] Figure 2A flowchart of a text processing method provided by an embodiment of the present disclosure;

[0023] Figure 3 A schematic diagram of determining a quality dimension provided by an embodiment of the present disclosure;

[0024] Figure 4 A schematic diagram of a preset strategy provided in an embodiment of the present disclosure;

[0025] Figure 5 A schematic diagram of a process for determining a quality dimension level provided by an embodiment of the present disclosure;

[0026] Figure 6 A schematic diagram of a process for determining text quality provided by an embodiment of the present disclosure;

[0027] Figure 7 A schematic diagram of a method for determining a change in a level of a quality dimension provided by an embodiment of the present disclosure;

[0028] Figure 8 A structural schematic diagram of a text processing device provided by an embodiment of the present disclosure;

[0029] Fig. 9 A schematic diagram of the structure of another text processing device provided by an embodiment of the present disclosure;

[0030] Fig.10 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0031] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0032] It is understandable that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, scope of use, usage scenarios, etc. of the personal information involved in the present disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0033] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly prompt the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can autonomously choose whether to provide personal information to software or hardware such as an electronic device, application, server, or storage medium that performs the operation of the technical solution of the present disclosure according to the prompt message.

[0034] As an optional but non-limiting implementation, in response to receiving an active request from the user, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0035] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet the relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0036] To facilitate understanding, the concepts involved in the embodiments of the present disclosure are explained below.

[0037] Electronic device: is a device with wireless transceiver function. Electronic devices can be deployed on land, including indoors or outdoors, handheld, wearable or vehicle-mounted. The electronic device can be a mobile phone, a tablet computer, a computer with wireless transceiver function, a virtual reality (VR) electronic device, an augmented reality (AR) electronic device, a wireless terminal in industrial control, a vehicle-mounted electronic device, a wireless terminal in self-driving, a wireless electronic device in remote medical care, a wireless electronic device in smart grid, a wireless electronic device in transportation safety, a wireless electronic device in smart city, a wireless electronic device in smart home, a wearable electronic device, etc. The electronic device involved in the embodiments of the present disclosure can also be called a terminal, a user equipment (UE), an access electronic device, a vehicle-mounted terminal, an industrial control terminal, a UE unit, a UE station, a mobile station, a mobile station, a remote station, a remote electronic device, a mobile device, a UE electronic device, a wireless communication device, a UE agent or a UE device, etc. The electronic device can also be fixed or mobile.

[0038] In the related art, a large language model can output text content, and a server can distribute the text content. For example, an electronic device can input the text "Create an article related to weather forecast" into a large language model, and the large language model can generate an article based on the input text, which can describe the future weather. After the large language model outputs the text content, it is necessary to conduct a quality review of the text content. Only after the quality review is passed can the server distribute the text content online. At present, the quality review of the text content output by the large language model can be based on manual review. For example, a large language model can create 1,000 articles, and the reviewer can conduct a quality review on each article. If the quality review of the article passes, the electronic device can recommend the article to multiple users. However, when the amount of text content to be reviewed is large, the efficiency and accuracy of manual review are low, which leads to low efficiency and accuracy in determining the quality of the text.

[0039] In order to solve the technical problems in the related art, the embodiment of the present disclosure provides a text processing method, the electronic device can obtain multiple text contents and preset indicators corresponding to each text content, determine the quality dimensions corresponding to the multiple text contents according to the multiple preset indicators, for any text content, the electronic device can obtain a preset strategy, wherein the preset strategy can include multiple preset quality dimensions and a determination strategy related to each preset quality dimension, the determination strategy is used to determine the level of the preset quality dimension, the electronic device can determine the level of the quality dimension corresponding to the text content according to the preset strategy and the text content, and determine the text quality of the multiple text contents according to the level of the quality dimension corresponding to the multiple text contents and the multiple preset indicators. In the above method, since the level of the quality dimension is used to indicate the performance level of the text content on the quality dimension, the electronic device can quickly and accurately determine the text quality of the multiple text contents based on the level of the quality dimension and the preset indicator, thereby improving the efficiency and accuracy of determining the text quality.

[0040] Next, combine Figure 1 , the application scenarios of the embodiments of the present disclosure are described.

[0041] Figure 1 A schematic diagram of an application scenario provided by an embodiment of the present disclosure. Figure 1 , including: article 1, article 2, ..., article n and a large language model. The large language model can be set in an electronic device ( Figure 1 The preset indicator corresponding to article 1 is 1000 readings, the preset indicator corresponding to article 2 is 2000 readings, ..., the preset indicator corresponding to article n is 7000 readings.

[0042] See also Figure 1, the electronic device can input article 1, article 2, ..., article n and the preset indicators of each article into the large language model. The large language model can output that article 1 is related to quality dimension A and quality dimension B, the level of quality dimension A is 3 points, the level of quality dimension B is 4 points, article 2 is related to quality dimension A and quality dimension C, the quality dimension A is 3 points, the level of quality dimension C is 5 points, ..., article n is related to quality dimension D and quality dimension E, the level of quality dimension D is 2 points, and the level of quality dimension E is 3 points.

[0043] See also Figure 1 , the electronic device can fit the relationship between the level of quality dimension A and the level of quality dimension B associated with article 1 based on indicator a associated with article 1, get 3.5 points, and determine that the quality review of article 1 has passed. The electronic device can fit the level of quality dimension A and the level of quality dimension C associated with article 2 based on indicator b associated with article 2, get 4.5 points, and determine that the quality review of article 2 has passed. ..., the electronic device can fit the level of quality dimension D and the level of quality dimension E associated with article n based on indicator c associated with article n, get 2.3 points, and determine that the quality review of article n has not passed. In this way, the electronic device can quickly and accurately determine the text quality of the article, and improve the efficiency and accuracy of determining the text quality.

[0044] It should be noted that Figure 1 The above is an example of the application scenario of the embodiment of the present disclosure, but not a limitation of the application scenario of the embodiment of the present disclosure.

[0045] The technical solution of the present invention and how the technical solution of the present invention solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present invention will be described below in conjunction with the accompanying drawings.

[0046] Figure 2 A flowchart of a text processing method provided by an embodiment of the present disclosure. Figure 2 , the method may include:

[0047] S201: Acquire multiple text contents and a preset indicator corresponding to each text content.

[0048] The execution subject of the embodiments of the present disclosure may be an electronic device, or a text processing device provided in the electronic device. The text processing device may be implemented according to software, or may be implemented according to a combination of software and hardware, which is not limited in the embodiments of the present disclosure. The electronic device may be any device with terminal computing capability. For example, the electronic device may be a server, a computer, or other device, which is not limited in the embodiments of the present disclosure.

[0049] The text content may be any text content whose text quality is to be determined, for example, an article, a paragraph, a sentence, etc. The text content may also be any other form of text, which is not limited in the embodiments of the present disclosure.

[0050] Optionally, the electronic device may receive multiple text contents sent by other devices. For example, the server may receive text contents sent by multiple terminal devices, and then obtain multiple text contents. For example, user 1 creates an article a based on terminal device A and sends the article a to the server, and user 2 may create an article b based on terminal device B and send the article b to the server. In this way, the server may obtain article a and article b based on terminal device A and terminal device B.

[0051] Optionally, the electronic device may obtain multiple text contents based on the large language model. For example, the electronic device may include a large language model, and the electronic device may obtain multiple text contents based on the output of the large language model.

[0052] It should be noted that the electronic device may also obtain multiple text contents based on any feasible implementation method (eg, obtaining multiple text contents from a database, etc.), and the embodiments of the present disclosure are not limited to this.

[0053] The preset indicator may be an indicator corresponding to the text content. For example, the preset indicator may be a business indicator corresponding to the text content. For example, the preset indicator corresponding to the text content may be any feasible indicator such as the reading volume, click-through rate, forwarding rate, number of comments, etc. of the text content, which is not limited in the embodiments of the present disclosure.

[0054] Optionally, the electronic device may pre-set preset indicators corresponding to each text content, or may determine the preset indicators corresponding to the text content based on business needs (e.g., after an article is published, if the required reading volume of the article is 1000, the preset indicator corresponding to the article may be a reading volume of 1000). The embodiments of the present disclosure are not limited to this.

[0055] S202: Determine quality dimensions corresponding to multiple text contents according to multiple preset indicators.

[0056] The quality dimension can be used to determine the quality attributes of the text content. For example, the quality dimension of the text content can include any dimension such as accuracy, timeliness, readability, topicality, emotionality, interest, coherence, completeness, style consistency, format standardization, etc., which is not limited in the embodiments of the present disclosure.

[0057] Among them, for any text content, the electronic device can determine the quality dimensions corresponding to multiple text contents according to the following feasible implementation method: based on the preset indicators corresponding to the text content, determine the correlation between the text content and each preset quality dimension, and determine the preset quality dimension with a correlation greater than or equal to a preset threshold as the quality dimension corresponding to the text content. In this way, the accuracy of the quality dimension related to the text content can be improved, thereby improving the accuracy of determining the text quality.

[0058] The degree of correlation can be used to indicate the degree of association between the text content and the preset quality dimension, wherein the preset quality dimension can be any of the above quality dimensions, which is not limited in the embodiments of the present disclosure. For example, the electronic device can understand the text content based on the large language model, and determine the degree of correlation associated with each preset quality dimension according to the preset indicator corresponding to the text content, and output the preset quality dimension whose correlation degree is greater than or equal to the preset threshold value, to obtain the quality dimension corresponding to the text content.

[0059] For example, the electronic device can input text content and preset indicators into the large language model, and the large language model can output multiple preset quality dimensions that are highly correlated with the preset indicators to obtain quality dimensions corresponding to the text content. The large language model can also output the reasons for selecting multiple preset quality dimensions. Before the electronic device inputs text content and preset indicators into the large language model, it can randomly extract multiple samples (sample text content, sample indicators of the sample text content, and sample quality dimensions corresponding to the sample text content) to fine-tune the large language model, thereby improving the accuracy of the large language model.

[0060] Next, combine Figure 3 , a detailed description is given of the quality dimensions corresponding to the text content.

[0061] Figure 3 A schematic diagram of determining quality dimensions provided by an embodiment of the present disclosure. Figure 3 , including: large language model. Among them, electronic equipment ( Figure 3 (Not shown) An article and a preset indicator (read volume of 100,000) corresponding to the article can be input into the large language model. The large language model can understand the content of the article and, based on the preset indicator, output the quality dimension corresponding to the article, where the quality dimension includes topicality, timeliness, and interest.

[0062] Optionally, the electronic device may determine the type of text content, and pre-set the correspondence between each type of text content, the type of preset indicator, and the quality dimension. The electronic device may determine the quality dimension corresponding to the text content according to the type of text content, the type of preset indicator, and the correspondence. For example, the type of text content may include popular science text content, natural science text content, entertainment text content, etc., wherein the correspondence may be that popular science text content, reading volume is associated with readability and completeness, natural science text content, reading volume, click-through rate is associated with readability and fun, and entertainment content, reading volume, click-through rate is associated with topicality and timeliness, etc.

[0063] It should be noted that the electronic device may also determine the quality dimension corresponding to the text content according to any feasible implementation method, and the embodiments of the present disclosure are not limited to this.

[0064] S203: Determine the levels of quality dimensions corresponding to the multiple text contents.

[0065] Among them, the level of the quality dimension can be used to indicate the performance level of the text content in the quality dimension. For example, the quality dimension level can be level 1, level 2, level 3, level 4 and level 5, wherein the higher the quality dimension level, the better the performance level of the text content in the quality dimension. For example, the quality dimension corresponding to text content 1 is timeliness, and the quality dimension corresponding to text content 2 is also timeliness. If the timeliness level of text content 1 is level 5 and the timeliness level of text content 2 is level 3, it means that the timeliness of text content 1 is better than the timeliness of text content 2.

[0066] It should be noted that the electronic device may also perform level classification of the quality dimension (eg, 1 point, 2 points, etc.) based on any feasible implementation method, and the embodiments of the present disclosure are not limited to this.

[0067] Among them, for any text content, the electronic device can determine the levels of quality dimensions corresponding to multiple text contents according to the following feasible implementation method: obtain a preset strategy, and determine the levels of quality dimensions corresponding to the text content according to the preset strategy and the text content.

[0068] The preset strategy may include multiple preset quality dimensions and a determination strategy related to each preset quality dimension, and the determination strategy may be used to determine the level of the quality dimension. For example, the preset measurement may include timeliness, a determination strategy corresponding to timeliness, topicality, and a determination strategy corresponding to topicality, wherein the determination strategy corresponding to timeliness may be used to indicate the division method of the level of timeliness, and the determination strategy corresponding to topicality may be used to indicate the division method of the level of topicality.

[0069] Next, combine Figure 4, describe the preset strategy.

[0070] Figure 4 A schematic diagram of a preset strategy provided by an embodiment of the present disclosure. Figure 4 , including: preset strategies. Among them, the preset strategies include readability and fun. Among them, the determination strategies corresponding to readability include the judgment method of readability and the level division method of readability. Among them, the judgment method of readability is the reading difficulty of the content, including the conciseness of the language, the clarity of the logic and the neatness of the format. Level 3 readability is concise and clear language, clear logic, distinct paragraphs, neat format, and smooth reading experience. Level 2 readability is general language and logic, ordinary format, and medium reading experience. Level 1 readability is lengthy or obscure language, confusing logic, messy format, and poor reading experience.

[0071] See also Figure 4 , the corresponding determination strategy of interest includes a method for judging interest and a method for dividing interest levels. Among them, the method for judging interest is whether the content is vivid and interesting, and whether it can attract and maintain the interest of readers. Level 3 interest means that the content is interesting and can attract readers, and readers are happier during the reading process. Level 2 interest means that the content is interesting to a certain extent, but the appeal is average, and readers may find it boring. Level 1 interest means that the content is boring and readers find it difficult to finish reading. In this way, the electronic device can accurately determine the level of the quality dimension corresponding to the text content based on the preset strategy.

[0072] Among them, the electronic device determines the quality dimension level corresponding to the text content according to the preset strategy and the text content, which can be specifically: obtaining a large language model, processing the text content and the preset strategy according to the target sub-model in the large language model, and obtaining the level of the quality dimension corresponding to the text content.

[0073] The large language model may include multiple sub-models, and the sub-models may be associated with preset quality dimensions. For example, the large language model may include sub-model 1, sub-model 2, and sub-model 3, wherein sub-model 1 is associated with timeliness, sub-model 2 is associated with topicality, and sub-model 3 is associated with fun, that is, sub-model 1 may output the level of timeliness corresponding to the text content, sub-model 2 may output the level of topicality corresponding to the text content, and sub-model 3 may output the level of fun corresponding to the text content.

[0074] Optionally, the large language model may be a large model base. For example, the large model base may include multiple quality dimension-related models, and each quality dimension-related model may determine the level of the text content in the quality dimension.

[0075] Among them, the preset quality dimension associated with the target sub-model is the same as the quality dimension corresponding to the text content. For example, the large language model may include sub-model 1, sub-model 2 and sub-model 3, wherein sub-model 1 is associated with timeliness, sub-model 2 is associated with topicality, and sub-model 3 is associated with fun. If the quality dimensions corresponding to the text content are timeliness and topicality, the electronic device can determine that the target sub-models in the large language model are sub-model 1 and sub-model 2, and the electronic device can process the text content and the preset strategy based on sub-model 1 to obtain the level of timeliness of the text content, and the electronic device can process the text content and the preset strategy based on sub-model 2 to obtain the level of topicality of the text content.

[0076] Next, combine Figure 5 , the process of determining the level of the quality dimension corresponding to the text content is explained.

[0077] Figure 5 A schematic diagram of a process for determining a quality dimension level provided by an embodiment of the present disclosure. Figure 5 , including text content, preset strategies and a large language model. Among them, the quality dimensions related to the text content are timeliness and topicality. The large language model includes a sub-model related to timeliness, a sub-model related to topicality, ..., a sub-model related to interest. The large language model can determine that the target sub-model includes a sub-model related to timeliness and a sub-model related to topicality. The large language model can process the text content and the preset strategy based on the sub-model related to timeliness, and obtain the level of timeliness: level 5. The large language model can process the text content and the preset strategy based on the sub-model related to topicality, and obtain the level of topicality: level 4. In this way, the electronic device can accurately determine the level of the quality dimension corresponding to the text content, and then accurately determine the text quality of the text content.

[0078] S204: Determine text quality of the multiple text contents according to the levels of the quality dimensions corresponding to the multiple text contents and multiple preset indicators.

[0079] Among them, the electronic device can determine the text quality of multiple text contents according to the following feasible implementation method: determine the weight distribution of the quality dimension corresponding to each text content according to the levels of the quality dimensions corresponding to the multiple text contents and multiple preset indicators, and for any text content, determine the text quality of the text content according to the level of the quality dimension corresponding to the text content and the weight distribution of the quality dimension corresponding to the text content.

[0080] The weight distribution may include the weight corresponding to the level of each quality dimension. For example, if the quality dimensions corresponding to the text content include timeliness, topicality, and fun, the weight distribution may be (0.3, 0.2, 0.5), where the weights other than timeliness, topicality, and fun are 0. For example, the number of preset quality dimensions is 10, and if the text content is associated with 3 of the preset quality dimensions, then in the weight distribution, the 3 preset quality dimensions have corresponding weights, and the weights of the other 7 preset quality dimensions are 0.

[0081] The process of determining the weight distribution is described below based on a specific example.

[0082] Among them, if multiple text contents have quality scores corresponding to M quality dimensions, the preset indicators are N, and for any text content, the following formula is satisfied:

[0083]

[0084] Among them, P N*M is the N*M weight distribution matrix, is the level-related vector of the M quality dimensions of the i-th text content, N preset indicators related to the i-th text content (eg, 100,000 readings, 70% click-through rate, etc.).

[0085] Among them, in the above formula, when determining P N*M When , the electronic device can determine the step length s, and extract R valid text contents within the step length range of s, and obtain the following formula:

[0086]

[0087] Right now,

[0088] P N*M Q M*R =W N*R

[0089] So, Q M*R is R effective text content related quality dimension matrix, W N*R is a preset index matrix related to R valid text content. The electronic device can calculate P based on any feasible method such as gradient descent solution. N*M , that is, the weight distribution of quality dimensions corresponding to multiple text contents.

[0090] Among them, for any text content, the electronic device can determine the text quality of the text content according to the following feasible implementation method: perform weighted summation of the level of the quality dimension and the weight distribution to obtain the target parameter, and determine the text quality according to the target parameter.

[0091] The target parameter may be used to indicate the text quality of the text content. The text quality is proportional to the target parameter. For example, the larger the target parameter corresponding to the text content, the better the text quality of the text content, and the smaller the target parameter corresponding to the text content, the worse the text quality of the text content. For example, if the target parameter corresponding to text content 1 is 3 points and the target parameter corresponding to text content 2 is 3.5 points, the text quality of text content 2 is higher than the text quality of text content 1.

[0092] For example, the quality dimensions corresponding to the text content include timeliness and topicality, where the level of timeliness is 5 points and the level of topicality is 3 points. If the weight distribution of the quality dimensions corresponding to the text content is (0.3, 0.7), the electronic device can determine that the target parameter corresponding to the text content is 3.6 (0.3*5+0.7*3). In this way, the electronic device can quantify the text quality based on the target parameter to improve the accuracy of determining the text quality.

[0093] Optionally, when the target parameter is greater than or equal to the first threshold, the electronic device can determine that the text quality of the text content related to the target parameter is high, and the text quality review of the text content has passed. When the target parameter is less than the first threshold, the electronic device can determine that the text quality of the text content related to the target parameter is low, and the text quality review of the text content has not passed. For example, if the first threshold is 4 points, if the target parameter of text content 1 is 3.9 points, the target parameter of text content 2 is 4 points, and the target parameter of text content 3 is 4.1 points, the electronic device can determine that the text quality review of text content 1 has not passed, and the text quality reviews of text content 2 and text content 3 have passed.

[0094] Next, combine Figure 6 , a process for determining text quality of text content is described.

[0095] Figure 6 A schematic diagram of a process for determining text quality provided by an embodiment of the present disclosure. Figure 6 , including: Article 1, Article 2 and Article 3. Among them, the preset indicator of Article 1 is 1000 readings, the preset indicator of Article 2 is 2000 clicks, and the preset indicator of Article 3 is 6000 readings. Among them, electronic equipment ( Figure 6 (Not shown) Based on article 1 and a reading volume of 1000, it can be determined that the quality dimensions of article 1 include readability and timeliness. Based on article 2 and a click volume of 2000, it can be determined that the quality dimensions of article 2 include readability and interest. Based on article 3 and a reading volume of 6000, it can be determined that the quality dimensions of article 3 include interest and timeliness.

[0096] See also Figure 6, the electronic device can input article 1, article 2, article 3 and preset strategies into the large language model, wherein the preset strategies can include a determination strategy for readability, a determination strategy for timeliness, a determination strategy for interest, a task and a return format. The task can be the text "determine the level of the quality dimension of the article according to the determination strategy, and give an explanation for each level". The return format can be the format of the text output by the large language model.

[0097] See also Figure 6 , the large language model can output that the readability of article 1 is 3 points and the timeliness is 4 points, the readability of article 2 is 3 points and the interest is 5 points, and the interest of article 3 is 2 points and the timeliness is 3 points. The electronic device can determine the weight distribution based on the preset indicators. Among them, the weight distribution of article 1 is: readability: 0.3, timeliness: 0.7, and interest: 0. The weight distribution of article 2 is: readability: 0.6, timeliness: 0, and interest: 0.4. The weight distribution of article 3 is: readability: 0, timeliness: 0.5, and interest: 0.5.

[0098] See also Figure 6 , the electronic device can determine the text quality according to the weight distribution and the level of the quality dimension corresponding to each article. Among them, the first threshold can be 3.5, the target parameter of article 1 is 3.7, and article 1 passes the review, the target parameter of article 2 is 3.8, and article 2 passes the review, and the target parameter of article 3 is 2.5, and article 3 fails the review. In this way, the electronic device can quickly and accurately determine the text quality, and improve the efficiency and accuracy of determining the text quality.

[0099] It should be noted that Figure 6 The illustrated embodiment exemplifies the number of articles and the number of quality dimensions of each article, but does not limit the number of articles and the number of quality dimensions of each article in the embodiment of the present disclosure.

[0100] The disclosed embodiment provides a text processing method, in which an electronic device can obtain multiple text contents and preset indicators corresponding to each text content, determine the quality dimensions corresponding to the multiple text contents according to the multiple preset indicators, and for any text content, the electronic device can obtain a preset strategy, and determine the level of the quality dimension corresponding to the text content according to the preset strategy and the text content. The electronic device can determine the weight distribution of the quality dimension corresponding to each text content according to the levels of the quality dimensions corresponding to the multiple text contents and the multiple preset indicators, and determine the text quality of the text content according to the levels of the quality dimensions corresponding to the text contents and the weight distribution of the quality dimensions corresponding to the text contents. In the above method, since the level of the quality dimension is used to indicate the performance level of the text content on the quality dimension, the electronic device can quickly and accurately determine the text quality of multiple text contents based on the level of the quality dimension and the preset indicators, thereby improving the efficiency and accuracy of determining the text quality.

[0101] exist Figure 2 Based on the embodiment shown in the figure, after the electronic device determines the target weight of the quality dimension corresponding to each text content, the above text processing method also includes a method for determining the change amount of the level of the quality dimension. Figure 7 , a method for determining the amount of change in the level of the quality dimension is described in detail.

[0102] Figure 7 A schematic diagram of a method for determining the change in the level of a quality dimension provided by an embodiment of the present disclosure. Figure 7 The method flow includes:

[0103] S701, obtaining the change amount of a preset indicator.

[0104] Among them, the change amount of the preset indicator corresponding to the text content can be an arbitrarily set change amount. For example, the preset indicator corresponding to the text content is a reading volume of 1000. If the change amount of the preset indicator can be an increase of 500, the reading volume corresponding to the text content is updated from 1000 to 1500. For example, the preset indicator corresponding to the text content is a click-through rate of 50%. If the change amount of the preset indicator can be an increase of 10%, the click-through rate corresponding to the text content is updated from 50% to 60%. For example, the preset indicator corresponding to the text content is a reading volume of 5000 and a click-through rate of 60%. If the change amount of the preset indicator can be an increase of 2000, an increase of 20%, the reading volume corresponding to the text content is updated from 5000 to 700, and the click-through rate is updated from 60% to 80%.

[0105] It should be noted that the electronic device can obtain the change in the preset indicator according to any feasible implementation method, for example, receiving the change in the preset indicator sent by other devices, etc. The change in the preset indicator is determined according to business needs (increasing the number of readings, increasing the click rate, etc.), and the embodiments of the present disclosure are not limited to this.

[0106] S702: Determine the change in the level of the quality dimension according to the change in the preset indicator and the weight distribution of the quality dimension.

[0107] Optionally, the change in the level of the quality dimension can indicate the update direction of the text content. For example, if the change in the level of readability corresponding to the text content is an increase of 0.4 points, and the change in the level of interest is an increase of 0.3 points, the user can update the text content and improve the readability and interest of the text content, which can accurately improve the text quality of the text content.

[0108] Among them, the change in the level of the quality dimension is determined to satisfy the following formula:

[0109] P N*M ΔQ=ΔW

[0110] Wherein, ΔW can be the change of the preset index, ΔQ can be the change of the level of the quality dimension, and P N*M It can be a weight distribution.

[0111] Based on the above formula, the electronic device can obtain the following formula:

[0112]

[0113] In this way, the electronic device can accurately determine the amount of change in the level of the quality dimension.

[0114] S703: Update the text content according to the change in the level of the quality dimension.

[0115] For example, the preset indicator corresponding to the text content is a reading volume of 1000, and the quality dimensions corresponding to the text content include readability and fun. The electronic device can determine that the weight distribution corresponding to the text content is (K, L). If the electronic device determines that the preset indicator corresponding to the text content is updated from a reading volume of 1000 to a reading volume of 1500, the electronic device can determine that the change in reading volume is 500. The electronic device can determine the score that needs to be increased for readability and the score that needs to be increased for fun based on the change in reading volume (500) and the weight distribution (K, L). In this way, the text quality of the text content can be improved and the efficiency of online distribution of text content can be improved.

[0116] The disclosed embodiment provides a method for determining the amount of change in the level of a quality dimension, where the electronic device can obtain the amount of change in a preset indicator, determine the amount of change in the level of the quality dimension based on the amount of change in the preset indicator and the weight distribution of the quality dimension, and update the text content according to the amount of change in the level of the quality dimension. In this way, when the preset indicator changes, the electronic device can accurately determine the amount of change in the level of the quality dimension, and update the text content according to the amount of change in the level of the quality dimension, so that the accuracy of text content updates can be improved, the text quality of the text content can be improved, and the online distribution efficiency of the text content can be improved.

[0117] Figure 8 This is a structural diagram of a text processing device provided by an embodiment of the present disclosure. Figure 8 The text processing device 800 includes an acquisition module 801, a first determination module 802, a second determination module 803 and a third determination module 804, wherein:

[0118] The acquisition module 801 is used to acquire multiple text contents and a preset indicator corresponding to each text content;

[0119] The first determination module 802 is used to determine the quality dimensions corresponding to the multiple text contents according to multiple preset indicators;

[0120] The second determination module 803 is used to determine the levels of the quality dimensions corresponding to the multiple text contents;

[0121] The third determination module 804 is used to determine the text quality of the multiple text contents according to the levels of the quality dimensions corresponding to the multiple text contents and the multiple preset indicators.

[0122] According to one or more embodiments of the present disclosure, the second determining module 803 is specifically configured to:

[0123] Acquire a preset strategy, where the preset strategy includes a plurality of preset quality dimensions and a determination strategy related to each preset quality dimension, where the determination strategy is used to determine a level of the preset quality dimension;

[0124] According to the preset strategy and the text content, the level of the quality dimension corresponding to the text content is determined.

[0125] According to one or more embodiments of the present disclosure, the second determining module 803 is specifically configured to:

[0126] Acquire a large language model, wherein the large language model includes a plurality of sub-models, and the sub-models are associated with preset quality dimensions;

[0127] The text content and the preset strategy are processed according to the target sub-model in the large language model to obtain the level of the quality dimension corresponding to the text content, and the preset quality dimension associated with the target sub-model is the same as the quality dimension corresponding to the text content.

[0128] According to one or more embodiments of the present disclosure, the first determining module 802 is specifically configured to:

[0129] Determining the relevance of the text content to each preset quality dimension based on the preset indicators corresponding to the text content;

[0130] A preset quality dimension with a correlation degree greater than or equal to a preset threshold is determined as the quality dimension corresponding to the text content.

[0131] According to one or more embodiments of the present disclosure, the third determining module 804 is specifically configured to:

[0132] Determine, according to the levels of the quality dimensions corresponding to the multiple text contents and the multiple preset indicators, a weight distribution of the quality dimensions corresponding to each text content, wherein the weight distribution includes a weight corresponding to the level of each quality dimension;

[0133] For any text content, the text quality of the text content is determined according to the level of the quality dimension corresponding to the text content and the weight distribution of the quality dimension corresponding to the text content.

[0134] According to one or more embodiments of the present disclosure, the third determining module 804 is specifically configured to:

[0135] Performing a weighted summation on the level of the quality dimension and the weight distribution to obtain a target parameter;

[0136] The text quality is determined according to the target parameter, and the text quality is proportional to the target parameter.

[0137] The text processing device provided in the embodiment of the present disclosure can be used to execute the technical solution of the above-mentioned method embodiment. Its implementation principle and technical effect are similar, and this embodiment will not be repeated here.

[0138] Fig. 9 A schematic diagram of the structure of another text processing device provided by an embodiment of the present disclosure. Figure 8 Based on the examples shown, see Fig. 9 The text processing device 800 further includes an updating module 804, wherein the updating module 805 is used to:

[0139] Get the change of preset indicators;

[0140] Determining a change in the level of the quality dimension according to a change in the preset indicator and a weight distribution of the quality dimension;

[0141] The text content is updated according to the change in the level of the quality dimension.

[0142] The text processing device provided in the embodiment of the present disclosure can be used to execute the technical solution of the above-mentioned method embodiment. Its implementation principle and technical effect are similar, and this embodiment will not be repeated here.

[0143] Fig.10 This is a schematic diagram of the structure of an electronic device provided by an embodiment of the present disclosure. Fig.10 , which shows a schematic diagram of the structure of an electronic device 1000 suitable for implementing the embodiment of the present disclosure. The electronic device may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, personal digital assistants (PDAs), tablet computers (Portable Android Devices, PADs), portable multimedia players (PMPs), vehicle terminals (such as vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Fig.10 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0144] like Fig.10 As shown, the electronic device 1000 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 1001, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1008 to a random access memory (RAM) 1003. Various programs and data required for the operation of the electronic device 1000 are also stored in the RAM 1003. The processing device 1001, the ROM 1002, and the RAM 1003 are connected to each other via a bus 1004. An input / output (I / O) interface 1005 is also connected to the bus 1004.

[0145] Typically, the following devices may be connected to the I / O interface 1005: input devices 1006 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 1007 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1008 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1009. The communication device 1009 may allow the electronic device 1000 to communicate with other devices wirelessly or by wire to exchange data. Although Fig.10 The electronic device 1000 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0146] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device 1009, or installed from a storage device 1008, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0147] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0148] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0149] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device executes the method shown in the above embodiment.

[0150] An embodiment of the present disclosure provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, various methods that may be involved in the above embodiments are implemented.

[0151] An embodiment of the present disclosure provides a computer program product, including a computer program, which implements various methods that may be involved in the above embodiments when executed by a processor.

[0152] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may 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 may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0153] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0154] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware. The name of a unit does not limit the unit itself in some cases. For example, the first acquisition unit may also be described as a "unit for acquiring at least two Internet Protocol addresses".

[0155] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0156] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0157] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0158] In a first aspect, an embodiment of the present disclosure provides a text processing method, the text processing method comprising:

[0159] Obtain multiple text contents and preset indicators corresponding to each text content;

[0160] Determining, according to a plurality of preset indicators, quality dimensions corresponding to the plurality of text contents, and determining levels of the quality dimensions corresponding to the plurality of text contents;

[0161] The text qualities of the multiple text contents are determined according to the levels of the quality dimensions corresponding to the multiple text contents and the multiple preset indicators.

[0162] According to one or more embodiments of the present disclosure, for any text content, determining the levels of the quality dimensions corresponding to the multiple text contents includes:

[0163] Acquire a preset strategy, where the preset strategy includes a plurality of preset quality dimensions and a determination strategy related to each preset quality dimension, where the determination strategy is used to determine a level of the preset quality dimension;

[0164] According to the preset strategy and the text content, the level of the quality dimension corresponding to the text content is determined.

[0165] According to one or more embodiments of the present disclosure, determining the level of the quality dimension corresponding to the text content according to the preset strategy and the text content includes:

[0166] Acquire a large language model, wherein the large language model includes a plurality of sub-models, and the sub-models are associated with preset quality dimensions;

[0167] The text content and the preset strategy are processed according to the target sub-model in the large language model to obtain the level of the quality dimension corresponding to the text content, and the preset quality dimension associated with the target sub-model is the same as the quality dimension corresponding to the text content.

[0168] According to one or more embodiments of the present disclosure, for any text content, determining the quality dimensions corresponding to the multiple text contents according to multiple preset indicators includes:

[0169] Determining the relevance of the text content to each preset quality dimension based on the preset indicators corresponding to the text content;

[0170] A preset quality dimension with a correlation degree greater than or equal to a preset threshold is determined as the quality dimension corresponding to the text content.

[0171] According to one or more embodiments of the present disclosure, determining the text quality of the multiple text contents according to the levels of the quality dimensions corresponding to the multiple text contents and the multiple preset indicators includes:

[0172] Determine, according to the levels of the quality dimensions corresponding to the multiple text contents and the multiple preset indicators, a weight distribution of the quality dimensions corresponding to each text content, wherein the weight distribution includes a weight corresponding to the level of each quality dimension;

[0173] For any text content, the text quality of the text content is determined according to the level of the quality dimension corresponding to the text content and the weight distribution of the quality dimension corresponding to the text content.

[0174] According to one or more embodiments of the present disclosure, determining the text quality of the text content according to the level of the quality dimension corresponding to the text content and the weight distribution of the quality dimension corresponding to the text content includes:

[0175] Performing a weighted summation on the level of the quality dimension and the weight distribution to obtain a target parameter;

[0176] The text quality is determined according to the target parameter, and the text quality is proportional to the target parameter.

[0177] According to one or more embodiments of the present disclosure, after determining the target weight of the quality dimension corresponding to each text content, the method further includes:

[0178] Get the change of preset indicators;

[0179] Determining a change in the level of the quality dimension according to a change in the preset indicator and a weight distribution of the quality dimension;

[0180] The text content is updated according to the change in the level of the quality dimension.

[0181] In a second aspect, an embodiment of the present disclosure provides a text processing device, the text processing device comprising an acquisition module, a first determination module, a second determination module and a third determination module, wherein:

[0182] The acquisition module is used to acquire multiple text contents and a preset indicator corresponding to each text content;

[0183] The first determination module is used to determine the quality dimensions corresponding to the multiple text contents according to multiple preset indicators;

[0184] The second determination module is used to determine the levels of the quality dimensions corresponding to the multiple text contents;

[0185] The third determination module is used to determine the text quality of the multiple text contents according to the levels of the quality dimensions corresponding to the multiple text contents and the multiple preset indicators.

[0186] According to one or more embodiments of the present disclosure, the second determining module is specifically configured to:

[0187] Acquire a preset strategy, where the preset strategy includes a plurality of preset quality dimensions and a determination strategy related to each preset quality dimension, where the determination strategy is used to determine a level of the preset quality dimension;

[0188] According to the preset strategy and the text content, the level of the quality dimension corresponding to the text content is determined.

[0189] According to one or more embodiments of the present disclosure, the second determining module is specifically configured to:

[0190] Acquire a large language model, wherein the large language model includes a plurality of sub-models, and the sub-models are associated with preset quality dimensions;

[0191] The text content and the preset strategy are processed according to the target sub-model in the large language model to obtain the level of the quality dimension corresponding to the text content, and the preset quality dimension associated with the target sub-model is the same as the quality dimension corresponding to the text content.

[0192] According to one or more embodiments of the present disclosure, the first determining module is specifically configured to:

[0193] Determining the relevance of the text content to each preset quality dimension based on the preset indicators corresponding to the text content;

[0194] A preset quality dimension with a correlation degree greater than or equal to a preset threshold is determined as the quality dimension corresponding to the text content.

[0195] According to one or more embodiments of the present disclosure, the third determination module is specifically configured to:

[0196] Determine, according to the levels of the quality dimensions corresponding to the multiple text contents and the multiple preset indicators, a weight distribution of the quality dimensions corresponding to each text content, wherein the weight distribution includes a weight corresponding to the level of each quality dimension;

[0197] For any text content, the text quality of the text content is determined according to the level of the quality dimension corresponding to the text content and the weight distribution of the quality dimension corresponding to the text content.

[0198] According to one or more embodiments of the present disclosure, the third determination module is specifically configured to:

[0199] Performing a weighted summation on the level of the quality dimension and the weight distribution to obtain a target parameter;

[0200] The text quality is determined according to the target parameter, and the text quality is proportional to the target parameter.

[0201] According to one or more embodiments of the present disclosure, the text processing device further includes an updating module, wherein the updating module is used to:

[0202] Get the change of preset indicators;

[0203] Determining a change in the level of the quality dimension according to a change in the preset indicator and a weight distribution of the quality dimension;

[0204] The text content is updated according to the change in the level of the quality dimension.

[0205] In a third aspect, the present disclosure provides an electronic device comprising: a processor and a memory;

[0206] The memory stores computer-executable instructions;

[0207] The processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the text processing method as described in the first aspect and various possible aspects of the first aspect.

[0208] In a fourth aspect, the present disclosure provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer execution instructions. When a processor executes the computer execution instructions, the text processing method as described in the first aspect and various possible aspects of the first aspect are implemented.

[0209] In a fifth aspect, the present disclosure provides a computer program product, including a computer program, which, when executed by a processor, implements the text processing method as described in the first aspect and various possible aspects of the first aspect.

[0210] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0211] It is understood that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of the relevant laws and regulations. The data may include information, parameters and messages, such as flow switching indication information.

[0212] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

[0213] In addition, although each operation is depicted in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although several specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Certain features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination. Although the subject matter has been described in a language specific to structural features and / or method logic actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.

Claims

1. A text processing method, characterized in that: include: Obtain multiple text contents and preset indicators corresponding to each text content; Determining, according to a plurality of preset indicators, quality dimensions corresponding to the plurality of text contents, and determining levels of the quality dimensions corresponding to the plurality of text contents; The text qualities of the multiple text contents are determined according to the levels of the quality dimensions corresponding to the multiple text contents and the multiple preset indicators.

2. The method according to claim 1, characterized in that For any text content, the step of determining the levels of the quality dimensions corresponding to the multiple text contents includes: Acquire a preset strategy, where the preset strategy includes a plurality of preset quality dimensions and a determination strategy related to each preset quality dimension, where the determination strategy is used to determine a level of the preset quality dimension; According to the preset strategy and the text content, the level of the quality dimension corresponding to the text content is determined.

3. The method according to claim 2, characterized in that The step of determining the level of the quality dimension corresponding to the text content according to the preset strategy and the text content includes: Acquire a large language model, wherein the large language model includes a plurality of sub-models, and the sub-models are associated with preset quality dimensions; The text content and the preset strategy are processed according to the target sub-model in the large language model to obtain the level of the quality dimension corresponding to the text content, and the preset quality dimension associated with the target sub-model is the same as the quality dimension corresponding to the text content.

4. The method according to claim 1, characterized in that For any text content; according to multiple preset indicators, determine the quality dimensions corresponding to the multiple text contents, including: Determining the relevance of the text content to each preset quality dimension based on the preset indicators corresponding to the text content; A preset quality dimension with a correlation degree greater than or equal to a preset threshold is determined as the quality dimension corresponding to the text content.

5. The method according to any one of claims 1 to 4, characterized in that: Determining the text quality of the multiple text contents according to the levels of the quality dimensions corresponding to the multiple text contents and the multiple preset indicators includes: Determine, according to the levels of the quality dimensions corresponding to the multiple text contents and the multiple preset indicators, a weight distribution of the quality dimensions corresponding to each text content, wherein the weight distribution includes a weight corresponding to the level of each quality dimension; For any text content, the text quality of the text content is determined according to the level of the quality dimension corresponding to the text content and the weight distribution of the quality dimension corresponding to the text content.

6. The method according to claim 5, characterized in that Determining the text quality of the text content according to the level of the quality dimension corresponding to the text content and the weight distribution of the quality dimension corresponding to the text content includes: Performing a weighted summation on the level of the quality dimension and the weight distribution to obtain a target parameter; The text quality is determined according to the target parameter, and the text quality is proportional to the target parameter.

7. The method according to claim 5, characterized in that After determining the target weight of the quality dimension corresponding to each text content, the method further includes: Get the change of preset indicators; Determining a change in the level of the quality dimension according to a change in the preset indicator and a weight distribution of the quality dimension; The text content is updated according to the change in the level of the quality dimension.

8. A text processing device, characterized in that: It includes an acquisition module, a first determination module, a second determination module and a third determination module, wherein: The acquisition module is used to acquire multiple text contents and a preset indicator corresponding to each text content; The first determination module is used to determine the quality dimensions corresponding to the multiple text contents according to multiple preset indicators; The second determination module is used to determine the levels of the quality dimensions corresponding to the multiple text contents; The third determination module is used to determine the text quality of the multiple text contents according to the levels of the quality dimensions corresponding to the multiple text contents and the multiple preset indicators.

9. An electronic device, characterized in that: include: Processor and memory; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor executes the text processing method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions. When the processor executes the computer-executable instructions, the text processing method according to any one of claims 1 to 7 is implemented.

11. A computer program product, characterized in that It comprises a computer program, which, when executed by a processor, implements the text processing method according to any one of claims 1 to 7.

Images